StartDate: 2023-05-21 11:36:19+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: d6d429ae51f26379f2dc33b64015d7bb356f05fe CommitTime: 2023-05-21 07:18:56 +0200 CommitAuthor: Matthias Krack CommitSubject: Update input description #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=d6d429ae51f26379f2dc33b64015d7bb356f05fe 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 369.2MB 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 ---> 22611512e296 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> f786a3364ac8 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 2ccb962ca377 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 a8fdce13f12d './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container a8fdce13f12d ---> 001857e2e8d0 Step 35/42 : COPY ./data ./data ---> 5df008301a58 Step 36/42 : COPY ./tests ./tests ---> 02593d1beb2a Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 4034b914919e Step 38/42 : COPY ./benchmarks ./benchmarks ---> 0b61de836af1 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> ae67ac05f27d Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 1a5b3822a181 ========== 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 0.043 0.043 97.352 97.352 qs_mol_dyn_low 1 2.0 0.003 0.003 96.657 96.657 qs_forces 11 3.9 0.001 0.001 96.615 96.615 qs_energies 11 4.9 0.001 0.001 89.927 89.927 scf_env_do_scf 11 5.9 0.001 0.001 78.150 78.150 velocity_verlet 10 3.0 0.002 0.002 63.746 63.746 scf_env_do_scf_inner_loop 108 6.5 0.012 0.012 59.707 59.707 rebuild_ks_matrix 119 8.3 0.001 0.001 22.531 22.531 qs_ks_build_kohn_sham_matrix 119 9.3 0.014 0.014 22.530 22.530 dbcsr_multiply_generic 2286 12.5 0.178 0.178 22.330 22.330 qs_scf_new_mos 108 7.5 0.001 0.001 22.040 22.040 qs_scf_loop_do_ot 108 8.5 0.001 0.001 22.040 22.040 qs_rho_update_rho_low 119 7.7 0.001 0.001 21.159 21.159 calculate_rho_elec 119 8.7 0.964 0.964 21.159 21.159 qs_ks_update_qs_env 119 7.6 0.001 0.001 20.661 20.661 ot_scf_mini 108 9.5 0.003 0.003 20.442 20.442 init_scf_loop 11 6.9 0.000 0.000 18.325 18.325 grid_collocate_task_list 119 9.7 16.435 16.435 16.435 16.435 prepare_preconditioner 11 7.9 0.000 0.000 15.570 15.570 make_preconditioner 11 8.9 0.000 0.000 15.570 15.570 sum_up_and_integrate 119 10.3 0.890 0.890 14.534 14.534 make_full_inverse_cholesky 11 9.9 0.027 0.027 14.368 14.368 integrate_v_rspace 119 11.3 0.103 0.103 13.644 13.644 ot_mini 108 10.5 0.001 0.001 13.199 13.199 make_m2s 4572 13.5 0.053 0.053 11.939 11.939 grid_integrate_task_list 119 12.3 11.400 11.400 11.400 11.400 qs_ot_get_derivative 108 11.5 0.001 0.001 7.083 7.083 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.989 6.989 pw_transfer 1439 11.6 0.077 0.077 6.787 6.787 fft_wrap_pw1pw2 1201 12.6 0.007 0.007 6.519 6.519 dbcsr_make_dense_low 5837 15.5 0.089 0.089 6.275 6.275 make_dense_data 5837 16.5 5.485 5.485 6.170 6.170 ot_diis_step 108 11.5 0.004 0.004 6.111 6.111 make_images 4572 14.5 2.339 2.339 6.034 6.034 multiply_cannon 2286 13.5 0.220 0.220 5.992 5.992 fft_wrap_pw1pw2_140 487 13.2 0.481 0.481 5.665 5.665 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.625 5.625 apply_single 119 13.6 0.001 0.001 5.625 5.625 dbcsr_make_images_dense 3978 14.8 0.019 0.019 5.544 5.544 multiply_cannon_loop 2286 14.5 0.054 0.054 5.442 5.442 multiply_cannon_multrec 2286 15.5 5.325 5.325 5.386 5.386 cp_fm_cholesky_decompose 22 10.9 5.314 5.314 5.314 5.314 cp_fm_cholesky_invert 11 10.9 4.779 4.779 4.779 4.779 init_scf_run 11 5.9 0.002 0.002 4.155 4.155 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.153 4.153 dbcsr_copy 2102 12.0 0.271 0.271 4.049 4.049 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.838 3.838 dbcsr_complete_redistribute 329 12.2 2.000 2.000 3.836 3.836 density_rs2pw 119 9.7 0.006 0.006 3.760 3.760 dbcsr_copy_into_existing 22 7.9 3.736 3.736 3.736 3.736 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.692 3.692 wfi_extrapolate 11 7.9 0.001 0.001 3.630 3.630 qs_create_task_list 11 7.9 0.000 0.000 3.299 3.299 generate_qs_task_list 11 8.9 1.968 1.968 3.298 3.298 fft3d_s 1202 14.6 3.249 3.249 3.271 3.271 qs_ot_get_p 119 10.4 0.001 0.001 3.263 3.263 copy_dbcsr_to_fm 153 11.3 0.003 0.003 3.126 3.126 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.849 2.849 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.847 2.847 dbcsr_data_release 279534 16.0 2.531 2.531 2.531 2.531 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.473 2.473 qs_ot_get_derivative_taylor 59 13.0 0.002 0.002 2.279 2.279 potential_pw2rs 119 12.3 0.052 0.052 2.141 2.141 pw_poisson_solve 119 10.3 0.372 0.372 2.127 2.127 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.117 2.117 ------------------------------------------------------------------------------- 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 54.642 54.654 qs_mol_dyn_low 1 2.0 0.003 0.004 54.497 54.501 qs_forces 11 3.9 0.002 0.002 54.449 54.449 qs_energies 11 4.9 0.001 0.001 51.000 51.005 scf_env_do_scf 11 5.9 0.001 0.002 46.944 46.945 scf_env_do_scf_inner_loop 108 6.5 0.003 0.023 43.449 43.449 velocity_verlet 10 3.0 0.002 0.006 32.397 32.399 rebuild_ks_matrix 119 8.3 0.001 0.001 19.510 19.628 qs_ks_build_kohn_sham_matrix 119 9.3 0.019 0.023 19.509 19.627 qs_ks_update_qs_env 119 7.6 0.001 0.001 17.341 17.442 qs_rho_update_rho_low 119 7.7 0.001 0.001 16.628 16.651 calculate_rho_elec 119 8.7 0.033 0.035 16.627 16.650 dbcsr_multiply_generic 2286 12.5 0.090 0.106 15.566 15.808 sum_up_and_integrate 119 10.3 0.040 0.044 14.687 14.724 integrate_v_rspace 119 11.3 0.005 0.006 14.647 14.682 qs_scf_new_mos 108 7.5 0.001 0.001 12.680 12.834 qs_scf_loop_do_ot 108 8.5 0.001 0.001 12.679 12.833 ot_scf_mini 108 9.5 0.002 0.003 11.886 12.031 grid_collocate_task_list 119 9.7 10.261 11.469 10.261 11.469 multiply_cannon 2286 13.5 0.166 0.197 10.858 11.350 multiply_cannon_loop 2286 14.5 0.110 0.124 10.089 10.618 grid_integrate_task_list 119 12.3 9.221 9.940 9.221 9.940 mp_waitall_1 158411 16.6 8.214 9.141 8.214 9.141 ot_mini 108 10.5 0.001 0.001 7.021 7.185 multiply_cannon_metrocomm3 18288 15.5 0.042 0.046 5.698 6.882 rs_pw_transfer 974 11.9 0.013 0.015 6.070 6.522 density_rs2pw 119 9.7 0.006 0.007 5.662 6.124 pw_transfer 1439 11.6 0.104 0.122 4.843 4.942 fft_wrap_pw1pw2 1201 12.6 0.011 0.012 4.657 4.748 fft_wrap_pw1pw2_140 487 13.2 0.802 0.963 3.808 4.045 potential_pw2rs 119 12.3 0.007 0.008 4.007 4.040 qs_ot_get_derivative 108 11.5 0.001 0.001 3.812 3.956 multiply_cannon_multrec 18288 15.5 3.400 3.655 3.413 3.670 init_scf_loop 11 6.9 0.000 0.000 3.479 3.479 mp_waitany 9880 13.7 2.780 3.304 2.780 3.304 fft3d_ps 1201 14.6 1.455 1.624 2.992 3.276 ot_diis_step 108 11.5 0.004 0.004 3.150 3.158 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.016 3.129 apply_single 119 13.6 0.000 0.001 3.016 3.128 make_m2s 4572 13.5 0.053 0.058 2.910 