StartDate: 2023-05-11 19:58:20+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 7bc86a78c0ac0290a6988a96c6457910b8c51242 CommitTime: 2023-05-11 10:42:13 +0200 CommitAuthor: Mathieu Taillefumier CommitSubject: [toolchain] Fix a cosma build issue #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=7bc86a78c0ac0290a6988a96c6457910b8c51242 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 368.4MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu dbf6a9befcde: Pulling fs layer dbf6a9befcde: Verifying Checksum dbf6a9befcde: Download complete dbf6a9befcde: Pull complete Digest: sha256:dfd64a3b4296d8c9b62aa3309984f8620b98d87e47492599ee20739e8eb54fbf Status: Downloaded newer image for ubuntu:22.04 ---> 3b418d7b466a Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 619f01a4797f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 0fd24d6c852f Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> e7e4b42ee3f5 Step 5/42 : RUN mkdir scripts ---> Using cache ---> 0a29c146d904 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 ---> 4670a3abe39c Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 5a9f0a9db405 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 9d05574e9905 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 4d21ad59cc0c Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 7f38356a5ef8 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> f7f19fb679bf Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> b1b8cd3b860c Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 0f83aebf2b45 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 790ebf267fac Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 4e227f21a831 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 87bcc482f688 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> d91028d1a469 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 2552a3738917 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> da845ce975af Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 3c7ce6ff4c65 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> a22e842d9331 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> e2f946f01bab Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 9ea36a7f5e89 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 1bfb7b8cf7ac Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 89add6a91ec9 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> f7b52fc75b23 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> b2e60927a921 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 8df1e6c0de20 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> ba7e2a063506 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 332ee870b583 Step 31/42 : COPY ./src ./src ---> Using cache ---> 844488519a47 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 50f7ce3907ed Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 15fabf0375f4 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 c0bc9600e9ea './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container c0bc9600e9ea ---> f60662882f8c Step 35/42 : COPY ./data ./data ---> a5d729f0b229 Step 36/42 : COPY ./tests ./tests ---> ee83d6b2cd00 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 793da8e31df5 Step 38/42 : COPY ./benchmarks ./benchmarks ---> ae27a9f79a5e Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> a7036a66a662 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 98971b35f314 ========== 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 0.035 0.035 89.051 89.051 qs_mol_dyn_low 1 2.0 0.003 0.003 88.379 88.379 qs_forces 11 3.9 0.001 0.001 88.339 88.339 qs_energies 11 4.9 0.001 0.001 82.110 82.110 scf_env_do_scf 11 5.9 0.001 0.001 70.906 70.906 velocity_verlet 10 3.0 0.002 0.002 58.135 58.135 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 53.905 53.905 rebuild_ks_matrix 119 8.3 0.001 0.001 20.503 20.503 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.503 20.503 dbcsr_multiply_generic 2286 12.5 0.173 0.173 19.879 19.879 qs_scf_new_mos 108 7.5 0.001 0.001 19.717 19.717 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.716 19.716 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.121 19.121 calculate_rho_elec 119 8.7 0.961 0.961 19.121 19.121 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.787 18.787 ot_scf_mini 108 9.5 0.002 0.002 18.303 18.303 init_scf_loop 11 6.9 0.000 0.000 16.877 16.877 grid_collocate_task_list 119 9.7 14.955 14.955 14.955 14.955 prepare_preconditioner 11 7.9 0.000 0.000 14.437 14.437 make_preconditioner 11 8.9 0.000 0.000 14.436 14.436 sum_up_and_integrate 119 10.3 0.795 0.795 13.379 13.379 make_full_inverse_cholesky 11 9.9 0.016 0.016 13.306 13.306 integrate_v_rspace 119 11.3 0.095 0.095 12.584 12.584 ot_mini 108 10.5 0.001 0.001 11.954 11.954 make_m2s 4572 13.5 0.047 0.047 11.027 11.027 grid_integrate_task_list 119 12.3 10.581 10.581 10.581 10.581 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.662 6.662 qs_ot_get_derivative 108 11.5 0.001 0.001 6.501 6.501 pw_transfer 1439 11.6 0.064 0.064 5.850 5.850 dbcsr_make_dense_low 5837 15.5 0.081 0.081 5.816 5.816 make_dense_data 5837 16.5 5.153 5.153 5.721 5.721 make_images 4572 14.5 2.221 2.221 5.654 5.654 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.631 5.631 ot_diis_step 108 11.5 0.004 0.004 5.449 5.449 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.016 5.016 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 4.965 4.965 apply_single 119 13.6 0.000 0.000 4.965 4.965 cp_fm_cholesky_decompose 22 10.9 4.962 4.962 4.962 4.962 multiply_cannon 2286 13.5 0.178 0.178 4.909 4.909 fft_wrap_pw1pw2_140 487 13.2 0.481 0.481 4.829 4.829 multiply_cannon_loop 2286 14.5 0.073 0.073 4.446 4.446 multiply_cannon_multrec 2286 15.5 4.322 4.322 4.373 4.373 cp_fm_cholesky_invert 11 10.9 4.236 4.236 4.236 4.236 init_scf_run 11 5.9 0.002 0.002 3.927 3.927 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.925 3.925 dbcsr_copy 2102 12.0 0.241 0.241 3.803 3.803 dbcsr_complete_redistribute 329 12.2 1.931 1.931 3.788 3.788 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.641 3.641 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.543 3.543 dbcsr_copy_into_existing 22 7.9 3.519 3.519 3.520 3.520 wfi_extrapolate 11 7.9 0.001 0.001 3.392 3.392 qs_create_task_list 11 7.9 0.000 0.000 3.256 3.256 generate_qs_task_list 11 8.9 1.960 1.960 3.256 3.256 density_rs2pw 119 9.7 0.005 0.005 3.205 3.205 copy_dbcsr_to_fm 153 11.3 0.003 0.003 3.045 3.045 qs_ot_get_p 119 10.4 0.001 0.001 2.972 2.972 fft3d_s 1202 14.6 2.865 2.865 2.869 2.869 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.684 2.684 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.590 2.590 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.390 2.390 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 2.209 2.209 dbcsr_data_release 279534 16.0 2.037 2.037 2.037 2.037 pw_poisson_solve 119 10.3 0.340 0.340 1.979 1.979 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.919 1.919 potential_pw2rs 119 12.3 0.046 0.046 1.908 1.908 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.895 