StartDate: 2023-08-22 19:14:30+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 48569ea349cb18ceba39f7b29707d418937e7537 CommitTime: 2023-08-22 17:27:34 +0200 CommitAuthor: Matthias Krack CommitSubject: Switch to latest oneAPI HPC Toolkit version 2023.2.1 #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=48569ea349cb18ceba39f7b29707d418937e7537 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 383.9MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu b237fe92c417: Pulling fs layer b237fe92c417: Verifying Checksum b237fe92c417: Download complete b237fe92c417: Pull complete Digest: sha256:ec050c32e4a6085b423d36ecd025c0d3ff00c38ab93a3d71a460ff1c44fa6d77 Status: Downloaded newer image for ubuntu:22.04 ---> 01f29b872827 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> ed64d4bb2bb3 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 6d64b6caa119 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 528403065b56 Step 5/42 : RUN mkdir scripts ---> Using cache ---> 2a7005b78c0e 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 ---> 79098f2a61a6 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 016fb3bf205d Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> ea5f28b1e1f8 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 767ac113086c Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 1d159a3113a2 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 837e9801a1b9 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> e44fec745045 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 720c06412111 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 5373ea6abc17 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 68d9e0e398d7 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 64760ac7a9c1 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> ddc0d0908887 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> cdbd05e994b4 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> d2e08907b5bb Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 336098c3bd03 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 1791da06b70f Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> a44961f0b64e Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 62be1a5cfe61 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 4f87b58cf817 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 0458d246ac05 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> dbfdbc9c4cc4 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 41b533aa1375 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 8475af688f1d Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> c14489066aca Step 30/42 : COPY ./Makefile . ---> Using cache ---> df1b2cadb2fb Step 31/42 : COPY ./src ./src ---> Using cache ---> 5299335640d2 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> a39b277d2006 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 398f4a094358 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 55d164ee68c1 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 55d164ee68c1 ---> c289a1418903 Step 35/42 : COPY ./data ./data ---> ea76d0449091 Step 36/42 : COPY ./tests ./tests ---> c0ffd6b96c80 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 351bc3c91bd7 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 012bfc4c8085 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 113f5158399c Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 7cc304de1722 ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 75 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 0.033 0.033 91.640 91.640 qs_mol_dyn_low 1 2.0 0.003 0.003 91.069 91.069 qs_forces 11 3.9 0.001 0.001 91.027 91.027 qs_energies 11 4.9 0.001 0.001 84.937 84.937 scf_env_do_scf 11 5.9 0.002 0.002 73.587 73.587 velocity_verlet 10 3.0 0.002 0.002 58.742 58.742 scf_env_do_scf_inner_loop 108 6.5 0.012 0.012 57.013 57.013 rebuild_ks_matrix 119 8.3 0.001 0.001 21.359 21.359 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 21.358 21.358 dbcsr_multiply_generic 2286 12.5 0.158 0.158 