2.983 init_scf_run 11 5.9 0.000 0.005 2.876 2.876 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.876 2.876 rs_pw_transfer_RS2PW_140 130 11.5 0.175 0.201 2.294 2.745 wfi_extrapolate 11 7.9 0.001 0.002 2.623 2.623 make_images 4572 14.5 0.132 0.143 2.533 2.615 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.319 2.337 mp_alltoall_d11v 2130 13.8 1.627 1.994 1.627 1.994 qs_ot_get_p 119 10.4 0.001 0.001 1.628 1.828 mp_sum_l 11298 13.2 1.266 1.793 1.266 1.793 rs_gather_matrices 119 12.3 0.116 0.139 1.349 1.732 mp_alltoall_z22v 1201 16.6 1.245 1.636 1.245 1.636 multiply_cannon_metrocomm1 18288 15.5 0.021 0.023 0.649 1.515 rs_pw_transfer_PW2RS_140 130 13.9 0.402 0.500 1.410 1.468 make_images_data 4572 15.5 0.038 0.043 1.233 1.440 prepare_preconditioner 11 7.9 0.000 0.000 1.389 1.408 make_preconditioner 11 8.9 0.000 0.000 1.389 1.408 mp_sum_d 4135 12.0 0.838 1.372 0.838 1.372 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.295 1.361 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.252 1.290 hybrid_alltoall_any 4725 16.4 0.079 0.239 1.064 1.281 qs_ot_get_derivative_taylor 59 13.0 0.001 0.002 1.185 1.258 ------------------------------------------------------------------------------- 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=53.393, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=16.435, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=11.4, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.485, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.325, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=5.314, 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=20.766000000000005, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=10.261, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=9.221, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.4, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.214, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.78, 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 0.037 0.037 130.977 130.977 qs_mol_dyn_low 1 2.0 0.003 0.003 130.263 130.263 qs_forces 11 3.9 0.002 0.002 130.218 130.218 qs_energies 11 4.9 0.001 0.001 121.074 121.074 scf_env_do_scf 11 5.9 0.001 0.001 105.792 105.792 velocity_verlet 10 3.0 0.002 0.002 85.999 85.999 scf_env_do_scf_inner_loop 96 6.5 0.012 0.012 83.947 83.947 rebuild_ks_matrix 107 8.3 0.001 0.001 38.712 38.712 qs_ks_build_kohn_sham_matrix 107 9.3 0.015 0.015 38.712 38.712 qs_rho_update_rho_low 107 7.7 0.001 0.001 36.718 36.718 calculate_rho_elec 107 8.7 0.889 0.889 36.717 36.717 qs_ks_update_qs_env 107 7.6 0.001 0.001 34.687 34.687 grid_collocate_task_list 107 9.7 31.413 31.413 31.413 31.413 sum_up_and_integrate 107 10.3 0.921 0.921 30.873 30.873 integrate_v_rspace 107 11.3 0.101 0.101 29.952 29.952 grid_integrate_task_list 107 12.3 27.378 27.378 27.378 27.378 init_scf_loop 11 6.9 0.000 0.000 21.640 21.640 dbcsr_multiply_generic 1966 12.4 0.172 0.172 21.039 21.039 qs_scf_new_mos 96 7.5 0.001 0.001 20.511 20.511 qs_scf_loop_do_ot 96 8.5 0.001 0.001 20.510 20.510 ot_scf_mini 96 9.5 0.003 0.003 18.977 18.977 prepare_preconditioner 11 7.9 0.000 0.000 16.961 16.961 make_preconditioner 11 8.9 0.000 0.000 16.961 16.961 make_full_inverse_cholesky 11 9.9 0.017 0.017 15.757 15.757 ot_mini 96 10.5 0.001 0.001 12.161 12.161 make_m2s 3932 13.4 0.052 0.052 11.322 11.322 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 8.138 8.138 pw_transfer 1295 11.6 0.079 0.079 7.881 7.881 fft_wrap_pw1pw2 1081 12.6 0.007 0.007 7.620 7.620 qs_ot_get_derivative 96 11.5 0.001 0.001 6.745 6.745 fft_wrap_pw1pw2_140 439 13.2 0.566 0.566 6.724 6.724 init_scf_run 11 5.9 0.002 0.002 6.305 6.305 scf_env_initial_rho_setup 11 6.9 0.001 0.001 6.302 6.302 cp_fm_cholesky_decompose 22 10.9 6.274 6.274 6.274 6.274 dbcsr_make_dense_low 4961 15.5 0.090 0.090 5.995 5.995 make_dense_data 4961 16.5 5.158 5.158 5.890 5.890 make_images 3932 14.4 2.293 2.293 5.826 5.826 multiply_cannon 1966 13.4 0.229 0.229 5.664 5.664 wfi_extrapolate 11 7.9 0.001 0.001 5.601 5.601 ot_diis_step 96 11.5 0.004 0.004 5.412 5.412 cp_fm_cholesky_invert 11 10.9 5.163 5.163 5.163 5.163 dbcsr_make_images_dense 3386 14.7 0.018 0.018 5.147 5.147 multiply_cannon_loop 1966 14.4 0.051 0.051 5.111 5.111 multiply_cannon_multrec 1966 15.4 4.995 4.995 5.059 5.059 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 5.039 5.039 apply_single 107 13.6 0.001 0.001 5.039 5.039 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.949 4.949 dbcsr_copy 1855 11.9 0.281 0.281 4.817 4.817 dbcsr_copy_into_existing 22 7.9 4.480 4.480 4.481 4.481 density_rs2pw 107 9.7 0.006 0.006 4.415 4.415 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.297 4.297 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 4.192 4.192 dbcsr_complete_redistribute 317 12.2 2.050 2.050 4.058 4.058 qs_create_task_list 11 7.9 0.000 0.000 3.820 3.820 generate_qs_task_list 11 8.9 2.407 2.407 3.820 3.820 fft3d_s 1082 14.6 3.799 3.799 3.805 3.805 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 3.365 3.365 copy_dbcsr_to_fm 147 11.2 0.003 0.003 3.353 3.353 qs_ot_get_p 107 10.4 0.001 0.001 3.075 3.075 ------------------------------------------------------------------------------- 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 0.010 0.025 90.104 90.116 qs_mol_dyn_low 1 2.0 0.003 0.004 89.939 89.944 qs_forces 11 3.9 0.002 0.002 89.890 89.891 qs_energies 11 4.9 0.001 0.001 84.156 84.158 scf_env_do_scf 11 5.9 0.000 0.002 77.836 77.837 scf_env_do_scf_inner_loop 96 6.5 0.003 0.022 72.112 72.113 velocity_verlet 10 3.0 0.002 0.004 53.456 53.457 rebuild_ks_matrix 107 8.3 0.001 0.001 37.824 37.967 qs_ks_build_kohn_sham_matrix 107 9.3 0.018 0.021 37.823 37.966 qs_ks_update_qs_env 107 7.6 0.001 0.001 33.337 33.461 qs_rho_update_rho_low 107 7.7 0.001 0.001 33.046 33.058 calculate_rho_elec 107 8.7 0.030 0.031 33.046 33.057 sum_up_and_integrate 107 10.3 0.043 0.049 32.641 32.704 integrate_v_rspace 107 11.3 0.005 0.005 32.597 32.658 grid_integrate_task_list 107 12.3 25.743 27.623 25.743 27.623 grid_collocate_task_list 107 9.7 25.091 27.507 25.091 27.507 dbcsr_multiply_generic 1966 12.4 0.082 0.101 16.573 16.907 qs_scf_new_mos 96 7.5 0.001 0.001 12.889 13.038 qs_scf_loop_do_ot 96 8.5 0.001 0.001 12.889 13.037 multiply_cannon 1966 13.4 0.156 0.194 12.159 12.625 ot_scf_mini 96 9.5 0.002 0.003 12.143 12.274 multiply_cannon_loop 1966 14.4 0.108 0.123 11.433 11.960 mp_waitall_1 136719 16.5 9.891 10.711 9.891 10.711 rs_pw_transfer 878 11.9 0.013 0.017 7.981 8.938 density_rs2pw 107 9.7 0.005 0.006 7.254 8.190 multiply_cannon_metrocomm3 15728 15.4 0.040 0.048 7.069 7.984 ot_mini 96 10.5 0.001 0.001 7.184 7.331 init_scf_loop 11 6.9 0.000 0.000 5.707 5.708 mp_waitany 8968 13.7 4.410 5.442 4.410 5.442 init_scf_run 11 5.9 0.000 0.005 5.072 5.073 scf_env_initial_rho_setup 11 