1.895 dbcsr_finalize 5186 13.8 0.107 0.107 1.839 1.839 ------------------------------------------------------------------------------- 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 0.022 44.992 45.002 qs_mol_dyn_low 1 2.0 0.003 0.004 44.862 44.866 qs_forces 11 3.9 0.001 0.002 44.821 44.821 qs_energies 11 4.9 0.001 0.001 41.832 41.835 scf_env_do_scf 11 5.9 0.000 0.002 38.203 38.203 scf_env_do_scf_inner_loop 108 6.5 0.003 0.019 35.279 35.279 velocity_verlet 10 3.0 0.002 0.003 26.900 26.902 rebuild_ks_matrix 119 8.3 0.000 0.001 16.231 16.347 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.017 16.231 16.346 qs_ks_update_qs_env 119 7.6 0.001 0.001 14.386 14.490 qs_rho_update_rho_low 119 7.7 0.001 0.001 13.422 13.437 calculate_rho_elec 119 8.7 0.030 0.032 13.421 13.436 dbcsr_multiply_generic 2286 12.5 0.073 0.077 12.833 13.036 sum_up_and_integrate 119 10.3 0.032 0.035 12.067 12.094 integrate_v_rspace 119 11.3 0.004 0.005 12.035 12.064 qs_scf_new_mos 108 7.5 0.001 0.001 10.166 10.356 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.166 10.356 multiply_cannon 2286 13.5 0.150 0.169 9.444 9.844 ot_scf_mini 108 9.5 0.002 0.002 9.540 9.725 multiply_cannon_loop 2286 14.5 0.085 0.099 8.911 9.376 grid_collocate_task_list 119 9.7 9.054 9.364 9.054 9.364 mp_waitall_1 158411 16.6 7.370 8.303 7.370 8.303 grid_integrate_task_list 119 12.3 8.081 8.287 8.081 8.287 multiply_cannon_metrocomm3 18288 15.5 0.035 0.039 5.130 6.151 ot_mini 108 10.5 0.001 0.001 5.598 5.799 rs_pw_transfer 974 11.9 0.010 0.014 4.251 4.559 density_rs2pw 119 9.7 0.005 0.006 3.750 4.089 pw_transfer 1439 11.6 0.096 0.104 3.909 4.031 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.745 3.851 fft_wrap_pw1pw2_140 487 13.2 0.605 0.776 3.179 3.386 potential_pw2rs 119 12.3 0.006 0.007 3.328 3.362 multiply_cannon_multrec 18288 15.5 2.934 3.201 2.944 3.211 qs_ot_get_derivative 108 11.5 0.001 0.001 2.877 3.064 init_scf_loop 11 6.9 0.000 0.000 2.911 2.912 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.575 2.705 apply_single 119 13.6 0.000 0.000 2.575 2.704 ot_diis_step 108 11.5 0.003 0.004 2.698 2.698 fft3d_ps 1201 14.6 1.227 1.352 2.399 2.597 init_scf_run 11 5.9 0.000 0.004 2.592 2.593 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.592 2.592 make_m2s 4572 13.5 0.044 0.046 2.213 2.307 wfi_extrapolate 11 7.9 0.001 0.001 2.233 2.234 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.979 1.992 make_images 4572 14.5 0.114 0.119 1.900 1.988 mp_waitany 9880 13.7 1.347 1.748 1.347 1.748 qs_ot_get_p 119 10.4 0.001 0.001 1.216 1.469 mp_sum_l 11298 13.2 0.746 1.383 0.746 1.383 multiply_cannon_metrocomm1 18288 15.5 0.017 0.020 0.561 1.327 mp_alltoall_z22v 1201 16.6 0.948 1.291 0.948 1.291 rs_pw_transfer_PW2RS_140 130 13.9 0.318 0.404 1.192 1.274 rs_pw_transfer_RS2PW_140 130 11.5 0.185 0.232 0.970 1.269 make_images_data 4572 15.5 0.033 0.036 1.079 1.261 mp_sum_d 4135 12.0 0.722 1.233 0.722 1.233 prepare_preconditioner 11 7.9 0.000 0.000 1.132 1.163 make_preconditioner 11 8.9 0.000 0.000 1.132 1.163 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.026 1.054 hybrid_alltoall_any 4725 16.4 0.055 0.202 0.922 1.054 mp_alltoall_d11v 2130 13.8 0.810 1.050 0.810 1.050 rs_pw_transfer_PW2RS_50 119 14.3 0.263 0.335 0.844 1.020 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.914 1.013 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.922 1.000 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.864 0.946 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.922 0.924 ------------------------------------------------------------------------------- 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=49.078, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.955, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.581, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.153, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.962, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.322, 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=16.205999999999996, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.054, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.081, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.934, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.37, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.347, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.031 0.031 113.773 113.773 qs_mol_dyn_low 1 2.0 0.003 0.003 113.078 113.078 qs_forces 11 3.9 0.001 0.001 113.038 113.038 qs_energies 11 4.9 0.001 0.001 105.101 105.101 scf_env_do_scf 11 5.9 0.001 0.001 91.750 91.750 velocity_verlet 10 3.0 0.002 0.002 73.427 73.427 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 72.748 72.748 rebuild_ks_matrix 107 8.3 0.001 0.001 34.200 34.200 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 34.199 34.199 qs_rho_update_rho_low 107 7.7 0.001 0.001 31.413 31.413 calculate_rho_elec 107 8.7 0.853 0.853 31.413 31.413 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.707 30.707 grid_collocate_task_list 107 9.7 27.442 27.442 27.442 27.442 sum_up_and_integrate 107 10.3 0.724 0.724 27.148 27.148 integrate_v_rspace 107 11.3 0.105 0.105 26.423 26.423 grid_integrate_task_list 107 12.3 24.562 24.562 24.562 24.562 init_scf_loop 11 6.9 0.000 0.000 18.849 18.849 dbcsr_multiply_generic 1966 12.4 0.146 0.146 18.336 18.336 qs_scf_new_mos 96 7.5 0.001 0.001 17.444 17.444 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.444 17.444 ot_scf_mini 96 9.5 0.002 0.002 16.263 16.263 prepare_preconditioner 11 7.9 0.000 0.000 14.754 14.754 make_preconditioner 11 8.9 0.000 0.000 14.754 14.754 make_full_inverse_cholesky 11 9.9 0.032 0.032 13.556 13.556 ot_mini 96 10.5 0.001 0.001 10.531 10.531 make_m2s 3932 13.4 0.040 0.040 9.988 9.988 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.325 7.325 pw_transfer 1295 11.6 0.059 0.059 5.730 5.730 qs_ot_get_derivative 96 11.5 0.001 0.001 5.649 5.649 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.520 5.520 init_scf_run 11 5.9 0.002 0.002 5.374 5.374 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.372 5.372 dbcsr_make_dense_low 4961 15.5 0.059 0.059 5.209 5.209 make_dense_data 4961 16.5 4.708 4.708 5.139 5.139 make_images 3932 14.4 1.974 1.974 5.126 5.126 cp_fm_cholesky_decompose 22 10.9 4.911 4.911 4.911 4.911 ot_diis_step 96 11.5 0.003 0.003 4.878 4.878 fft_wrap_pw1pw2_140 439 13.2 0.536 0.536 4.792 4.792 wfi_extrapolate 11 7.9 0.001 0.001 4.765 4.765 dbcsr_make_images_dense 3386 14.7 0.014 0.014 4.581 4.581 multiply_cannon 1966 13.4 0.189 0.189 4.569 4.569 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.555 4.555 apply_single 107 13.6 0.000 0.000 4.555 4.555 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.375 4.375 cp_fm_cholesky_invert 11 10.9 4.366 4.366 4.366 4.366 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.140 4.140 multiply_cannon_loop 1966 14.4 0.035 0.035 4.078 4.078 multiply_cannon_multrec 1966 15.4 3.998 3.998 4.041 4.041 dbcsr_copy 1855 11.9 0.225 0.225 3.905 3.905 dbcsr_complete_redistribute 317 12.2 1.927 1.927 3.754 3.754 qs_create_task_list 