21.245 21.245 qs_scf_new_mos 108 7.5 0.001 0.001 21.063 21.063 qs_scf_loop_do_ot 108 8.5 0.001 0.001 21.063 21.063 qs_rho_update_rho_low 119 7.7 0.001 0.001 20.223 20.223 calculate_rho_elec 119 8.7 0.965 0.965 20.223 20.223 qs_ks_update_qs_env 119 7.6 0.001 0.001 19.705 19.705 ot_scf_mini 108 9.5 0.002 0.002 19.696 19.696 init_scf_loop 11 6.9 0.000 0.000 16.462 16.462 grid_collocate_task_list 119 9.7 15.924 15.924 15.924 15.924 prepare_preconditioner 11 7.9 0.000 0.000 13.891 13.891 make_preconditioner 11 8.9 0.000 0.000 13.891 13.891 sum_up_and_integrate 119 10.3 0.805 0.805 13.729 13.729 integrate_v_rspace 119 11.3 0.125 0.125 12.924 12.924 make_full_inverse_cholesky 11 9.9 0.015 0.015 12.721 12.721 ot_mini 108 10.5 0.001 0.001 12.636 12.636 make_m2s 4572 13.5 0.045 0.045 10.971 10.971 grid_integrate_task_list 119 12.3 10.958 10.958 10.958 10.958 qs_ot_get_derivative 108 11.5 0.001 0.001 6.916 6.916 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.798 6.798 multiply_cannon 2286 13.5 0.177 0.177 6.349 6.349 multiply_cannon_loop 2286 14.5 0.059 0.059 5.883 5.883 pw_transfer 1439 11.6 0.066 0.066 5.878 5.878 multiply_cannon_multrec 2286 15.5 5.770 5.770 5.822 5.822 ot_diis_step 108 11.5 0.003 0.003 5.717 5.717 make_images 4572 14.5 2.251 2.251 5.668 5.668 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.656 5.656 dbcsr_make_dense_low 5837 15.5 0.080 0.080 5.642 5.642 make_dense_data 5837 16.5 5.021 5.021 5.548 5.548 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.227 5.227 apply_single 119 13.6 0.000 0.000 5.227 5.227 dbcsr_make_images_dense 3978 14.8 0.017 0.017 4.969 4.969 fft_wrap_pw1pw2_140 487 13.2 0.432 0.432 4.821 4.821 cp_fm_cholesky_decompose 22 10.9 4.510 4.510 4.510 4.510 cp_fm_cholesky_invert 11 10.9 4.157 4.157 4.157 4.157 init_scf_run 11 5.9 0.003 0.003 3.937 3.937 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.934 3.934 dbcsr_copy 2102 12.0 0.236 0.236 3.898 3.898 dbcsr_complete_redistribute 329 12.2 1.940 1.940 3.654 3.654 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.607 3.607 dbcsr_copy_into_existing 22 7.9 3.605 3.605 3.606 3.606 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.463 3.463 wfi_extrapolate 11 7.9 0.001 0.001 3.421 3.421 qs_ot_get_p 119 10.4 0.001 0.001 3.414 3.414 density_rs2pw 119 9.7 0.005 0.005 3.334 3.334 qs_create_task_list 11 7.9 0.000 0.000 3.244 3.244 generate_qs_task_list 11 8.9 1.957 1.957 3.244 3.244 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.961 2.961 fft3d_s 1202 14.6 2.943 2.943 2.948 2.948 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.785 2.785 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.625 2.625 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.302 2.302 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.277 2.277 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 2.073 2.073 dbcsr_data_release 279532 16.0 2.062 2.062 2.062 2.062 qs_ot_p2m_diag 50 11.0 0.154 0.154 2.023 2.023 pw_poisson_solve 119 10.3 0.347 0.347 1.988 1.988 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.870 1.870 potential_pw2rs 119 12.3 0.048 0.048 1.841 1.841 ------------------------------------------------------------------------------- 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 0.029 51.162 51.174 qs_mol_dyn_low 1 2.0 0.004 0.005 51.020 51.025 qs_forces 11 3.9 0.002 0.002 50.975 50.975 qs_energies 11 4.9 0.001 0.001 47.763 47.765 scf_env_do_scf 11 5.9 0.001 0.003 43.835 43.835 scf_env_do_scf_inner_loop 108 6.5 0.003 0.021 40.474 40.475 velocity_verlet 10 3.0 0.001 0.003 30.275 30.276 rebuild_ks_matrix 119 8.3 0.001 0.001 18.216 18.265 qs_ks_build_kohn_sham_matrix 119 9.3 0.017 0.020 18.215 18.264 qs_ks_update_qs_env 119 7.6 0.001 0.001 16.223 16.269 dbcsr_multiply_generic 2286 12.5 0.083 0.086 15.724 15.837 qs_rho_update_rho_low 119 7.7 0.001 0.001 14.447 14.455 calculate_rho_elec 119 8.7 0.031 0.032 14.446 14.454 sum_up_and_integrate 119 10.3 0.039 0.043 13.347 13.365 integrate_v_rspace 119 11.3 0.004 0.005 13.308 13.326 