6.9 0.000 0.004 5.072 5.073 pw_transfer 1295 11.6 0.098 0.109 4.739 4.831 rs_pw_transfer_RS2PW_140 118 11.5 0.171 0.211 3.799 4.764 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.648 4.666 fft_wrap_pw1pw2 1081 12.6 0.010 0.011 4.563 4.642 wfi_extrapolate 11 7.9 0.001 0.001 4.631 4.632 potential_pw2rs 107 12.3 0.006 0.007 4.201 4.242 fft_wrap_pw1pw2_140 439 13.2 0.795 0.997 3.762 3.930 qs_ot_get_derivative 96 11.5 0.001 0.001 3.716 3.855 multiply_cannon_multrec 15728 15.4 3.322 3.641 3.335 3.653 mp_alltoall_d11v 1998 13.7 2.866 3.626 2.866 3.626 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.407 3.515 apply_single 107 13.6 0.000 0.001 3.407 3.514 ot_diis_step 96 11.5 0.004 0.005 3.424 3.424 fft3d_ps 1081 14.6 1.380 1.539 2.946 3.291 rs_gather_matrices 107 12.3 0.116 0.135 2.579 3.264 make_m2s 3932 13.4 0.047 0.052 2.882 2.967 make_images 3932 14.4 0.117 0.127 2.541 2.643 ------------------------------------------------------------------------------- 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=50.596000000000004, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=31.413, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=27.378, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=6.274, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=5.163, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.158, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.995, 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=21.64699999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=25.091, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.743, 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="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.322, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=9.891, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=4.41, 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 0.229 0.229 117.654 117.654 qs_energies 1 2.0 0.000 0.000 116.733 116.733 scf_env_do_scf 1 3.0 0.000 0.000 115.280 115.280 qs_ks_update_qs_env 8 5.0 0.000 0.000 109.668 109.668 rebuild_ks_matrix 7 6.0 0.000 0.000 109.608 109.608 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 109.608 109.608 hfx_ks_matrix 7 8.0 0.000 0.000 99.499 99.499 integrate_four_center 7 9.0 1.708 1.708 99.467 99.467 integrate_four_center_main 7 10.0 0.768 0.768 91.297 91.297 integrate_four_center_bin 449 11.0 90.529 90.529 90.529 90.529 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 63.919 63.919 init_scf_loop 1 4.0 0.000 0.000 51.345 51.345 integrate_four_center_load 7 10.0 0.000 0.000 6.183 6.183 hfx_load_balance 1 11.0 0.002 0.002 6.182 6.182 qs_vxc_create 14 8.0 0.000 0.000 3.650 3.650 xc_vxc_pw_create 14 9.0 0.143 0.143 3.649 3.649 hfx_load_balance_bin 1 12.0 3.101 3.101 3.101 3.101 hfx_load_balance_count 1 12.0 3.063 3.063 3.063 3.063 calculate_rho_elec 15 7.4 0.120 0.120 2.933 2.933 xc_rho_set_and_dset_create 14 10.0 0.119 0.119 2.646 2.646 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.488 2.488 prepare_preconditioner 1 5.0 0.000 0.000 2.488 2.488 make_preconditioner 1 6.0 0.000 0.000 2.488 2.488 ------------------------------------------------------------------------------- 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 0.245 0.270 111.678 111.689 qs_energies 1 2.0 0.000 0.000 111.226 111.234 scf_env_do_scf 1 3.0 0.000 0.000 110.649 110.650 qs_ks_update_qs_env 8 5.0 0.000 0.000 107.940 107.941 rebuild_ks_matrix 7 6.0 0.000 0.000 107.930 107.931 qs_ks_build_kohn_sham_matrix 7 7.0 0.002 0.002 107.930 107.931 hfx_ks_matrix 7 8.0 0.000 0.000 101.333 101.335 integrate_four_center 7 9.0 0.061 0.390 101.323 101.324 integrate_four_center_main 7 10.0 0.004 0.005 89.741 92.874 integrate_four_center_bin 448 11.0 89.736 92.869 89.736 92.869 scf_env_do_scf_inner_loop 7 4.0 0.000 0.002 62.864 62.864 init_scf_loop 1 4.0 0.000 0.000 47.784 47.784 integrate_four_center_load 7 10.0 0.000 0.000 6.692 6.694 hfx_load_balance 1 11.0 0.001 0.001 6.692 6.693 mp_sync 56 11.2 4.092 5.458 4.092 5.458 hfx_load_balance_bin 1 12.0 3.089 3.343 3.089 3.343 hfx_load_balance_count 1 12.0 3.079 3.339 3.079 3.339 qs_vxc_create 14 8.0 0.000 0.000 2.828 2.829 xc_vxc_pw_create 14 9.0 0.008 0.009 2.828 2.829 xc_rho_set_and_dset_create 14 10.0 0.013 0.015 2.154 2.264 ------------------------------------------------------------------------------- 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=18.256, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=90.529, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=3.101, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=3.063, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.708, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.768, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.229, 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=11.371999999999986, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=89.736, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=3.089, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=3.079, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.061, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.004, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.245, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=4.092, 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 89.989 89.989 qs_energies 1 2.0 0.000 0.000 89.553 89.553 mp2_main 1 3.0 0.000 0.000 85.794 85.794 mp2_gpw_main 1 4.0 0.000 0.000 85.654 85.654 rpa_ri_compute_en 1 5.0 0.000 0.000 81.649 81.649 rpa_num_int 1 6.0 0.001 0.001 81.643 81.643 compute_mat_P_omega 1 7.0 0.003 0.003 69.734 69.734 compute_mat_P_omega_contract 10 8.0 9.298 9.298 69.486 69.486 dbt_total 2336 9.6 0.019 0.019 55.432 55.432 dbt_contract 787 11.0 0.059 0.059 46.704 46.704 dbt_tas_total 1149 12.2 0.303 0.303 45.024 45.024 dbt_tas_multiply 807 12.1 0.003 0.003 43.585 43.585 dbt_tas_dbm 807 14.1 0.005 0.005 36.070 36.070 dbm_multiply 807 16.1 36.057 36.057 36.057 36.057 dbt_tas_mm_1N 524 15.1 0.002 0.002 26.717 26.717 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 25.106 25.106 compute_mat_P_omega_calc_M_occ 250 9.0 9.319 9.319 19.191 19.191 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.877 8.877 dbt_tas_mm_2 251 15.0 0.002 0.002 7.633 7.633 dbt_copy 1103 10.7 0.098 0.098 7.262 7.262 compute_QP_energies 1 7.0 0.000 0.000 5.787 5.787 compute_self_energy_cubic_gw 1 8.0 0.055 0.055 5.786 5.786 contract_cubic_gw 21 9.0 0.000 0.000 4.579 4.579 dbt_tas_reserve_blocks_index 3261 14.3 0.539 0.539 4.486 4.486 dbm_reserve_blocks 3628 15.3 4.033 4.033 4.033 4.033 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.997 3.997 scf_env_do_scf 1 3.0 0.000 0.000 3.595 3.595 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 3.594 3.594 dbt_reserve_blocks_index 2280 13.1 0.073 0.073 3.418 3.418 