11 7.9 0.000 0.000 3.682 3.682 generate_qs_task_list 11 8.9 2.381 2.381 3.682 3.682 dbcsr_copy_into_existing 22 7.9 3.621 3.621 3.621 3.621 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.559 3.559 density_rs2pw 107 9.7 0.004 0.004 3.118 3.118 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.033 3.033 fft3d_s 1082 14.6 2.816 2.816 2.820 2.820 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.763 2.763 qs_ot_get_p 107 10.4 0.001 0.001 2.536 2.536 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.385 2.385 ------------------------------------------------------------------------------- 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 0.021 70.942 70.952 qs_mol_dyn_low 1 2.0 0.003 0.003 70.814 70.818 qs_forces 11 3.9 0.002 0.002 70.773 70.774 qs_energies 11 4.9 0.001 0.001 66.011 66.013 scf_env_do_scf 11 5.9 0.000 0.002 61.029 61.029 scf_env_do_scf_inner_loop 96 6.5 0.002 0.016 56.473 56.474 velocity_verlet 10 3.0 0.002 0.003 42.210 42.211 rebuild_ks_matrix 107 8.3 0.000 0.001 30.560 30.653 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.016 30.560 30.653 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.897 26.979 sum_up_and_integrate 107 10.3 0.031 0.035 26.678 26.710 integrate_v_rspace 107 11.3 0.004 0.005 26.647 26.681 qs_rho_update_rho_low 107 7.7 0.001 0.001 26.079 26.083 calculate_rho_elec 107 8.7 0.027 0.029 26.078 26.083 grid_integrate_task_list 107 12.3 22.719 23.077 22.719 23.077 grid_collocate_task_list 107 9.7 21.915 22.340 21.915 22.340 dbcsr_multiply_generic 1966 12.4 0.065 0.070 11.997 12.166 multiply_cannon 1966 13.4 0.133 0.147 8.966 9.433 qs_scf_new_mos 96 7.5 0.001 0.001 9.246 9.341 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.245 9.341 multiply_cannon_loop 1966 14.4 0.080 0.098 8.518 8.878 ot_scf_mini 96 9.5 0.002 0.002 8.686 8.773 mp_waitall_1 136719 16.5 7.136 7.931 7.136 7.931 multiply_cannon_metrocomm3 15728 15.4 0.032 0.038 5.056 5.820 ot_mini 96 10.5 0.001 0.001 5.082 5.181 rs_pw_transfer 878 11.9 0.009 0.012 4.209 4.830 init_scf_loop 11 6.9 0.000 0.000 4.543 4.543 density_rs2pw 107 9.7 0.005 0.006 3.618 4.287 init_scf_run 11 5.9 0.000 0.004 3.948 3.948 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.947 3.948 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.782 3.794 pw_transfer 1295 11.6 0.087 0.096 3.561 3.669 wfi_extrapolate 11 7.9 0.001 0.001 3.587 3.587 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 3.413 3.509 potential_pw2rs 107 12.3 0.006 0.007 3.148 3.177 fft_wrap_pw1pw2_140 439 13.2 0.557 0.735 2.907 3.100 multiply_cannon_multrec 15728 15.4 2.713 3.076 2.722 3.087 qs_ot_get_derivative 96 11.5 0.001 0.001 2.610 2.696 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.448 2.540 apply_single 107 13.6 0.000 0.000 2.448 2.540 ot_diis_step 96 11.5 0.003 0.003 2.454 2.454 fft3d_ps 1081 14.6 1.117 1.273 2.171 2.372 mp_waitany 8968 13.7 1.490 2.151 1.490 2.151 make_m2s 3932 13.4 0.039 0.047 2.072 2.131 make_images 3932 14.4 0.102 0.107 1.790 1.847 rs_pw_transfer_RS2PW_140 118 11.5 0.171 0.209 1.095 1.725 mp_alltoall_d11v 1998 13.7 0.937 1.604 0.937 1.604 ------------------------------------------------------------------------------- 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=43.78599999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.442, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.562, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.911, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.708, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.366, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.998, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_nonortho_timings_32mpi", title="Timings of H2O-64_nonortho with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="rest", label="rest", y=14.968999999999987, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.915, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.719, 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="make_dense_data", label="make_dense_data", 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=2.713, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.136, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.49, 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 0.199 0.199 105.507 105.507 qs_energies 1 2.0 0.000 0.000 104.635 104.635 scf_env_do_scf 1 3.0 0.000 0.000 103.395 103.395 qs_ks_update_qs_env 8 5.0 0.000 0.000 98.270 98.270 rebuild_ks_matrix 7 6.0 0.000 0.000 98.214 98.214 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 98.214 98.214 hfx_ks_matrix 7 8.0 0.000 0.000 89.258 89.258 integrate_four_center 7 9.0 1.719 1.719 89.229 89.229 integrate_four_center_main 7 10.0 0.742 0.742 81.523 81.523 integrate_four_center_bin 448 11.0 80.781 80.781 80.781 80.781 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.506 56.506 init_scf_loop 1 4.0 0.000 0.000 46.879 46.879 integrate_four_center_load 7 10.0 0.000 0.000 5.723 5.723 hfx_load_balance 1 11.0 0.013 0.013 5.723 5.723 qs_vxc_create 14 8.0 0.000 0.000 3.098 3.098 xc_vxc_pw_create 14 9.0 0.116 0.116 3.098 3.098 hfx_load_balance_bin 1 12.0 2.848 2.848 2.848 2.848 hfx_load_balance_count 1 12.0 2.845 2.845 2.845 2.845 prepare_preconditioner 1 5.0 0.000 0.000 2.481 2.481 make_preconditioner 1 6.0 0.000 0.000 2.481 2.481 calculate_rho_elec 15 7.4 0.119 0.119 2.462 2.462 xc_rho_set_and_dset_create 14 10.0 0.095 0.095 2.391 2.391 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.372 2.372 ------------------------------------------------------------------------------- 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 0.222 0.243 96.292 96.305 qs_energies 1 2.0 0.000 0.000 95.896 95.903 scf_env_do_scf 1 3.0 0.000 0.000 95.560 95.561 qs_ks_update_qs_env 8 5.0 0.000 0.000 93.515 93.516 rebuild_ks_matrix 7 6.0 0.000 0.000 93.508 93.508 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 93.508 93.508 hfx_ks_matrix 7 8.0 0.000 0.000 88.055 88.057 integrate_four_center 7 9.0 0.053 0.331 88.047 88.048 integrate_four_center_main 7 10.0 0.003 0.004 80.088 81.398 integrate_four_center_bin 448 11.0 80.084 81.395 80.084 81.395 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 53.503 53.503 init_scf_loop 1 4.0 0.000 0.000 42.056 42.057 integrate_four_center_load 7 10.0 0.000 0.000 5.657 5.658 hfx_load_balance 1 11.0 0.001 0.001 5.657 5.658 mp_sync 56 11.2 1.633 2.919 1.633 2.919 hfx_load_balance_count 1 12.0 2.777 2.828 2.777 2.828 hfx_load_balance_bin 1 12.0 2.776 2.826 2.776 2.826 qs_vxc_create 14 8.0 0.000 0.000 2.458 2.459 xc_vxc_pw_create 14 9.0 0.007 0.008 2.458 2.458 xc_rho_set_and_dset_create 14 10.0 0.009 0.010 1.950 2.063 ------------------------------------------------------------------------------- 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=16.373000000000005, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.781, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.848, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.845, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.719, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.742, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.199, 