qs_scf_new_mos 108 7.5 0.001 0.001 12.780 12.839 qs_scf_loop_do_ot 108 8.5 0.001 0.001 12.779 12.838 ot_scf_mini 108 9.5 0.002 0.003 12.056 12.111 multiply_cannon 2286 13.5 0.146 0.154 11.585 11.979 multiply_cannon_loop 2286 14.5 0.105 0.113 10.940 11.166 grid_collocate_task_list 119 9.7 9.687 10.084 9.687 10.084 mp_waitall_1 158411 16.6 8.608 8.979 8.608 8.979 grid_integrate_task_list 119 12.3 8.704 8.874 8.704 8.874 ot_mini 108 10.5 0.001 0.001 7.152 7.210 multiply_cannon_metrocomm3 18288 15.5 0.047 0.050 6.565 6.850 pw_transfer 1439 11.6 0.071 0.080 4.619 4.710 density_rs2pw 119 9.7 0.006 0.006 4.275 4.687 fft_wrap_pw1pw2 1201 12.6 0.010 0.010 4.467 4.556 multiply_cannon_multrec 18288 15.5 3.934 4.037 3.947 4.049 fft_wrap_pw1pw2_140 487 13.2 0.747 0.800 3.832 3.965 potential_pw2rs 119 12.3 0.007 0.007 3.954 3.963 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.692 3.757 apply_single 119 13.6 0.000 0.000 3.692 3.757 ot_diis_step 108 11.5 0.003 0.003 3.645 3.645 qs_ot_get_derivative 108 11.5 0.001 0.001 3.487 3.540 init_scf_loop 11 6.9 0.000 0.000 3.342 3.342 fft3d_ps 1201 14.6 1.514 1.679 2.878 3.051 make_m2s 4572 13.5 0.048 0.056 2.885 2.945 init_scf_run 11 5.9 0.000 0.006 2.758 2.759 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.758 2.758 transfer_pw2rs 487 13.2 0.007 0.007 2.739 2.742 make_images 4572 14.5 0.119 0.123 2.535 2.602 transfer_rs2pw 487 10.6 0.007 0.007 2.149 2.579 wfi_extrapolate 11 7.9 0.001 0.001 2.497 2.498 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.152 2.157 mp_waitany 9880 13.7 1.707 2.152 1.707 2.152 qs_ot_get_p 119 10.4 0.001 0.001 1.603 1.650 transfer_rs2pw_140 130 11.5 0.210 0.243 1.194 1.626 make_images_data 4572 15.5 0.040 0.046 1.416 1.562 transfer_pw2rs_140 130 13.9 0.450 0.481 1.464 1.486 hybrid_alltoall_any 4725 16.4 0.071 0.197 1.247 1.349 prepare_preconditioner 11 7.9 0.000 0.000 1.327 1.338 make_preconditioner 11 8.9 0.000 0.000 1.327 1.338 mp_alltoall_d11v 2130 13.8 0.977 1.274 0.977 1.274 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.205 1.219 mp_alltoall_z22v 1201 16.6 1.065 1.162 1.065 1.162 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.057 1.092 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.048 1.069 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 1.052 1.054 transfer_pw2rs_50 119 14.3 0.387 0.399 0.994 1.028 ------------------------------------------------------------------------------- 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=49.457, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.924, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.958, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.77, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.021, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.51, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", 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=18.522, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.687, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.704, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.934, 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="mp_waitany", label="mp_waitany", y=1.707, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.608, 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 0.037 116.932 116.932 qs_mol_dyn_low 1 2.0 0.003 0.003 116.286 116.286 qs_forces 11 3.9 0.001 0.001 116.242 116.242 qs_energies 11 4.9 0.001 0.001 108.108 108.108 scf_env_do_scf 11 5.9 0.002 0.002 94.757 94.757 scf_env_do_scf_inner_loop 96 6.5 0.012 0.012 76.419 76.419 velocity_verlet 10 3.0 0.002 0.002 74.815 74.815 rebuild_ks_matrix 107 8.3 0.001 0.001 35.232 35.232 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 35.231 35.231 qs_rho_update_rho_low 107 7.7 0.001 0.001 33.035 33.035 calculate_rho_elec 107 8.7 0.867 0.867 33.035 33.035 qs_ks_update_qs_env 107 7.6 0.001 0.001 31.480 31.480 grid_collocate_task_list 107 9.7 28.918 28.918 28.918 28.918 sum_up_and_integrate 107 10.3 0.716 0.716 28.215 28.215 