dbt_reserve_blocks_index_array 2222 12.2 0.014 0.014 3.370 3.370 dbt_crop 1042 12.0 1.853 1.853 2.978 2.978 dbt_tas_copy 574 11.4 1.726 1.726 2.856 2.856 compute_W_cubic_GW 10 7.0 0.020 0.020 2.630 2.630 convert_to_new_pgrid 2421 14.1 0.161 0.161 2.612 2.612 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.559 2.559 dbm_copy 1614 15.1 2.451 2.451 2.451 2.451 dbt_reshape 278 11.9 1.378 1.378 2.447 2.447 dbt_tas_reshape 367 15.0 0.009 0.009 2.231 2.231 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 2.063 2.063 get_2c_integrals 1 6.0 0.000 0.000 1.885 1.885 cp_fm_cholesky_decompose 14 8.1 1.857 1.857 1.857 1.857 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.022 40.797 40.807 qs_energies 1 2.0 0.000 0.000 40.643 40.645 mp2_main 1 3.0 0.000 0.001 39.181 39.183 mp2_gpw_main 1 4.0 0.000 0.000 39.122 39.124 rpa_ri_compute_en 1 5.0 0.000 0.000 37.634 37.636 rpa_num_int 1 6.0 0.000 0.002 37.633 37.635 dbt_total 2336 9.6 0.019 0.023 33.388 33.402 compute_mat_P_omega 1 7.0 0.001 0.006 32.118 32.136 compute_mat_P_omega_contract 10 8.0 0.475 0.497 31.958 31.966 dbt_contract 787 11.0 0.046 0.059 24.210 24.217 dbt_tas_total 1149 12.2 0.091 0.109 21.397 21.399 dbt_tas_multiply 807 12.1 0.002 0.003 21.369 21.374 dbt_tas_dbm 807 14.1 0.004 0.005 15.979 15.990 dbm_multiply 807 16.1 12.506 13.527 12.506 13.527 compute_mat_P_omega_calc_M_occ 250 9.0 0.450 0.470 9.403 9.404 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 9.348 9.350 dbt_copy 1149 10.8 0.017 0.021 7.885 8.252 mp_sync 8688 11.6 6.118 8.202 6.118 8.202 dbt_reshape 1136 11.8 3.193 3.403 7.529 7.891 dbt_tas_mm_2 251 15.0 0.002 0.003 7.657 7.662 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 6.437 6.443 dbt_tas_mm_1N 524 15.1 0.002 0.002 5.557 6.241 compute_QP_energies 1 7.0 0.000 0.000 3.508 3.509 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 3.508 3.508 mp_waitall_2 3812 15.3 3.208 3.427 3.208 3.427 dbt_communicate_buffer 1136 12.8 0.057 0.064 3.221 3.386 contract_cubic_gw 21 9.0 0.000 0.000 2.697 2.697 dbt_reserve_blocks_index 2887 13.1 0.078 0.086 2.132 2.651 dbt_reserve_blocks_index_array 2829 12.2 0.010 0.012 2.120 2.637 dbt_tas_reserve_blocks_index 3347 14.5 0.469 0.509 2.110 2.626 dbm_reserve_blocks 3752 15.4 1.748 2.234 1.748 2.234 dbt_crop 1042 12.0 1.038 1.126 1.679 1.893 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 1.486 1.487 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.408 1.417 scf_env_do_scf 1 3.0 0.000 0.000 1.406 1.406 scf_env_do_scf_inner_loop 17 4.0 0.001 0.003 1.405 1.406 dbt_tas_replicate 405 14.1 0.611 0.812 1.290 1.374 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.279 1.286 parallel_gemm_fm 105 8.4 0.000 0.002 1.199 1.211 parallel_gemm_fm_cosma 105 9.4 1.199 1.211 1.199 1.211 convert_to_new_pgrid 2421 14.1 0.030 0.034 0.946 1.161 dbm_copy 1608 15.1 0.910 1.128 0.910 1.128 mp_max_i 2002 9.8 0.769 1.059 0.769 1.059 compute_W_cubic_GW 10 7.0 0.001 0.001 0.924 0.934 ------------------------------------------------------------------------------- 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=27.452999999999996, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=36.057, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_calc_M_occ", label="compute_mat_P_omega_calc_M_occ", y=9.319, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=9.298, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=4.033, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.451, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.378, 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=12.188999999999993, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=12.506, 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=0.45, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.475, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.748, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.91, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.193, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.208, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=6.118, 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 0.019 293.677 293.677 qs_forces 1 2.0 0.000 0.000 293.085 293.085 rebuild_ks_matrix 7 6.6 0.000 0.000 291.332 291.332 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 291.332 291.332 hfx_ks_matrix 7 8.6 0.000 0.000 288.989 288.989 hfx_ri_update_ks 7 9.6 0.000 0.000 249.967 249.967 hfx_ri_update_ks_Pmat 7 10.6 37.415 37.415 249.960 249.960 dbt_total 783 11.1 0.008 0.008 227.205 227.205 qs_energies 1 3.0 0.000 0.000 221.319 221.319 scf_env_do_scf 1 4.0 0.000 0.000 220.923 220.923 qs_ks_update_qs_env 8 6.0 0.000 0.000 219.636 219.636 dbt_contract 207 12.4 0.046 0.046 206.330 206.330 dbt_tas_total 317 14.0 1.730 1.730 203.444 203.444 dbt_tas_multiply 216 13.5 0.001 0.001 199.985 199.985 dbt_tas_dbm 216 15.5 0.001 0.001 190.394 190.394 dbm_multiply 216 17.5 190.390 190.390 190.390 190.390 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 184.309 184.309 dbt_tas_mm_2 91 16.5 0.001 0.001 174.864 174.864 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 140.428 140.428 init_scf_loop 2 5.0 0.000 0.000 80.492 80.492 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 71.702 71.702 hfx_ri_update_forces 1 7.0 1.689 1.689 39.019 39.019 hfx_ri_forces_Pmat_3c 1 8.0 4.804 4.804 20.670 20.670 dbt_copy 409 11.7 0.047 0.047 17.405 17.405 precalc_derivatives 1 8.0 2.210 2.210 14.096 14.096 dbt_reshape 132 13.2 7.747 7.747 12.095 12.095 dbt_tas_mm_3T 77 17.1 0.000 0.000 10.726 10.726 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 10.590 10.590 dbt_tas_reserve_blocks_index 1229 15.4 1.107 1.107 8.643 8.643 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 8.369 8.369 build_3c_derivatives 3 9.0 2.600 2.600 7.945 7.945 dbm_reserve_blocks 1345 16.4 7.657 7.657 7.657 7.657 dbt_reserve_blocks_index 818 14.4 0.129 0.129 6.794 6.794 dbt_reserve_blocks_index_array 795 13.4 0.008 0.008 6.692 6.692 ------------------------------------------------------------------------------- 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 0.009 0.025 58.035 58.046 qs_forces 1 2.0 0.000 0.000 57.776 57.777 rebuild_ks_matrix 7 6.6 0.000 0.000 56.796 56.797 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.002 56.796 56.797 hfx_ks_matrix 7 8.6 0.000 0.001 55.465 55.472 dbt_total 783 11.1 0.007 0.010 49.324 49.342 dbt_contract 207 12.4 0.029 0.034 38.107 38.116 dbt_tas_total 317 14.0 0.051 0.066 33.690 33.690 hfx_ri_update_ks 7 9.6 0.000 0.000 33.633 33.633 hfx_ri_update_ks_Pmat 7 10.6 1.425 1.548 33.626 33.631 dbt_tas_multiply 216 13.5 0.001 0.001 33.581 33.582 qs_energies 1 3.0 0.000 0.000 31.773 31.773 scf_env_do_scf 1 4.0 0.000 0.001 31.596 31.596 qs_ks_update_qs_env 8 6.0 0.000 0.000 30.807 30.807 dbt_tas_dbm 216 15.5 0.001 0.002 28.362 