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=8.744000000000014, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.084, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.776, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.777, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.053, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.222, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=1.633, 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 77.888 77.888 qs_energies 1 2.0 0.000 0.000 77.457 77.457 mp2_main 1 3.0 0.000 0.000 74.642 74.642 mp2_gpw_main 1 4.0 0.000 0.000 74.538 74.538 rpa_ri_compute_en 1 5.0 0.000 0.000 70.780 70.780 rpa_num_int 1 6.0 0.001 0.001 70.774 70.774 compute_mat_P_omega 1 7.0 0.003 0.003 60.825 60.825 compute_mat_P_omega_contract 10 8.0 9.007 9.007 60.618 60.618 dbt_total 2336 9.6 0.014 0.014 46.696 46.696 dbt_contract 787 11.0 0.042 0.042 39.726 39.726 dbt_tas_total 1149 12.2 0.209 0.209 38.545 38.545 dbt_tas_multiply 807 12.1 0.002 0.002 37.342 37.342 dbt_tas_dbm 807 14.1 0.003 0.003 30.881 30.881 dbm_multiply 807 16.1 30.872 30.872 30.872 30.872 dbt_tas_mm_1N 524 15.1 0.001 0.001 23.362 23.362 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 21.934 21.934 compute_mat_P_omega_calc_M_occ 250 9.0 9.008 9.008 17.053 17.053 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.076 7.076 dbt_tas_mm_2 251 15.0 0.001 0.001 6.018 6.018 dbt_copy 1103 10.7 0.073 0.073 5.749 5.749 compute_QP_energies 1 7.0 0.000 0.000 4.995 4.995 compute_self_energy_cubic_gw 1 8.0 0.053 0.053 4.994 4.994 contract_cubic_gw 21 9.0 0.000 0.000 3.977 3.977 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.751 3.751 dbt_tas_reserve_blocks_index 3261 14.3 0.484 0.484 3.680 3.680 dbm_reserve_blocks 3628 15.3 3.265 3.265 3.265 3.265 dbt_reserve_blocks_index 2280 13.1 0.053 0.053 2.769 2.769 dbt_reserve_blocks_index_array 2222 12.2 0.008 0.008 2.724 2.724 scf_env_do_scf 1 3.0 0.000 0.000 2.709 2.709 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.709 2.709 convert_to_new_pgrid 2421 14.1 0.092 0.092 2.493 2.493 dbm_copy 1614 15.1 2.401 2.401 2.401 2.401 dbt_tas_copy 574 11.4 1.338 1.338 2.297 2.297 dbt_crop 1042 12.0 1.401 1.401 2.267 2.267 compute_W_cubic_GW 10 7.0 0.009 0.009 2.029 2.029 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.996 1.996 dbt_reshape 278 11.9 1.061 1.061 1.942 1.942 dbt_tas_reshape 367 15.0 0.007 0.007 1.849 1.849 get_2c_integrals 1 6.0 0.000 0.000 1.812 1.812 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.577 1.577 ------------------------------------------------------------------------------- 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 31.787 31.798 qs_energies 1 2.0 0.000 0.000 31.685 31.686 mp2_main 1 3.0 0.000 0.000 30.765 30.767 mp2_gpw_main 1 4.0 0.000 0.000 30.734 30.736 rpa_ri_compute_en 1 5.0 0.000 0.000 29.469 29.471 rpa_num_int 1 6.0 0.000 0.002 29.469 29.470 dbt_total 2336 9.6 0.015 0.015 26.145 26.153 compute_mat_P_omega 1 7.0 0.001 0.005 24.995 25.019 compute_mat_P_omega_contract 10 8.0 0.385 0.416 24.873 24.878 dbt_contract 787 11.0 0.038 0.039 19.276 19.280 dbt_tas_total 1149 12.2 0.072 0.081 17.102 17.103 dbt_tas_multiply 807 12.1 0.002 0.002 17.040 17.042 dbt_tas_dbm 807 14.1 0.003 0.003 12.942 12.945 dbm_multiply 807 16.1 10.172 10.935 10.172 10.935 compute_mat_P_omega_calc_M_occ 250 9.0 0.373 0.404 7.338 7.339 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.221 7.222 dbt_copy 1149 10.8 0.013 0.014 6.095 6.363 dbt_reshape 1136 11.8 2.588 2.805 5.818 6.068 dbt_tas_mm_2 251 15.0 0.001 0.001 6.002 6.003 mp_sync 8688 11.6 4.464 5.739 4.464 5.739 dbt_tas_mm_1N 524 15.1 0.001 0.001 4.611 5.404 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.250 5.251 compute_QP_energies 1 7.0 0.000 0.000 2.805 2.806 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 2.804 2.805 mp_waitall_2 3812 15.3 2.384 2.589 2.384 2.589 dbt_communicate_buffer 1136 12.8 0.050 0.054 2.407 2.538 contract_cubic_gw 21 9.0 0.000 0.000 2.197 2.205 dbt_reserve_blocks_index 2887 13.1 0.066 0.073 1.725 2.035 dbt_reserve_blocks_index_array 2829 12.2 0.007 0.009 1.715 2.024 dbt_tas_reserve_blocks_index 3347 14.5 0.432 0.469 1.707 2.012 dbm_reserve_blocks 3752 15.4 1.363 1.640 1.363 1.640 dbt_crop 1042 12.0 0.857 0.958 1.380 1.591 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 1.263 1.264 dbt_tas_replicate 405 14.1 0.542 0.718 1.078 1.156 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.063 1.066 parallel_gemm_fm 105 8.4 0.000 0.000 1.006 1.014 parallel_gemm_fm_cosma 105 9.4 1.006 1.014 1.006 1.014 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.994 0.996 convert_to_new_pgrid 2421 14.1 0.024 0.030 0.749 0.911 dbm_copy 1608 15.1 0.720 0.882 0.720 0.882 scf_env_do_scf 1 3.0 0.000 0.000 0.882 0.882 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.882 0.882 compute_W_cubic_GW 10 7.0 0.001 0.001 0.753 0.761 mp_max_i 2002 9.8 0.543 0.743 0.543 0.743 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 0.650 0.650 ------------------------------------------------------------------------------- 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=22.274000000000008, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=30.872, 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=9.008, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=9.007, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.265, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.401, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.061, 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=9.338000000000001, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.172, 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=0.373, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.385, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.363, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.72, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.588, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.464, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.384, 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 0.019 266.544 266.544 qs_forces 1 2.0 0.000 0.000 265.951 265.951 rebuild_ks_matrix 7 6.6 0.000 0.000 264.412 264.412 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 264.412 264.412 hfx_ks_matrix 7 8.6 0.000 0.000 262.609 262.609 hfx_ri_update_ks 7 9.6 0.000 0.000 226.018 226.018 hfx_ri_update_ks_Pmat 7 10.6 31.196 31.196 226.013 226.013 dbt_total 783 11.1 0.006 0.006 208.465 208.465 qs_energies 1 3.0 0.000 0.000 199.001 199.001 scf_env_do_scf 1 4.0 0.000 0.000 198.710 198.710 qs_ks_update_qs_env 8 6.0 0.000 0.000 197.515 197.515 dbt_contract 207 12.4 0.061 0.061 189.733 189.733 dbt_tas_total 317 14.0 1.698 1.698 187.611 187.611 dbt_tas_multiply 216 13.5 0.001 0.001 184.474 184.474 dbt_tas_dbm 216 15.5 0.001 0.001 175.491 175.491 dbm_multiply 216 17.5 175.488 175.488 175.488 175.488 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 170.202 170.202 