integrate_v_rspace 107 11.3 0.084 0.084 27.499 27.499 grid_integrate_task_list 107 12.3 25.390 25.390 25.390 25.390 dbcsr_multiply_generic 1966 12.4 0.138 0.138 19.376 19.376 qs_scf_new_mos 96 7.5 0.001 0.001 19.019 19.019 qs_scf_loop_do_ot 96 8.5 0.001 0.001 19.019 19.019 init_scf_loop 11 6.9 0.000 0.000 18.205 18.205 ot_scf_mini 96 9.5 0.002 0.002 17.804 17.804 prepare_preconditioner 11 7.9 0.000 0.000 14.014 14.014 make_preconditioner 11 8.9 0.000 0.000 14.014 14.014 make_full_inverse_cholesky 11 9.9 0.027 0.027 12.820 12.820 ot_mini 96 10.5 0.001 0.001 11.310 11.310 make_m2s 3932 13.4 0.040 0.040 9.968 9.968 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.051 7.051 qs_ot_get_derivative 96 11.5 0.001 0.001 6.022 6.022 pw_transfer 1295 11.6 0.059 0.059 5.975 5.975 multiply_cannon 1966 13.4 0.157 0.157 5.873 5.873 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.725 5.725 init_scf_run 11 5.9 0.003 0.003 5.657 5.657 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.654 5.654 multiply_cannon_loop 1966 14.4 0.042 0.042 5.446 5.446 multiply_cannon_multrec 1966 15.4 5.358 5.358 5.404 5.404 ot_diis_step 96 11.5 0.003 0.003 5.286 5.286 make_images 3932 14.4 2.075 2.075 5.255 5.255 dbcsr_make_dense_low 4961 15.5 0.057 0.057 5.030 5.030 wfi_extrapolate 11 7.9 0.001 0.001 4.999 4.999 make_dense_data 4961 16.5 4.569 4.569 4.961 4.961 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.937 4.937 apply_single 107 13.6 0.000 0.000 4.936 4.936 fft_wrap_pw1pw2_140 439 13.2 0.547 0.547 4.852 4.852 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.620 4.620 cp_fm_cholesky_decompose 22 10.9 4.455 4.455 4.455 4.455 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.447 4.447 cp_fm_cholesky_invert 11 10.9 4.146 4.146 4.146 4.146 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.099 4.099 qs_create_task_list 11 7.9 0.000 0.000 3.705 3.705 generate_qs_task_list 11 8.9 2.386 2.386 3.705 3.705 dbcsr_complete_redistribute 317 12.2 1.927 1.927 3.677 3.677 dbcsr_copy 1855 11.9 0.222 0.222 3.608 3.608 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.511 3.511 dbcsr_copy_into_existing 22 7.9 3.352 3.352 3.353 3.353 density_rs2pw 107 9.7 0.004 0.004 3.249 3.249 qs_ot_get_p 107 10.4 0.001 0.001 3.169 3.169 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.022 3.022 fft3d_s 1082 14.6 2.952 2.952 2.957 2.957 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.534 2.534 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.362 2.362 ------------------------------------------------------------------------------- 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 0.033 78.456 78.475 qs_mol_dyn_low 1 2.0 0.003 0.003 78.324 78.329 qs_forces 11 3.9 0.002 0.002 78.281 78.282 qs_energies 11 4.9 0.001 0.001 73.212 73.215 scf_env_do_scf 11 5.9 0.000 0.002 67.828 67.829 scf_env_do_scf_inner_loop 96 6.5 0.003 0.018 62.818 62.818 velocity_verlet 10 3.0 0.001 0.003 46.291 46.292 rebuild_ks_matrix 107 8.3 0.001 0.001 33.166 33.227 qs_ks_build_kohn_sham_matrix 107 9.3 0.016 0.020 33.165 33.227 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.293 29.344 sum_up_and_integrate 107 10.3 0.038 0.040 28.555 28.595 integrate_v_rspace 107 11.3 0.004 0.005 28.517 28.558 qs_rho_update_rho_low 107 7.7 0.001 0.001 27.984 27.996 calculate_rho_elec 107 8.7 0.028 0.029 27.983 27.996 grid_integrate_task_list 107 12.3 23.670 24.063 23.670 24.063 grid_collocate_task_list 107 9.7 23.086 23.466 23.086 23.466 dbcsr_multiply_generic 1966 12.4 0.071 0.075 14.691 14.878 qs_scf_new_mos 96 7.5 0.001 0.001 11.649 11.744 qs_scf_loop_do_ot 96 8.5 0.001 0.001 11.648 11.744 multiply_cannon 1966 13.4 0.129 0.157 10.859 11.350 ot_scf_mini 96 9.5 0.002 0.002 11.003 11.100 multiply_cannon_loop 1966 14.4 0.098 0.108 10.266 10.591 mp_waitall_1 136719 16.5 8.129 8.564 8.129 8.564 ot_mini 96 10.5 0.001 0.001 6.639 6.748 multiply_cannon_metrocomm3 15728 15.4 0.045 0.048 6.239 6.579 density_rs2pw 107 9.7 0.005 0.006 4.454 5.194 init_scf_loop 11 6.9 0.000 0.001 4.992 4.992 pw_transfer 