28.363 dbm_multiply 216 17.5 25.089 26.246 25.089 26.246 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 25.991 25.991 hfx_ri_update_forces 1 7.0 0.070 0.076 21.831 21.838 scf_env_do_scf_inner_loop 6 5.0 0.000 0.002 17.751 17.751 hfx_ri_forces_Pmat_3c 1 8.0 0.196 0.216 15.825 15.825 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 15.553 15.553 init_scf_loop 2 5.0 0.000 0.000 13.844 13.845 dbt_tas_mm_2 91 16.5 0.001 0.001 13.498 13.498 dbt_copy 497 12.3 0.014 0.019 10.416 10.927 dbt_reshape 365 13.6 4.163 4.309 8.083 8.443 mp_sync 2665 13.0 5.995 8.306 5.995 8.306 dbt_tas_mm_3T 77 17.1 0.000 0.000 7.274 7.918 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.967 5.968 dbt_tas_mm_3N 37 15.4 0.000 0.000 5.350 5.626 precalc_derivatives 1 8.0 0.094 0.103 4.535 4.536 dbt_tas_reserve_blocks_index 1356 15.8 0.969 0.999 3.778 4.446 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.001 4.255 4.255 dbt_reserve_blocks_index 1051 14.7 0.124 0.135 3.136 3.636 dbt_reserve_blocks_index_array 1028 13.8 0.006 0.008 3.102 3.599 dbm_reserve_blocks 1481 16.7 2.889 3.540 2.889 3.540 dbt_crop 372 13.7 2.023 2.142 2.932 3.093 mp_waitall_2 1138 16.4 2.873 2.990 2.873 2.990 dbt_communicate_buffer 365 14.6 0.014 0.015 2.557 2.683 build_3c_derivatives 3 9.0 0.259 0.289 2.559 2.569 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 2.094 2.099 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 2.016 2.016 convert_to_new_pgrid 648 15.5 0.047 0.095 1.566 1.841 dbt_tas_copy 132 12.5 0.748 0.807 1.466 1.641 dbm_copy 452 16.3 1.323 1.594 1.323 1.594 ------------------------------------------------------------------------------- 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=45.664000000000044, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=190.39, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=37.415, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=7.747, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.657, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.804, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=15.405000000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=25.089, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.425, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=4.163, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.889, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.196, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.873, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=5.995, 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 0.016 0.016 200.594 200.594 qs_energies 1 2.0 0.000 0.000 200.389 200.389 mp2_main 1 3.0 0.000 0.000 195.096 195.096 mp2_gpw_main 1 4.0 0.001 0.001 194.609 194.609 mp2_ri_gpw_compute_in 1 5.0 0.397 0.397 135.966 135.966 mp2_ri_gpw_compute_in_loop 1 6.0 0.014 0.014 126.410 126.410 mp2_eri_3c_integrate_gpw 2656 7.0 0.020 0.020 90.701 90.701 integrate_v_rspace 2666 8.0 0.791 0.791 76.450 76.450 grid_integrate_task_list 2666 9.0 73.442 73.442 73.442 73.442 mp2_ri_gpw_compute_en 1 5.0 0.091 0.091 58.615 58.615 mp2_ri_gpw_compute_en_RI_loop 1 6.0 11.135 11.135 56.606 56.606 mp2_ri_gpw_compute_en_expansio 2080 7.0 3.203 3.203 35.319 35.319 local_gemm 2080 8.0 32.116 32.116 32.116 32.116 dbcsr_multiply_generic 5322 8.0 0.226 0.226 25.219 25.219 ao_to_mo_and_store_B_mult_1 2656 7.0 0.014 0.014 25.201 25.201 pw_transfer 63872 10.6 1.119 1.119 13.066 13.066 calculate_wavefunction 2656 8.0 8.382 8.382 12.786 12.786 multiply_cannon 5322 9.0 0.565 0.565 12.489 12.489 fft_wrap_pw1pw2 53228 11.4 0.123 0.123 11.701 11.701 multiply_cannon_loop 5322 10.0 0.145 0.145 10.909 10.909 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.881 2.881 10.382 10.382 make_m2s 10644 9.0 0.078 0.078 10.206 10.206 make_images 10644 10.0 3.860 3.860 9.811 9.811 multiply_cannon_multrec 5322 11.0 9.117 9.117 9.167 9.167 get_2c_integrals 1 6.0 0.000 0.000 9.157 9.157 fft_wrap_pw1pw2_20 21271 12.4 0.547 0.547 8.207 8.207 compute_2c_integrals 1 7.0 0.006 0.006 8.182 8.182 copy_dbcsr_to_fm 2679 8.0 0.032 0.032 8.176 8.176 compute_2c_integrals_loop_lm 1 8.0 0.011 0.011 8.169 8.169 mp2_eri_2c_integrate_gpw 1 9.0 0.905 0.905 8.158 8.158 mp2_ri_gpw_compute_en_ener 2080 7.0 7.538 7.538 7.538 7.538 fft3d_s 53229 13.4 7.026 7.026 7.072 7.072 dbcsr_complete_redistribute 2689 9.0 1.214 1.214 6.379 6.379 dbcsr_finalize 10708 9.5 0.182 0.182 5.813 5.813 dbcsr_merge_all 8011 10.3 3.908 3.908 5.089 5.089 scf_env_do_scf 1 3.0 0.000 0.000 4.810 4.810 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.810 4.810 potential_pw2rs 5322 10.0 0.162 0.162 4.337 4.337 make_images_data 10644 11.0 0.084 0.084 4.100 4.100 hybrid_alltoall_any 13323 11.6 3.827 3.827 4.081 4.081 ------------------------------------------------------------------------------- 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 0.028 40.175 40.186 qs_energies 1 2.0 0.000 0.000 40.065 40.066 mp2_main 1 3.0 0.000 0.001 37.745 37.746 mp2_gpw_main 1 4.0 0.001 0.002 37.637 37.637 mp2_ri_gpw_compute_in 1 5.0 0.054 0.055 19.230 19.672 mp2_ri_gpw_compute_en 1 5.0 0.217 0.228 18.310 18.662 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 17.911 18.349 mp2_ri_gpw_compute_en_RI_loop 1 6.0 1.484 1.786 17.066 17.078 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 15.528 15.907 integrate_v_rspace 93 8.1 0.113 0.126 15.445 15.825 grid_integrate_task_list 93 9.1 15.042 15.409 15.042 15.409 mp2_ri_gpw_compute_en_expansio 65 7.0 0.123 0.152 12.073 12.476 local_gemm 65 8.0 11.950 12.385 11.950 12.385 mp2_ri_gpw_compute_en_comm 20 7.0 0.092 0.119 3.127 3.661 mp_sendrecv_dm3 1240 8.0 2.501 3.243 2.501 3.243 dbcsr_multiply_generic 176 8.0 0.009 0.010 2.046 2.266 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 2.016 2.238 scf_env_do_scf 1 3.0 0.000 0.000 2.188 2.189 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 2.188 2.189 multiply_cannon 176 9.0 0.019 0.023 1.206 1.294 get_2c_integrals 1 6.0 0.005 0.013 1.242 1.281 multiply_cannon_loop 176 10.0 0.002 0.003 1.135 1.215 multiply_cannon_multrec 246 11.0 0.964 1.019 0.970 1.026 qs_scf_new_mos 10 5.0 0.000 0.000 0.994 1.025 compute_2c_integrals 1 7.0 0.002 0.004 0.925 0.942 make_m2s 352 9.0 0.003 0.004 0.797 0.930 eigensolver 11 5.8 0.001 0.001 0.919 0.920 make_images 352 10.0 0.058 0.060 0.783 0.915 pw_transfer 2120 10.5 0.051 0.055 0.855 0.871 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.819 0.850 mp2_eri_2c_integrate_gpw 1 9.0 0.214 0.219 0.817 0.849 mp_min_d 2 7.0 0.457 0.818 0.457 0.818 ------------------------------------------------------------------------------- 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=66.40199999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=73.442, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=32.116, 