dbt_tas_mm_2 91 16.5 0.001 0.001 161.967 161.967 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 125.034 125.034 init_scf_loop 2 5.0 0.000 0.000 73.669 73.669 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 66.900 66.900 hfx_ri_update_forces 1 7.0 1.543 1.543 36.588 36.588 hfx_ri_forces_Pmat_3c 1 8.0 4.631 4.631 19.493 19.493 dbt_copy 409 11.7 0.029 0.029 15.588 15.588 precalc_derivatives 1 8.0 2.143 2.143 13.152 13.152 dbt_reshape 132 13.2 6.786 6.786 10.974 10.974 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.637 9.637 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.286 9.286 dbt_tas_reserve_blocks_index 1229 15.4 1.016 1.016 7.834 7.834 build_3c_derivatives 3 9.0 2.733 2.733 7.266 7.266 dbm_reserve_blocks 1345 16.4 6.922 6.922 6.922 6.922 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.882 6.882 dbt_reserve_blocks_index 818 14.4 0.093 0.093 6.195 6.195 dbt_reserve_blocks_index_array 795 13.4 0.007 0.007 6.089 6.089 ------------------------------------------------------------------------------- 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 45.321 45.329 qs_forces 1 2.0 0.000 0.000 45.172 45.172 rebuild_ks_matrix 7 6.6 0.000 0.000 44.472 44.473 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 44.472 44.472 hfx_ks_matrix 7 8.6 0.000 0.000 43.438 43.446 dbt_total 783 11.1 0.006 0.006 38.622 38.623 dbt_contract 207 12.4 0.024 0.025 29.770 29.784 hfx_ri_update_ks 7 9.6 0.000 0.000 26.756 26.756 hfx_ri_update_ks_Pmat 7 10.6 1.204 1.255 26.755 26.755 dbt_tas_total 317 14.0 0.042 0.058 26.173 26.173 dbt_tas_multiply 216 13.5 0.001 0.001 26.080 26.080 qs_energies 1 3.0 0.000 0.000 25.151 25.151 scf_env_do_scf 1 4.0 0.000 0.001 25.006 25.006 qs_ks_update_qs_env 8 6.0 0.000 0.000 24.462 24.463 dbt_tas_dbm 216 15.5 0.001 0.001 21.840 21.845 dbm_multiply 216 17.5 19.456 20.407 19.456 20.407 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 20.011 20.011 hfx_ri_update_forces 1 7.0 0.055 0.058 16.682 16.690 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 14.277 14.277 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 12.435 12.435 hfx_ri_forces_Pmat_3c 1 8.0 0.153 0.164 11.964 11.964 init_scf_loop 2 5.0 0.000 0.000 10.728 10.728 dbt_tas_mm_2 91 16.5 0.001 0.001 10.582 10.586 dbt_copy 497 12.3 0.011 0.013 8.290 8.656 dbt_reshape 365 13.6 3.498 3.640 6.428 6.717 mp_sync 2665 13.0 4.449 6.449 4.449 6.449 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.420 6.155 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.844 4.845 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.933 4.198 precalc_derivatives 1 8.0 0.077 0.083 3.600 3.600 dbt_tas_reserve_blocks_index 1356 15.8 0.889 0.952 3.062 3.528 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.134 3.134 dbt_reserve_blocks_index 1051 14.7 0.107 0.114 2.549 2.916 dbt_reserve_blocks_index_array 1028 13.8 0.005 0.006 2.521 2.888 dbm_reserve_blocks 1481 16.7 2.239 2.699 2.239 2.699 dbt_crop 372 13.7 1.710 1.762 2.464 2.617 mp_waitall_2 1138 16.4 2.097 2.224 2.097 2.224 build_3c_derivatives 3 9.0 0.222 0.242 2.038 2.046 dbt_communicate_buffer 365 14.6 0.012 0.014 1.859 1.976 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.642 1.643 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.566 1.571 convert_to_new_pgrid 648 15.5 0.032 0.059 1.292 1.475 dbt_tas_copy 132 12.5 0.606 0.647 1.186 1.328 dbm_copy 452 16.3 1.131 1.318 1.131 1.318 ------------------------------------------------------------------------------- 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=41.52099999999999, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=175.488, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.196, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=6.922, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", 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=4.631, 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=12.224999999999994, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=19.456, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.204, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.239, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.498, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.153, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.449, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.097, 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 0.015 173.180 173.180 qs_energies 1 2.0 0.000 0.000 172.982 172.982 mp2_main 1 3.0 0.000 0.000 168.168 168.168 mp2_gpw_main 1 4.0 0.001 0.001 167.757 167.757 mp2_ri_gpw_compute_in 1 5.0 0.391 0.391 121.257 121.257 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 112.656 112.656 mp2_eri_3c_integrate_gpw 2656 7.0 0.014 0.014 82.020 82.020 integrate_v_rspace 2666 8.0 0.630 0.630 69.048 69.048 grid_integrate_task_list 2666 9.0 66.175 66.175 66.175 66.175 mp2_ri_gpw_compute_en 1 5.0 0.091 0.091 46.476 46.476 mp2_ri_gpw_compute_en_RI_loop 1 6.0 10.190 10.190 44.572 44.572 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.056 2.056 27.066 27.066 local_gemm 2080 8.0 25.010 25.010 25.010 25.010 dbcsr_multiply_generic 5322 8.0 0.173 0.173 21.288 21.288 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 21.268 21.268 pw_transfer 63872 10.6 1.033 1.033 11.772 11.772 calculate_wavefunction 2656 8.0 8.124 8.124 11.678 11.678 multiply_cannon 5322 9.0 0.439 0.439 10.853 10.853 fft_wrap_pw1pw2 53228 11.4 0.113 0.113 10.533 10.533 multiply_cannon_loop 5322 10.0 0.123 0.123 9.502 9.502 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.351 2.351 9.252 9.252 get_2c_integrals 1 6.0 0.000 0.000 8.209 8.209 make_m2s 10644 9.0 0.062 0.062 8.148 8.148 multiply_cannon_multrec 5322 11.0 7.929 7.929 7.969 7.969 make_images 10644 10.0 3.084 3.084 7.849 7.849 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 7.497 7.497 fft_wrap_pw1pw2_20 21271 12.4 0.473 0.473 7.395 7.395 compute_2c_integrals 1 7.0 0.005 0.005 7.388 7.388 compute_2c_integrals_loop_lm 1 8.0 0.011 0.011 7.377 7.377 mp2_eri_2c_integrate_gpw 1 9.0 0.804 0.804 7.366 7.366 fft3d_s 53229 13.4 6.465 6.465 6.498 6.498 dbcsr_complete_redistribute 2689 9.0 1.091 1.091 5.754 5.754 dbcsr_finalize 10708 9.5 0.208 0.208 5.360 5.360 mp2_ri_gpw_compute_en_ener 2080 7.0 5.350 5.350 5.350 5.350 dbcsr_merge_all 8011 10.3 3.602 3.602 4.668 4.668 scf_env_do_scf 1 3.0 0.000 0.000 4.402 4.402 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.401 4.401 potential_pw2rs 5322 10.0 0.149 0.149 4.118 4.118 ------------------------------------------------------------------------------- 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 35.451 35.462 qs_energies 1 2.0 0.000 0.001 35.346 35.347 mp2_main 1 3.0 0.000 0.001 33.539 33.540 mp2_gpw_main 1 4.0 0.001 0.002 33.450 33.451 mp2_ri_gpw_compute_in 1 5.0 0.052 0.053 17.110 17.320 mp2_ri_gpw_compute_en 1 5.0 0.197 0.210 16.247 16.441 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.914 16.120 mp2_ri_gpw_compute_en_RI_loop 1 6.0 1.410 1.683 15.294 15.301 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.892 14.095 