1295 11.6 0.065 0.070 4.328 4.413 fft_wrap_pw1pw2 1081 12.6 0.009 0.010 4.191 4.276 init_scf_run 11 5.9 0.000 0.005 4.220 4.221 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.220 4.221 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.041 4.053 multiply_cannon_multrec 15728 15.4 3.637 3.874 3.648 3.884 wfi_extrapolate 11 7.9 0.001 0.001 3.838 3.839 potential_pw2rs 107 12.3 0.006 0.007 3.793 3.805 fft_wrap_pw1pw2_140 439 13.2 0.683 0.712 3.517 3.636 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.400 3.499 apply_single 107 13.6 0.000 0.001 3.400 3.499 qs_ot_get_derivative 96 11.5 0.001 0.001 3.324 3.421 ot_diis_step 96 11.5 0.003 0.003 3.300 3.300 transfer_rs2pw 439 10.6 0.006 0.007 2.471 3.222 fft3d_ps 1081 14.6 1.362 1.517 2.735 2.858 mp_waitany 8968 13.7 2.075 2.814 2.075 2.814 transfer_pw2rs 439 13.2 0.006 0.007 2.655 2.661 make_m2s 3932 13.4 0.042 0.051 2.585 2.654 make_images 3932 14.4 0.105 0.110 2.276 2.343 transfer_rs2pw_140 118 11.5 0.171 0.184 1.553 2.308 mp_alltoall_d11v 1998 13.7 1.366 2.115 1.366 2.115 rs_gather_matrices 107 12.3 0.067 0.077 1.008 1.737 ------------------------------------------------------------------------------- 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=48.242000000000004, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=28.918, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.39, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.358, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.569, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.455, 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=17.859, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=23.086, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=23.67, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.637, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.129, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.075, 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 0.230 0.230 139.939 139.939 qs_energies 1 2.0 0.000 0.000 139.077 139.077 scf_env_do_scf 1 3.0 0.000 0.000 137.823 137.823 qs_ks_update_qs_env 8 5.0 0.000 0.000 132.251 132.251 rebuild_ks_matrix 7 6.0 0.000 0.000 132.194 132.194 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 132.193 132.193 hfx_ks_matrix 7 8.0 0.000 0.000 122.915 122.915 integrate_four_center 7 9.0 1.865 1.865 122.882 122.882 integrate_four_center_main 7 10.0 0.700 0.700 108.430 108.430 integrate_four_center_bin 452 11.0 107.730 107.730 107.730 107.730 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 78.163 78.163 init_scf_loop 1 4.0 0.000 0.000 59.648 59.648 integrate_four_center_load 7 10.0 0.001 0.001 12.273 12.273 hfx_load_balance 1 11.0 0.002 0.002 12.273 12.273 hfx_load_balance_count 1 12.0 6.171 6.171 6.171 6.171 hfx_load_balance_bin 1 12.0 6.084 6.084 6.084 6.084 qs_vxc_create 14 8.0 0.000 0.000 3.052 3.052 xc_vxc_pw_create 14 9.0 0.117 0.117 3.052 3.052 ------------------------------------------------------------------------------- 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 0.253 0.274 135.333 135.345 qs_energies 1 2.0 0.000 0.000 134.904 134.915 scf_env_do_scf 1 3.0 0.000 0.000 134.539 134.541 qs_ks_update_qs_env 8 5.0 0.000 0.000 132.262 132.263 rebuild_ks_matrix 7 6.0 0.000 0.000 132.254 132.255 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 132.254 132.255 hfx_ks_matrix 7 8.0 0.000 0.000 126.356 126.357 integrate_four_center 7 9.0 0.056 0.345 126.347 126.348 integrate_four_center_main 7 10.0 0.003 0.004 106.029 112.656 integrate_four_center_bin 448 11.0 106.026 112.653 106.026 112.653 scf_env_do_scf_inner_loop 7 4.0 0.000 0.002 78.879 78.880 init_scf_loop 1 4.0 0.000 0.000 55.659 55.659 mp_sync 56 11.2 7.081 13.802 7.081 13.802 integrate_four_center_load 7 10.0 0.000 0.000 12.539 12.540 hfx_load_balance 1 11.0 0.001 0.001 12.539 12.540 hfx_load_balance_count 1 12.0 6.212 6.277 6.212 6.277 hfx_load_balance_bin 1 12.0 6.199 6.275 6.199 6.275 ------------------------------------------------------------------------------- 