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=11.135, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=9.117, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.382, 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=8.233999999999998, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=15.042, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=11.95, 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=1.484, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.964, 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=2.501, 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 0.090 0.090 155.867 155.867 qs_energies 1 2.0 0.000 0.000 154.352 154.352 scf_env_do_scf 1 3.0 0.000 0.000 146.629 146.629 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 146.629 146.629 qs_ks_update_qs_env 15 5.0 0.000 0.000 58.507 58.507 rebuild_ks_matrix 15 6.0 0.000 0.000 57.861 57.861 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 57.860 57.860 qs_scf_new_mos 15 5.0 0.000 0.000 55.016 55.016 eigensolver 15 6.0 0.002 0.002 44.867 44.867 qs_vxc_create 15 8.0 0.048 0.048 40.182 40.182 calculate_dispersion_nonloc 15 9.0 7.727 7.727 34.457 34.457 cp_fm_diag_elpa 15 7.0 0.000 0.000 28.977 28.977 cp_fm_diag_elpa_base 15 8.0 25.948 25.948 28.977 28.977 pw_transfer 1191 10.0 0.082 0.082 28.004 28.004 fft_wrap_pw1pw2 1086 11.0 0.011 0.011 27.774 27.774 qs_rho_update_rho_low 16 5.0 0.000 0.000 22.378 22.378 calculate_rho_elec 16 6.0 0.252 0.252 22.378 22.378 grid_collocate_task_list 16 7.0 20.620 20.620 20.620 20.620 fft_wrap_pw1pw2_150 765 12.0 4.650 4.650 19.969 19.969 sum_up_and_integrate 15 8.0 0.308 0.308 16.021 16.021 integrate_v_rspace 15 9.0 0.024 0.024 15.713 15.713 grid_integrate_task_list 15 10.0 15.021 15.021 15.021 15.021 cp_fm_cholesky_restore 45 7.0 12.985 12.985 12.985 12.985 fft3d_s 1087 13.0 11.769 11.769 11.779 11.779 gspace_mixing 14 5.0 0.200 0.200 11.726 11.726 broyden_mixing 14 6.0 10.979 10.979 10.980 10.980 pw_scatter_s 585 13.1 8.395 8.395 8.395 8.395 fft_wrap_pw1pw2_200 197 12.3 1.006 1.006 7.601 7.601 copy_dbcsr_to_fm 16 5.9 0.001 0.001 7.099 7.099 dbcsr_complete_redistribute 46 8.3 3.028 3.028 6.871 6.871 cp_fm_upper_to_full 30 8.0 5.931 5.931 5.931 5.931 xc_vxc_pw_create 15 9.0 0.254 0.254 5.676 5.676 vdW_energy 15 10.0 5.076 5.076 5.076 5.076 init_scf_run 1 3.0 0.000 0.000 3.805 3.805 xc_pw_derive 90 11.0 0.001 0.001 3.660 3.660 calculate_dm_sparse 15 6.0 0.038 0.038 3.441 3.441 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.326 3.326 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 3.294 3.294 ------------------------------------------------------------------------------- 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 0.116 0.131 67.882 67.892 qs_energies 1 2.0 0.000 0.000 67.437 67.442 scf_env_do_scf 1 3.0 0.000 0.001 62.922 62.923 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 62.922 62.923 qs_ks_update_qs_env 15 5.0 0.000 0.000 28.457 28.469 rebuild_ks_matrix 15 6.0 0.000 0.000 28.420 28.431 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.004 28.420 28.431 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.882 20.897 calculate_rho_elec 16 6.0 0.007 0.007 20.881 20.896 grid_collocate_task_list 16 7.0 19.168 19.644 19.168 19.644 sum_up_and_integrate 15 8.0 0.017 0.022 15.964 16.037 integrate_v_rspace 15 9.0 0.001 0.001 15.947 16.029 grid_integrate_task_list 15 10.0 14.644 15.193 14.644 15.193 qs_scf_new_mos 15 5.0 0.000 0.001 14.159 14.185 eigensolver 15 6.0 0.002 0.002 13.034 13.101 qs_vxc_create 15 8.0 0.001 0.001 12.065 12.081 pw_transfer 1191 10.0 0.099 0.109 9.870 9.990 fft_wrap_pw1pw2 1086 11.0 0.014 0.016 9.668 9.812 calculate_dispersion_nonloc 15 9.0 0.989 1.091 9.664 9.694 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.119 9.127 cp_fm_diag_elpa_base 15 8.0 8.938 8.986 9.111 9.111 fft3d_ps 1086 13.0 3.170 3.608 6.541 7.377 fft_wrap_pw1pw2_150 765 12.0 0.846 1.032 6.243 6.299 mp_alltoall_z22v 1086 15.0 2.681 4.131 2.681 4.131 cp_fm_cholesky_restore 45 7.0 3.731 3.852 3.731 3.852 fft_wrap_pw1pw2_200 197 12.3 0.581 0.725 3.246 3.335 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.774 2.774 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.403 2.655 xc_vxc_pw_create 15 9.0 0.018 0.026 2.400 2.454 x_to_yz 585 14.1 0.405 0.436 1.729 2.393 yz_to_x 501 13.9 0.255 0.292 1.612 2.381 xc_pw_derive 90 11.0 0.001 0.001 1.673 1.769 density_rs2pw 16 7.0 0.001 0.001 1.456 1.647 rs_pw_transfer 158 9.4 0.002 0.015 1.338 1.599 build_core_ppnl 1 5.0 1.410 1.585 1.410 1.585 vdW_energy 15 10.0 1.448 1.527 1.448 1.527 init_scf_run 1 3.0 0.000 0.000 1.503 1.505 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.386 1.387 ------------------------------------------------------------------------------- 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=69.52399999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=25.948, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.62, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=15.021, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=12.985, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=11.769, 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=18.231, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.938, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.168, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.644, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.731, 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=3.17, 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 0.083 0.083 302.414 302.414 qs_energies 1 2.0 0.000 0.000 302.261 302.261 ls_scf 1 3.0 0.000 0.000 300.890 300.890 ls_scf_main 1 4.0 0.002 0.002 290.383 290.383 density_matrix_trs4 11 5.0 0.015 0.015 185.001 185.001 ls_scf_dm_to_ks 11 5.0 0.000 0.000 99.260 99.260 matrix_ls_to_qs 11 6.0 0.000 0.000 95.575 95.575 dbcsr_multiply_generic 185 6.1 1.008 1.008 87.103 87.103 arnoldi_extremal 12 6.1 0.000 0.000 81.053 81.053 arnoldi_normal_ev 12 7.1 0.051 0.051 81.052 81.052 build_subspace 23 8.1 0.099 0.099 79.590 79.590 dbcsr_matrix_vector_mult 652 9.0 0.309 0.309 78.981 78.981 dbcsr_matrix_vector_mult_local 652 10.0 76.976 76.976 76.986 76.986 dbcsr_copy_into_existing 11 7.0 51.492 51.492 51.492 51.492 multiply_cannon 185 7.1 0.410 0.410 50.581 50.581 dbcsr_complete_redistribute 23 7.5 34.212 34.212 48.312 48.312 matrix_decluster 11 7.0 0.000 0.000 44.082 44.082 multiply_cannon_loop 185 8.1 0.289 0.289 37.293 37.293 make_m2s 370 7.1 0.041 0.041 30.777 30.777 make_images 370 8.1 12.893 12.893 27.953 27.953 multiply_cannon_multrec 185 9.1 26.753 26.753 26.801 26.801 dbcsr_finalize 646 7.5 0.337 0.337 18.890 18.890 dbcsr_merge_all 597 8.5 2.956 2.956 17.272 17.272 setup_rec_index_2d 370 8.1 12.764 12.764 12.764 12.764 dbcsr_sort_indices 1103 9.9 12.700 12.700 12.700 