integrate_v_rspace 93 8.1 0.098 0.104 13.755 13.965 grid_integrate_task_list 93 9.1 13.466 13.674 13.466 13.674 mp2_ri_gpw_compute_en_expansio 65 7.0 0.108 0.141 11.011 11.186 local_gemm 65 8.0 10.903 11.053 10.903 11.053 mp2_ri_gpw_compute_en_comm 20 7.0 0.071 0.113 2.528 3.076 mp_sendrecv_dm3 1240 8.0 2.017 2.734 2.017 2.734 dbcsr_multiply_generic 176 8.0 0.008 0.008 1.718 1.878 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.702 1.864 scf_env_do_scf 1 3.0 0.000 0.000 1.690 1.690 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.689 1.690 get_2c_integrals 1 6.0 0.004 0.013 1.113 1.147 multiply_cannon 176 9.0 0.016 0.018 1.035 1.102 multiply_cannon_loop 176 10.0 0.002 0.002 0.976 1.043 multiply_cannon_multrec 246 11.0 0.845 0.884 0.850 0.889 compute_2c_integrals 1 7.0 0.002 0.005 0.841 0.855 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.755 0.777 mp2_eri_2c_integrate_gpw 1 9.0 0.195 0.200 0.753 0.776 pw_transfer 2120 10.5 0.045 0.051 0.748 0.757 qs_scf_new_mos 10 5.0 0.000 0.000 0.750 0.754 make_m2s 352 9.0 0.003 0.003 0.647 0.740 make_images 352 10.0 0.051 0.052 0.634 0.727 ------------------------------------------------------------------------------- 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=55.75200000000001, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=66.175, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=25.01, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=10.19, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.124, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.929, 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=6.810000000000002, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.466, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.903, 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=1.41, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.845, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=2.017, 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 0.093 0.093 126.701 126.701 qs_energies 1 2.0 0.000 0.000 125.191 125.191 scf_env_do_scf 1 3.0 0.000 0.000 118.380 118.380 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 118.380 118.380 qs_ks_update_qs_env 15 5.0 0.000 0.000 49.935 49.935 rebuild_ks_matrix 15 6.0 0.000 0.000 49.726 49.726 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 49.726 49.726 qs_scf_new_mos 15 5.0 0.000 0.000 43.345 43.345 eigensolver 15 6.0 0.002 0.002 35.623 35.623 qs_vxc_create 15 8.0 0.017 0.017 34.128 34.128 calculate_dispersion_nonloc 15 9.0 6.789 6.789 29.643 29.643 pw_transfer 1191 10.0 0.066 0.066 23.557 23.557 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 23.377 23.377 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.537 22.537 cp_fm_diag_elpa_base 15 8.0 20.013 20.013 22.537 22.537 qs_rho_update_rho_low 16 5.0 0.000 0.000 22.132 22.132 calculate_rho_elec 16 6.0 0.216 0.216 22.132 22.132 grid_collocate_task_list 16 7.0 20.717 20.717 20.717 20.717 fft_wrap_pw1pw2_150 765 12.0 3.564 3.564 16.885 16.885 sum_up_and_integrate 15 8.0 0.139 0.139 14.353 14.353 integrate_v_rspace 15 9.0 0.019 0.019 14.214 14.214 grid_integrate_task_list 15 10.0 13.676 13.676 13.676 13.676 cp_fm_cholesky_restore 45 7.0 10.841 10.841 10.841 10.841 fft3d_s 1087 13.0 10.456 10.456 10.463 10.463 pw_scatter_s 585 13.1 7.317 7.317 7.317 7.317 fft_wrap_pw1pw2_200 197 12.3 0.824 0.824 6.309 6.309 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.580 5.580 dbcsr_complete_redistribute 46 8.3 2.203 2.203 5.514 5.514 cp_fm_upper_to_full 30 8.0 4.767 4.767 4.767 4.767 xc_vxc_pw_create 15 9.0 0.214 0.214 4.467 4.467 vdW_energy 15 10.0 4.358 4.358 4.358 4.358 gspace_mixing 14 5.0 0.171 0.171 4.185 4.185 broyden_mixing 14 6.0 3.529 3.529 3.529 3.529 init_scf_run 1 3.0 0.000 0.000 3.213 3.213 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.124 3.124 xc_pw_derive 90 11.0 0.001 0.001 2.955 2.955 ------------------------------------------------------------------------------- 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 60.386 60.398 qs_energies 1 2.0 0.000 0.000 60.115 60.121 scf_env_do_scf 1 3.0 0.000 0.001 56.054 56.055 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 56.054 56.055 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.291 24.302 rebuild_ks_matrix 15 6.0 0.000 0.000 24.260 24.271 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 24.260 24.271 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.524 20.530 calculate_rho_elec 16 6.0 0.007 0.007 20.524 20.530 grid_collocate_task_list 16 7.0 19.352 19.516 19.352 19.516 sum_up_and_integrate 15 8.0 0.014 0.020 14.022 14.079 integrate_v_rspace 15 9.0 0.001 0.001 14.008 14.070 grid_integrate_task_list 15 10.0 13.186 13.347 13.186 13.347 qs_scf_new_mos 15 5.0 0.000 0.001 11.899 11.928 eigensolver 15 6.0 0.001 0.002 10.952 10.993 qs_vxc_create 15 8.0 0.001 0.001 9.917 9.927 calculate_dispersion_nonloc 15 9.0 0.900 0.919 7.916 7.949 pw_transfer 1191 10.0 0.085 0.105 7.846 7.900 fft_wrap_pw1pw2 1086 11.0 0.011 0.014 7.690 7.774 cp_fm_diag_elpa 15 7.0 0.000 0.000 7.685 7.686 cp_fm_diag_elpa_base 15 8.0 7.535 7.567 7.683 7.683 fft3d_ps 1086 13.0 2.563 2.968 5.290 5.828 fft_wrap_pw1pw2_150 765 12.0 0.571 0.726 4.922 4.951 cp_fm_cholesky_restore 45 7.0 3.100 3.212 3.100 3.212 mp_alltoall_z22v 1086 15.0 2.199 3.123 2.199 3.123 fft_wrap_pw1pw2_200 197 12.3 0.412 0.534 2.648 2.696 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.444 2.444 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.150 2.340 xc_vxc_pw_create 15 9.0 0.015 0.020 2.000 2.043 x_to_yz 585 14.1 0.317 0.347 1.475 1.904 yz_to_x 501 13.9 0.185 0.241 1.227 1.703 xc_pw_derive 90 11.0 0.001 0.002 1.369 1.454 init_scf_run 1 3.0 0.000 0.000 1.395 1.396 build_core_ppnl 1 5.0 1.260 1.374 1.260 1.374 vdW_energy 15 10.0 1.282 1.341 1.282 1.341 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.307 1.307 ------------------------------------------------------------------------------- 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=50.99799999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.717, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.013, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.676, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.841, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.456, 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=14.649999999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.352, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=7.535, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.186, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.1, 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=2.563, 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 0.080 0.080 352.316 352.316 qs_energies 1 2.0 0.000 0.000 352.175 352.175 ls_scf 1 3.0 0.000 0.000 350.821 350.821 ls_scf_main 1 4.0 0.002 0.002 341.416 341.416 density_matrix_trs4 11 5.0 0.012 0.012 243.407 243.407 arnoldi_extremal 12 6.1 0.000 0.000 150.620 150.620 arnoldi_normal_ev 12 7.1 0.044 0.044 150.620 150.620 