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=17.158999999999978, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=107.73, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.171, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.084, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.865, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.7, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.23, 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=9.503, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=106.026, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.212, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.199, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.056, 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=0.253, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=7.081, 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 0.017 0.017 80.113 80.113 qs_energies 1 2.0 0.000 0.000 79.729 79.729 mp2_main 1 3.0 0.000 0.000 76.918 76.918 mp2_gpw_main 1 4.0 0.000 0.000 76.793 76.793 rpa_ri_compute_en 1 5.0 0.000 0.000 73.105 73.105 rpa_num_int 1 6.0 0.001 0.001 73.099 73.099 compute_mat_P_omega 1 7.0 0.005 0.005 63.019 63.019 compute_mat_P_omega_contract 10 8.0 8.898 8.898 62.790 62.790 dbt_total 2336 9.6 0.014 0.014 49.143 49.143 dbt_contract 787 11.0 0.042 0.042 41.871 41.871 dbt_tas_total 1149 12.2 0.214 0.214 40.303 40.303 dbt_tas_multiply 807 12.1 0.002 0.002 38.965 38.965 dbt_tas_dbm 807 14.1 0.003 0.003 32.176 32.176 dbm_multiply 807 16.1 32.167 32.167 32.167 32.167 dbt_tas_mm_1N 524 15.1 0.001 0.001 24.702 24.702 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 23.228 23.228 compute_mat_P_omega_calc_M_occ 250 9.0 8.924 8.924 17.912 17.912 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.965 6.965 dbt_tas_mm_2 251 15.0 0.001 0.001 5.951 5.951 dbt_copy 1103 10.7 0.118 0.118 5.915 5.915 compute_QP_energies 1 7.0 0.000 0.000 5.184 5.184 compute_self_energy_cubic_gw 1 8.0 0.052 0.052 5.183 5.183 contract_cubic_gw 21 9.0 0.000 0.000 4.171 4.171 dbt_tas_reserve_blocks_index 3261 14.3 0.491 0.491 3.986 3.986 mp2_ri_gpw_compute_in 1 5.0 0.002 0.002 3.682 3.682 dbm_reserve_blocks 3628 15.3 3.561 3.561 3.561 3.561 dbt_reserve_blocks_index 2280 13.1 0.061 0.061 3.042 3.042 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.987 2.987 dbt_crop 1042 12.0 1.618 1.618 2.789 2.789 scf_env_do_scf 1 3.0 0.000 0.000 2.696 2.696 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.696 2.696 dbt_tas_copy 574 11.4 1.364 1.364 2.367 2.367 convert_to_new_pgrid 2421 14.1 0.093 0.093 2.328 2.328 dbm_copy 1614 15.1 2.235 2.235 2.235 2.235 dbt_tas_reshape 367 15.0 0.066 0.066 2.220 2.220 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.048 2.048 compute_W_cubic_GW 10 7.0 0.004 0.004 2.016 2.016 dbt_reshape 278 11.9 1.073 1.073 1.976 1.976 get_2c_integrals 1 6.0 0.000 0.000 1.727 1.727 reshape_mm_small 367 14.1 0.050 0.050 1.662 1.662 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.605 1.605 ------------------------------------------------------------------------------- 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 0.009 0.029 36.570 36.583 qs_energies 1 2.0 0.000 0.000 36.398 36.418 mp2_main 1 3.0 0.000 0.001 35.296 35.316 mp2_gpw_main 1 4.0 0.000 0.000 35.153 35.174 rpa_ri_compute_en 1 5.0 0.000 0.000 33.658 33.677 rpa_num_int 1 6.0 0.000 0.003 33.657 33.677 dbt_total 2336 9.6 0.015 0.016 29.878 29.884 compute_mat_P_omega 1 7.0 0.001 0.006 28.781 28.833 compute_mat_P_omega_contract 10 8.0 0.431 0.447 28.604 28.607 dbt_contract 787 11.0 0.042 0.043 22.263 22.276 dbt_tas_total 1149 12.2 0.084 0.090 19.789 19.802 dbt_tas_multiply 807 12.1 0.002 0.002 19.694 19.706 dbt_tas_dbm 807 14.1 0.003 0.003 14.191 14.196 dbm_multiply 807 16.1 11.430 12.157 11.430 12.157 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.879 8.882 compute_mat_P_omega_calc_M_occ 250 9.0 0.417 0.428 8.202 8.204 dbt_copy 1149 10.8 0.014 0.015 6.621 6.847 dbt_tas_mm_2 251 15.0 0.001 