12.700 tree_to_linear_d 110 9.4 12.685 12.685 12.685 12.685 quick_finalize 395 10.0 0.561 0.561 11.075 11.075 dbcsr_special_finalize 370 9.1 0.002 0.002 10.258 10.258 calculate_norms 370 9.1 10.203 10.203 10.203 10.203 ls_scf_init_scf 1 4.0 0.000 0.000 9.778 9.778 ls_scf_init_matrix_S 1 5.0 0.000 0.000 9.423 9.423 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 8.720 8.720 dbcsr_dot_sd 144 6.3 7.563 7.563 7.564 7.564 matrix_qs_to_ls 12 5.1 0.000 0.000 6.265 6.265 matrix_cluster 12 6.1 0.000 0.000 6.265 6.265 ------------------------------------------------------------------------------- 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 0.022 76.992 77.003 qs_energies 1 2.0 0.000 0.000 76.868 76.868 ls_scf 1 3.0 0.000 0.000 76.811 76.812 ls_scf_main 1 4.0 0.001 0.007 73.951 73.952 density_matrix_trs4 11 5.0 0.007 0.022 71.147 71.208 dbcsr_multiply_generic 185 6.1 0.065 0.078 66.503 66.834 multiply_cannon 185 7.1 0.037 0.041 55.143 56.204 multiply_cannon_loop 185 8.1 0.128 0.168 52.438 54.319 multiply_cannon_multrec 1480 9.1 31.882 35.995 32.164 36.259 mp_waitall_1 11936 10.3 18.023 22.602 18.023 22.602 multiply_cannon_metrocomm3 1480 9.1 0.016 0.021 10.447 17.387 multiply_cannon_metrocomm1 1480 9.1 0.009 0.013 4.264 8.174 make_m2s 370 7.1 0.037 0.040 7.779 7.865 make_images 370 8.1 0.679 0.717 7.636 7.724 calculate_norms 2960 9.1 5.363 6.913 5.363 6.913 make_images_data 370 9.1 0.010 0.014 3.583 3.905 arnoldi_extremal 12 6.1 0.000 0.001 3.526 3.547 arnoldi_normal_ev 12 7.1 0.002 0.008 3.526 3.547 hybrid_alltoall_any 393 9.9 0.209 0.936 3.133 3.435 mp_sum_l 1199 5.3 2.474 3.430 2.474 3.430 build_subspace 23 8.1 0.023 0.029 3.410 3.412 dbcsr_matrix_vector_mult 652 9.0 0.017 0.062 2.676 2.886 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.425 2.561 dbcsr_matrix_vector_mult_local 652 10.0 1.934 2.350 1.936 2.353 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.444 2.268 dbcsr_complete_redistribute 23 7.5 1.309 1.421 2.133 2.259 ls_scf_init_scf 1 4.0 0.000 0.000 2.214 2.215 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.188 2.194 matrix_ls_to_qs 11 6.0 0.000 0.000 2.065 2.193 make_images_pack 370 9.1 1.843 2.045 1.847 2.049 matrix_decluster 11 7.0 0.000 0.000 1.915 2.045 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.995 1.998 buffer_matrices_ensure_size 370 8.1 1.521 1.787 1.521 1.787 dbcsr_finalize 646 7.5 0.008 0.009 1.426 1.556 ------------------------------------------------------------------------------- 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=89.88499999999999, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=76.976, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=51.492, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=34.212, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=26.753, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images", label="make_images", y=12.893, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=10.203, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=15.328000000000003, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.934, 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=1.309, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=31.882, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images", label="make_images", y=0.679, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.363, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=18.023, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.474, yerr=0.0 Running dbcsr.inp with 1 threads and 32 ranks... done. Running dbcsr.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/dbcsr_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.008 75.865 75.865 lib_test 1 2.0 0.000 0.000 75.856 75.856 dbcsr_run_tests 3 3.0 0.002 0.002 75.856 75.856 test_multiplies_multiproc 3 4.0 0.002 0.002 59.377 59.377 dbcsr_redistribute 9 5.0 38.669 38.669 40.299 40.299 dbcsr_multiply_generic 9 5.0 0.001 0.001 17.680 17.680 dbcsr_make_random_matrix 9 4.0 13.137 13.137 16.362 16.362 multiply_cannon 9 6.0 0.002 0.002 12.704 12.704 multiply_cannon_loop 9 7.0 0.021 0.021 12.326 12.326 multiply_cannon_multrec 9 8.0 12.305 12.305 12.305 12.305 dbcsr_finalize 27 5.7 0.022 0.022 5.846 5.846 dbcsr_merge_all 18 6.5 2.061 2.061 5.086 5.086 dbcsr_data_release 975 7.6 2.880 2.880 2.880 2.880 tree_to_linear_d 9 7.0 1.980 1.980 1.980 1.980 make_m2s 18 6.0 0.001 0.001 1.751 1.751 make_images 18 7.0 0.604 0.604 1.690 1.690 ------------------------------------------------------------------------------- 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 0.012 19.270 19.275 lib_test 1 2.0 0.000 0.000 19.242 19.259 dbcsr_run_tests 3 3.0 0.000 0.001 19.240 19.258 test_multiplies_multiproc 3 4.0 0.000 0.003 18.331 18.372 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.916 17.029 multiply_cannon 9 6.0 0.002 0.002 15.049 15.391 multiply_cannon_loop 9 7.0 0.002 0.003 14.737 15.079 multiply_cannon_multrec 72 8.0 12.286 12.782 12.287 12.783 mp_waitall_1 576 9.2 2.793 3.650 2.793 3.650 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 2.148 3.004 dbcsr_make_random_matrix 9 4.0 0.726 0.740 0.875 0.904 dbcsr_data_release 444 7.6 0.785 0.899 0.785 0.899 mp_sum_l 470 2.5 0.439 0.845 0.439 0.845 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.433 0.839 dbcsr_finalize 27 5.7 0.000 0.000 0.740 0.822 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.295 0.788 make_m2s 18 6.0 0.001 0.001 0.710 0.762 make_images 18 7.0 0.023 0.024 0.706 0.759 dbcsr_destroy 111 5.9 0.000 0.001 0.621 0.720 dbcsr_merge_all 18 6.5 0.108 0.132 0.574 0.630 dbcsr_redistribute 9 5.0 0.263 0.322 0.445 0.481 make_images_data 18 8.0 0.001 0.001 0.383 0.437 hybrid_alltoall_any 18 9.0 0.028 0.123 0.334 0.402 dbcsr_data_copy_aa2 18 7.5 0.340 0.398 0.340 0.398 ------------------------------------------------------------------------------- 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=6.813000000000002, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=38.669, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.137, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=12.305, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.88, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.061, 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=1.8699999999999974, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.263, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.726, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=12.286, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.785, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.108, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.793, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.439, 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 0.057 0.057 148.042 148.042 