dbcsr_matrix_vector_mult 652 9.0 0.235 0.235 148.082 148.082 build_subspace 23 8.1 0.084 0.084 147.703 147.703 dbcsr_matrix_vector_mult_local 652 10.0 146.508 146.508 146.518 146.518 ls_scf_dm_to_ks 11 5.0 0.000 0.000 91.940 91.940 matrix_ls_to_qs 11 6.0 0.000 0.000 88.375 88.375 dbcsr_multiply_generic 185 6.1 0.916 0.916 77.924 77.924 dbcsr_complete_redistribute 23 7.5 33.265 33.265 47.071 47.071 dbcsr_copy_into_existing 11 7.0 45.551 45.551 45.551 45.551 multiply_cannon 185 7.1 0.391 0.391 45.116 45.116 matrix_decluster 11 7.0 0.000 0.000 42.822 42.822 multiply_cannon_loop 185 8.1 0.235 0.235 32.497 32.497 make_m2s 370 7.1 0.038 0.038 27.890 27.890 make_images 370 8.1 12.322 12.322 25.727 25.727 multiply_cannon_multrec 185 9.1 23.331 23.331 23.484 23.484 dbcsr_finalize 646 7.5 0.241 0.241 17.773 17.773 dbcsr_merge_all 597 8.5 2.520 2.520 16.496 16.496 tree_to_linear_d 110 9.4 12.404 12.404 12.404 12.404 setup_rec_index_2d 370 8.1 12.124 12.124 12.124 12.124 dbcsr_sort_indices 1103 9.9 11.396 11.396 11.396 11.396 quick_finalize 395 10.0 0.422 0.422 9.802 9.802 dbcsr_special_finalize 370 9.1 0.002 0.002 9.062 9.062 calculate_norms 370 9.1 8.777 8.777 8.777 8.777 ls_scf_init_scf 1 4.0 0.000 0.000 8.710 8.710 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.371 8.371 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.711 7.711 ------------------------------------------------------------------------------- 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 0.007 0.021 67.387 67.398 qs_energies 1 2.0 0.000 0.000 67.287 67.288 ls_scf 1 3.0 0.000 0.000 67.238 67.239 ls_scf_main 1 4.0 0.001 0.009 64.644 64.645 density_matrix_trs4 11 5.0 0.006 0.017 62.153 62.219 dbcsr_multiply_generic 185 6.1 0.059 0.076 58.843 58.988 multiply_cannon 185 7.1 0.036 0.039 49.078 49.719 multiply_cannon_loop 185 8.1 0.125 0.140 46.571 47.574 multiply_cannon_multrec 1480 9.1 28.688 31.355 28.980 31.654 mp_waitall_1 11936 10.3 14.910 16.882 14.910 16.882 multiply_cannon_metrocomm3 1480 9.1 0.015 0.019 8.823 12.452 make_m2s 370 7.1 0.035 0.038 6.753 6.830 make_images 370 8.1 0.630 0.670 6.620 6.699 calculate_norms 2960 9.1 5.191 6.057 5.191 6.057 multiply_cannon_metrocomm1 1480 9.1 0.008 0.010 3.391 5.160 make_images_data 370 9.1 0.009 0.011 2.950 3.159 hybrid_alltoall_any 393 9.9 0.196 1.067 2.571 2.769 mp_sum_l 1199 5.3 1.844 2.473 1.844 2.473 arnoldi_extremal 12 6.1 0.000 0.001 2.382 2.401 arnoldi_normal_ev 12 7.1 0.002 0.008 2.381 2.401 build_subspace 23 8.1 0.021 0.026 2.291 2.292 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.156 2.229 dbcsr_matrix_vector_mult 652 9.0 0.014 0.050 1.975 2.033 dbcsr_complete_redistribute 23 7.5 1.194 1.299 1.944 2.022 matrix_ls_to_qs 11 6.0 0.000 0.000 1.897 1.984 ls_scf_init_scf 1 4.0 0.000 0.000 1.938 1.939 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.913 1.918 make_images_pack 370 9.1 1.687 1.851 1.690 1.857 matrix_decluster 11 7.0 0.000 0.003 1.757 1.841 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.744 1.747 dbcsr_matrix_vector_mult_local 652 10.0 1.646 1.694 1.648 1.696 buffer_matrices_ensure_size 370 8.1 1.432 1.567 1.432 1.567 dbcsr_finalize 646 7.5 0.008 0.008 1.436 1.563 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.006 1.545 ------------------------------------------------------------------------------- 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=82.47999999999996, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=146.508, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=45.551, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=33.265, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.331, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="tree_to_linear_d", label="tree_to_linear_d", y=12.404, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.777, 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 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", 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=12.226999999999997, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.646, 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=1.194, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=28.688, 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=5.191, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.91, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.844, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.687, 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 74.796 74.796 lib_test 1 2.0 0.000 0.000 74.788 74.788 dbcsr_run_tests 3 3.0 0.002 0.002 74.788 74.788 test_multiplies_multiproc 3 4.0 0.001 0.001 58.728 58.728 dbcsr_redistribute 9 5.0 36.661 36.661 38.291 38.291 dbcsr_multiply_generic 9 5.0 0.001 0.001 18.816 18.816 dbcsr_make_random_matrix 9 4.0 12.973 12.973 15.944 15.944 multiply_cannon 9 6.0 0.002 0.002 13.237 13.237 multiply_cannon_loop 9 7.0 0.012 0.012 12.848 12.848 multiply_cannon_multrec 9 8.0 12.836 12.836 12.837 12.837 dbcsr_finalize 27 5.7 0.009 0.009 5.789 5.789 dbcsr_merge_all 18 6.5 2.168 2.168 4.948 4.948 dbcsr_data_release 975 7.6 3.283 3.283 3.283 3.283 make_m2s 18 6.0 0.001 0.001 1.984 1.984 tree_to_linear_d 9 7.0 1.908 1.908 1.908 1.908 make_images 18 7.0 0.714 0.714 1.875 1.875 dbcsr_destroy 93 5.8 0.000 0.000 1.666 1.666 ------------------------------------------------------------------------------- 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 17.908 17.912 lib_test 1 2.0 0.000 0.000 17.879 17.897 dbcsr_run_tests 3 3.0 0.000 0.001 17.878 17.897 test_multiplies_multiproc 3 4.0 0.000 0.002 17.041 17.094 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.679 15.779 multiply_cannon 9 6.0 0.002 0.002 13.948 14.298 multiply_cannon_loop 9 7.0 0.002 0.002 13.644 13.963 multiply_cannon_multrec 72 8.0 11.455 11.840 11.456 11.841 mp_waitall_1 576 9.2 2.498 2.950 2.498 2.950 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.955 2.386 dbcsr_data_release 444 7.6 0.766 0.883 0.766 0.883 dbcsr_make_random_matrix 9 4.0 0.661 0.667 0.804 0.832 mp_sum_l 470 2.5 0.394 0.817 0.394 0.817 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.390 0.813 dbcsr_finalize 27 5.7 0.000 0.000 0.691 0.785 dbcsr_destroy 111 5.9 0.000 0.000 0.624 0.745 make_m2s 18 6.0 0.001 0.001 0.681 0.721 make_images 18 7.0 0.021 0.022 0.678 0.718 dbcsr_merge_all 18 6.5 0.103 0.127 0.548 0.618 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.226 0.584 dbcsr_redistribute 9 5.0 0.242 0.286 0.411 0.434 make_images_data 18 8.0 0.001 0.002 0.353 0.414 dbcsr_data_copy_aa2 18 7.5 0.327 0.371 0.327 0.371 hybrid_alltoall_any 18 9.0 0.030 0.147 0.308 0.370 ------------------------------------------------------------------------------- 