0.002 6.709 6.712 dbt_reshape 1136 11.8 2.777 2.944 6.299 6.515 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.878 5.878 mp_sync 8688 11.6 4.921 5.811 4.921 5.811 dbt_tas_mm_1N 524 15.1 0.001 0.002 5.135 5.494 compute_QP_energies 1 7.0 0.000 0.000 3.020 3.022 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 3.020 3.020 mp_waitall_2 3812 15.3 2.641 2.877 2.641 2.877 dbt_communicate_buffer 1136 12.8 0.053 0.057 2.620 2.771 contract_cubic_gw 21 9.0 0.000 0.000 2.370 2.371 dbt_reserve_blocks_index 2887 13.1 0.079 0.085 1.884 2.040 dbt_reserve_blocks_index_array 2829 12.2 0.008 0.010 1.874 2.029 dbt_tas_reserve_blocks_index 3347 14.5 0.438 0.472 1.857 2.013 dbt_crop 1042 12.0 0.964 1.054 1.565 1.713 dbm_reserve_blocks 3752 15.4 1.519 1.650 1.519 1.650 mp2_ri_gpw_compute_in 1 5.0 0.003 0.004 1.450 1.457 dbt_tas_replicate 405 14.1 0.554 0.723 1.170 1.229 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.166 1.173 parallel_gemm_fm 105 8.4 0.000 0.000 1.120 1.128 parallel_gemm_fm_cosma 105 9.4 1.119 1.128 1.119 1.128 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.095 1.098 scf_env_do_scf 1 3.0 0.000 0.000 1.051 1.052 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 1.051 1.051 convert_to_new_pgrid 2421 14.1 0.027 0.031 0.859 0.954 dbm_copy 1608 15.1 0.826 0.922 0.826 0.922 mp_sum_l 6165 12.9 0.825 0.869 0.825 0.869 mp_max_i 2004 9.8 0.666 0.854 0.666 0.854 compute_W_cubic_GW 10 7.0 0.001 0.001 0.839 0.846 ------------------------------------------------------------------------------- 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=23.254999999999995, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=32.167, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_calc_M_occ", label="compute_mat_P_omega_calc_M_occ", y=8.924, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.898, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.561, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.235, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.073, 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=11.608000000000004, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=11.43, 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=0.417, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.431, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.519, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.826, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.777, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.641, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.921, 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 0.022 0.022 242.917 242.917 qs_forces 1 2.0 0.000 0.000 242.373 242.373 rebuild_ks_matrix 7 6.6 0.000 0.000 240.906 240.906 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 240.906 240.906 hfx_ks_matrix 7 8.6 0.000 0.000 238.943 238.943 hfx_ri_update_ks 7 9.6 0.000 0.000 199.011 199.011 hfx_ri_update_ks_Pmat 7 10.6 31.781 31.781 199.008 199.008 dbt_total 809 11.0 0.006 0.006 183.762 183.762 qs_energies 1 3.0 0.000 0.000 176.585 176.585 scf_env_do_scf 1 4.0 0.001 0.001 176.287 176.287 qs_ks_update_qs_env 8 6.0 0.000 0.000 175.171 175.171 dbt_contract 207 12.4 0.030 0.030 164.541 164.541 dbt_tas_total 343 13.7 1.368 1.368 162.740 162.740 dbt_tas_multiply 216 13.5 0.001 0.001 159.298 159.298 dbt_tas_dbm 216 15.5 0.001 0.001 147.716 147.716 dbm_multiply 216 17.5 147.713 147.713 147.713 147.713 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 142.050 142.050 dbt_tas_mm_2 91 16.5 0.001 0.001 133.341 133.341 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 110.613 110.613 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 65.739 65.739 init_scf_loop 2 5.0 0.000 0.000 65.672 65.672 hfx_ri_update_forces 1 7.0 1.570 1.570 39.928 39.928 hfx_ri_forces_Pmat_3c 1 8.0 4.627 4.627 22.557 22.557 dbt_copy 409 11.7 0.035 0.035 15.770 15.770 precalc_derivatives 1 8.0 2.219 2.219 13.595 13.595 dbt_reshape 132 13.2 6.712 6.712 10.877 10.877 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 