qs_mol_dyn_low 1 2.0 0.004 0.004 146.102 146.102 velocity_verlet 5 3.0 0.005 0.005 118.946 118.946 qmmm_el_coupling 6 3.8 0.000 0.000 87.902 87.902 qmmm_elec_with_gaussian 6 4.8 0.043 0.043 87.897 87.897 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 86.715 86.715 qmmm_elec_gaussian_low_G 6 6.8 85.781 85.781 85.781 85.781 qs_forces 6 3.8 0.001 0.001 48.082 48.082 qs_energies 6 4.8 0.000 0.000 42.488 42.488 scf_env_do_scf 6 5.8 0.001 0.001 39.823 39.823 rebuild_ks_matrix 45 8.4 0.000 0.000 35.513 35.513 qs_ks_build_kohn_sham_matrix 45 9.4 0.006 0.006 35.513 35.513 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 34.465 34.465 qs_ks_update_qs_env 45 7.8 0.000 0.000 30.393 30.393 pw_transfer 966 12.3 0.063 0.063 20.857 20.857 fft_wrap_pw1pw2 801 13.6 0.007 0.007 20.609 20.609 fft_wrap_pw1pw2_150 507 15.2 3.144 3.144 20.205 20.205 qs_vxc_create 45 10.4 0.001 0.001 17.756 17.756 xc_vxc_pw_create 45 11.4 0.803 0.803 17.755 17.755 xc_pw_derive 270 13.4 0.002 0.002 11.479 11.479 xc_rho_set_and_dset_create 45 12.4 1.557 1.557 9.882 9.882 pw_integral_ab 2539 7.4 8.957 8.957 8.957 8.957 fft3d_s 802 15.6 8.870 8.870 8.880 8.880 qs_rho_update_rho_low 45 7.9 0.000 0.000 8.344 8.344 calculate_rho_elec 45 8.9 0.700 0.700 8.344 8.344 xc_pw_divergence 45 12.4 0.001 0.001 6.996 6.996 pw_scatter_s 429 15.8 6.861 6.861 6.861 6.861 qmmm_forces 6 3.8 0.004 0.004 6.569 6.569 qs_ks_ddapc 45 10.4 0.001 0.001 6.169 6.169 qmmm_forces_with_gaussian 6 4.8 0.052 0.052 6.086 6.086 init_scf_loop 6 6.8 0.000 0.000 5.352 5.352 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 5.143 5.143 sum_up_and_integrate 45 10.4 1.174 1.174 4.785 4.785 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.679 4.679 pw_poisson_solve 51 9.9 1.170 1.170 4.565 4.565 cp_ddapc_apply_CD 45 11.4 0.007 0.007 4.252 4.252 density_rs2pw 45 9.9 0.002 0.002 4.087 4.087 qmmm_forces_gaussian_low_G 6 6.8 3.899 3.899 3.899 3.899 integrate_v_rspace 45 11.4 0.008 0.008 3.611 3.611 grid_collocate_task_list 45 9.9 3.557 3.557 3.557 3.557 ------------------------------------------------------------------------------- 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 0.039 0.056 66.382 66.393 qs_mol_dyn_low 1 2.0 0.003 0.004 65.189 65.257 qs_forces 6 3.8 0.001 0.001 46.560 46.561 qs_energies 6 4.8 0.000 0.000 44.338 44.338 scf_env_do_scf 6 5.8 0.000 0.001 43.258 43.258 scf_env_do_scf_inner_loop 113 6.2 0.003 0.023 41.408 41.409 rebuild_ks_matrix 119 8.1 0.000 0.001 31.282 31.292 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.017 31.281 31.292 qs_ks_update_qs_env 119 7.3 0.001 0.001 29.378 29.385 velocity_verlet 5 3.0 0.002 0.003 28.975 28.979 pw_transfer 2446 12.3 0.186 0.211 22.419 23.087 fft_wrap_pw1pw2 2059 13.4 0.021 0.024 21.987 22.647 fft_wrap_pw1pw2_150 1321 14.9 3.779 4.393 21.252 21.914 qs_vxc_create 119 10.1 0.002 0.003 17.451 17.464 xc_vxc_pw_create 119 11.1 0.226 0.292 17.449 17.462 fft3d_ps 2059 15.4 7.593 8.253 13.598 15.499 xc_pw_derive 714 13.1 0.008 0.009 13.050 13.450 qs_rho_update_rho_low 119 7.3 0.000 0.001 11.928 11.933 calculate_rho_elec 119 8.3 0.053 0.061 11.928 11.932 sum_up_and_integrate 119 10.1 0.103 0.118 9.857 9.898 integrate_v_rspace 119 11.1 0.003 0.004 9.753 9.797 qmmm_forces 6 3.8 0.003 0.004 9.796 9.796 qmmm_forces_with_gaussian 6 4.8 0.009 0.011 9.294 9.544 xc_pw_divergence 119 12.1 0.004 0.004 8.657 9.004 xc_rho_set_and_dset_create 119 12.1 0.470 0.576 8.320 8.619 qmmm_el_coupling 6 3.8 0.000 0.000 7.766 7.963 qmmm_elec_with_gaussian 6 4.8 0.004 0.005 7.765 7.961 density_rs2pw 119 9.3 0.006 0.007 7.017 7.388 mp_alltoall_z22v 2059 17.4 4.375 7.112 4.375 7.112 rs_pw_transfer 988 11.5 0.011 0.013 6.287 6.623 potential_pw2rs 119 12.1 0.006 0.007 5.640 5.653 grid_collocate_task_list 119 9.3 4.694 4.960 4.694 4.960 pw_restrict_s3 18 5.8 2.458 2.571 4.343 4.575 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.366 4.510 x_to_yz 1095 16.8 0.955 1.070 3.137 4.441 yz_to_x 964 16.0 0.619 0.802 2.812 4.209 grid_integrate_task_list 119 12.1 3.794 4.004 3.794 4.004 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.639 3.768 qmmm_forces_gaussian_low_G 6 6.8 3.594 3.751 3.594 3.751 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 3.353 3.553 pw_prolongate_s3 18 6.8 1.887 1.999 3.353 3.553 qmmm_elec_gaussian_low_G 6 6.8 3.000 3.122 3.000 3.122 mp_waitany 4028 12.8 2.249 2.920 2.249 2.920 pw_gather_p 964 15.0 2.324 2.678 2.324 2.678 qs_ks_ddapc 119 10.1 0.002 0.003 2.382 2.480 rs_pw_transfer_PW2RS_150 125 13.9 0.819 0.964 2.340 2.415 pw_scatter_p 1095 15.8 2.199 2.377 2.199 2.377 qs_scf_new_mos 113 7.2 0.000 0.001 2.352 2.360 qs_scf_loop_do_ot 113 8.2 0.001 0.001 2.351 2.359 pw_integral_ab 2761 7.7 1.842 2.006 2.143 2.330 dbcsr_multiply_generic 2588 12.3 0.063 0.067 2.242 2.315 ot_scf_mini 113 9.2 0.001 0.001 2.255 2.259 rs_pw_transfer_RS2PW_150 125 11.2 0.666 0.831 1.920 2.244 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.921 1.922 init_scf_loop 6 6.8 0.000 0.000 1.847 1.847 mp_sum_d 5822 12.2 0.877 1.738 0.877 1.738 ot_mini 113 10.2 0.001 0.001 1.377 1.383 ------------------------------------------------------------------------------- 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=26.972999999999985, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=85.781, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=8.957, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.87, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=6.861, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.899, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.557, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=3.144, 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 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=33.711000000000006, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=3.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=1.842, 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="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.594, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.694, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=3.779, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.794, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.375, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.593, yerr=0.0 Summary: Performance test took 37 minutes. Status: OK Removing intermediate container 1a5b3822a181 ---> 4e312c941866 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in f643e4d3d7c6 Removing intermediate container f643e4d3d7c6 ---> eb656b851f26 Step 42/42 : ENTRYPOINT [] ---> Running in d7cc640537e2 Removing intermediate container d7cc640537e2 ---> 9b62ef077898 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 9b62ef077898 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: 2023-05-21 12:31:55+00:00