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=6.875, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=36.661, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.973, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=12.836, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=3.283, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.168, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=1.7890000000000015, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.242, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.661, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.455, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.766, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.103, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.394, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.498, 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 0.054 0.054 133.691 133.691 qs_mol_dyn_low 1 2.0 0.003 0.003 131.823 131.823 velocity_verlet 5 3.0 0.003 0.003 107.613 107.613 qmmm_el_coupling 6 3.8 0.000 0.000 87.927 87.927 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 87.923 87.923 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.286 87.286 qmmm_elec_gaussian_low_G 6 6.8 86.396 86.396 86.396 86.396 qs_forces 6 3.8 0.001 0.001 35.551 35.551 qs_energies 6 4.8 0.000 0.000 31.590 31.590 scf_env_do_scf 6 5.8 0.001 0.001 29.274 29.274 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 25.545 25.545 rebuild_ks_matrix 45 8.4 0.000 0.000 24.480 24.480 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.480 24.480 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.944 20.944 pw_transfer 966 12.3 0.053 0.053 17.651 17.651 fft_wrap_pw1pw2 801 13.6 0.006 0.006 17.442 17.442 fft_wrap_pw1pw2_150 507 15.2 2.344 2.344 16.972 16.972 qs_vxc_create 45 10.4 0.001 0.001 13.468 13.468 xc_vxc_pw_create 45 11.4 0.652 0.652 13.468 13.468 xc_pw_derive 270 13.4 0.002 0.002 9.474 9.474 fft3d_s 802 15.6 7.992 7.992 8.000 8.000 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.422 7.422 calculate_rho_elec 45 8.9 0.564 0.564 7.421 7.421 xc_rho_set_and_dset_create 45 12.4 0.598 0.598 6.887 6.887 xc_pw_divergence 45 12.4 0.001 0.001 5.860 5.860 pw_scatter_s 429 15.8 5.802 5.802 5.802 5.802 qmmm_forces 6 3.8 0.002 0.002 5.198 5.198 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 4.853 4.853 pw_integral_ab 2539 7.4 4.521 4.521 4.521 4.521 qs_ks_ddapc 45 10.4 0.001 0.001 4.164 4.164 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.129 4.129 init_scf_loop 6 6.8 0.000 0.000 3.725 3.725 sum_up_and_integrate 45 10.4 0.483 0.483 3.703 3.703 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.543 3.543 grid_collocate_task_list 45 9.9 3.440 3.440 3.440 3.440 qmmm_forces_gaussian_low_G 6 6.8 3.438 3.438 3.438 3.438 density_rs2pw 45 9.9 0.002 0.002 3.418 3.418 integrate_v_rspace 45 11.4 0.006 0.006 3.220 3.220 ------------------------------------------------------------------------------- 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 0.060 65.965 65.975 qs_mol_dyn_low 1 2.0 0.003 0.003 64.778 64.840 qs_forces 6 3.8 0.001 0.001 47.143 47.143 qs_energies 6 4.8 0.000 0.000 45.010 45.011 scf_env_do_scf 6 5.8 0.000 0.001 43.987 43.987 scf_env_do_scf_inner_loop 113 6.2 0.003 0.022 42.182 42.183 rebuild_ks_matrix 119 8.1 0.000 0.000 32.492 32.503 qs_ks_build_kohn_sham_matrix 119 9.1 0.012 0.014 32.491 32.503 qs_ks_update_qs_env 119 7.3 0.001 0.001 30.643 30.654 velocity_verlet 5 3.0 0.002 0.003 27.311 27.314 pw_transfer 2446 12.3 0.156 0.164 23.330 24.012 fft_wrap_pw1pw2 2059 13.4 0.015 0.016 22.927 23.612 fft_wrap_pw1pw2_150 1321 14.9 4.326 4.527 22.347 23.045 qs_vxc_create 119 10.1 0.002 0.002 19.107 19.117 xc_vxc_pw_create 119 11.1 0.330 0.392 19.105 19.116 xc_pw_derive 714 13.1 0.005 0.005 13.680 14.267 fft3d_ps 2059 15.4 7.272 7.527 12.749 13.464 qs_rho_update_rho_low 119 7.3 0.000 0.001 11.674 11.676 calculate_rho_elec 119 8.3 0.049 0.057 11.673 11.676 xc_rho_set_and_dset_create 119 12.1 0.659 0.789 9.392 9.815 xc_pw_divergence 119 12.1 0.002 0.003 9.134 9.658 sum_up_and_integrate 119 10.1 0.140 0.154 9.454 9.469 integrate_v_rspace 119 11.1 0.003 0.003 9.313 9.341 qmmm_forces 6 3.8 0.003 0.005 9.228 9.230 qmmm_forces_with_gaussian 6 4.8 0.009 0.011 8.753 9.018 qmmm_el_coupling 6 3.8 0.000 0.000 7.422 7.566 qmmm_elec_with_gaussian 6 4.8 0.005 0.005 7.420 7.564 density_rs2pw 119 9.3 0.004 0.005 7.151 7.414 rs_pw_transfer 988 11.5 0.009 0.009 6.196 6.438 potential_pw2rs 119 12.1 0.006 0.006 5.650 5.667 mp_alltoall_z22v 2059 17.4 3.817 4.815 3.817 4.815 grid_collocate_task_list 119 9.3 4.385 4.620 4.385 4.620 pw_restrict_s3 18 5.8 2.340 2.468 4.181 4.429 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.995 4.055 grid_integrate_task_list 119 12.1 3.455 3.621 3.455 3.621 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 3.420 3.564 pw_prolongate_s3 18 6.8 1.903 1.969 3.420 3.564 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.339 3.423 qmmm_forces_gaussian_low_G 6 6.8 3.295 3.355 3.295 3.355 yz_to_x 964 16.0 0.684 0.830 2.625 3.341 pw_scatter_p 1095 15.8 3.108 3.141 3.108 3.141 x_to_yz 1095 16.8 0.932 1.024 2.809 3.021 qmmm_elec_gaussian_low_G 6 6.8 2.741 2.822 2.741 2.822 pw_gather_p 964 15.0 2.636 2.717 2.636 2.717 qs_ks_ddapc 119 10.1 0.002 0.002 2.560 2.606 rs_pw_transfer_PW2RS_150 125 13.9 0.880 0.922 2.275 2.495 mp_waitany 4028 12.8 1.975 2.457 1.975 2.457 pw_integral_ab 2761 7.7 2.018 2.135 2.190 2.339 rs_pw_transfer_RS2PW_150 125 11.2 0.805 0.868 1.871 2.090 qs_scf_new_mos 113 7.2 0.000 0.001 2.064 2.072 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.064 2.072 ot_scf_mini 113 9.2 0.001 0.001 1.975 1.983 xc_functional_eval 238 13.1 0.002 0.002 1.594 1.903 dbcsr_multiply_generic 2588 12.3 0.060 0.062 1.834 1.872 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.863 1.863 init_scf_loop 6 6.8 0.000 0.000 1.802 1.803 pw_axpy 2291 9.2 1.310 1.366 1.310 1.366 ------------------------------------------------------------------------------- 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=23.196000000000012, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.396, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.992, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.802, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.521, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.44, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=2.344, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=37.95100000000001, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.741, 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=2.018, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.385, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=4.326, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.272, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.455, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.817, yerr=0.0 Summary: Performance test took 34 minutes. Status: OK Removing intermediate container 98971b35f314 ---> 6047c02cc256 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in c95c1307f57a Removing intermediate container c95c1307f57a ---> b36defb34c00 Step 42/42 : ENTRYPOINT [] ---> Running in 0479945ffdff Removing intermediate container 0479945ffdff ---> e64fafd77315 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built e64fafd77315 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: 2023-05-11 20:50:22+00:00