10.036 10.036 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.822 9.822 dbt_tas_reserve_blocks_index 1255 15.4 1.078 1.078 8.151 8.151 build_3c_derivatives 3 9.0 2.553 2.553 7.622 7.622 dbm_reserve_blocks 1397 16.3 7.295 7.295 7.295 7.295 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.974 6.974 dbt_reserve_blocks_index 818 14.4 0.106 0.106 6.347 6.347 dbt_reserve_blocks_index_array 795 13.4 0.008 0.008 6.241 6.241 dbt_crop 372 13.7 2.888 2.888 4.956 4.956 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-HFX_H2O-32_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.029 51.992 52.005 qs_forces 1 2.0 0.000 0.000 51.786 51.786 rebuild_ks_matrix 7 6.6 0.000 0.000 50.948 50.948 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 50.947 50.948 hfx_ks_matrix 7 8.6 0.000 0.000 49.816 49.822 dbt_total 809 11.0 0.006 0.007 44.574 44.581 dbt_contract 207 12.4 0.026 0.028 34.785 34.803 dbt_tas_total 343 13.7 0.071 0.189 30.538 30.551 dbt_tas_multiply 216 13.5 0.001 0.001 30.284 30.297 hfx_ri_update_ks 7 9.6 0.000 0.000 29.846 29.847 hfx_ri_update_ks_Pmat 7 10.6 1.296 1.353 29.842 29.842 qs_energies 1 3.0 0.000 0.000 28.076 28.076 scf_env_do_scf 1 4.0 0.000 0.001 27.917 27.917 qs_ks_update_qs_env 8 6.0 0.000 0.000 27.248 27.249 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 23.700 23.700 dbt_tas_dbm 216 15.5 0.001 0.001 23.437 23.446 dbm_multiply 216 17.5 21.329 21.932 21.329 21.932 hfx_ri_update_forces 1 7.0 0.059 0.063 19.969 19.975 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 15.967 15.967 hfx_ri_forces_Pmat_3c 1 8.0 0.162 0.169 15.022 15.022 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 14.001 14.001 init_scf_loop 2 5.0 0.000 0.000 11.949 11.949 dbt_tas_mm_2 91 16.5 0.001 0.001 11.131 11.140 dbt_copy 497 12.3 0.012 0.015 8.985 9.197 dbt_reshape 365 13.6 3.735 3.833 6.995 7.169 dbt_tas_mm_3T 77 17.1 0.000 0.000 6.125 6.562 mp_sync 2769 12.9 4.860 6.015 4.860 6.015 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.507 5.507 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.504 4.648 precalc_derivatives 1 8.0 0.089 0.093 3.697 3.697 dbt_tas_reserve_blocks_index 1380 15.8 0.895 0.916 3.250 3.589 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.411 3.411 mp_waitall_2 1234 16.4 2.960 3.059 2.960 3.059 dbt_reserve_blocks_index 1051 14.7 0.122 0.126 2.710 2.944 dbt_reserve_blocks_index_array 1028 13.8 0.006 0.006 2.685 2.916 dbm_reserve_blocks 1529 16.7 2.566 2.862 2.566 2.862 dbt_crop 372 13.7 1.840 1.884 2.663 2.767 dbt_communicate_buffer 365 14.6 0.013 0.017 2.109 2.204 build_3c_derivatives 3 9.0 0.227 0.246 2.082 2.088 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.810 1.812 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.767 1.771 dbt_tas_replicate 149 15.4 0.665 0.683 1.701 1.750 convert_to_new_pgrid 648 15.5 0.037 0.081 1.434 1.660 dbm_copy 452 16.3 1.252 1.479 1.252 1.479 dbt_tas_copy 132 12.5 0.658 0.687 1.265 1.381 mp_sum_l 6385 13.7 1.001 1.088 1.001 1.088 ------------------------------------------------------------------------------- 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=44.789000000000016, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=147.713, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.781, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.295, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.712, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.627, 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=15.084000000000003, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=21.329, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.296, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.566, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.735, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.162, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.96, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.86, 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 0.018 0.018 200.493 200.493 qs_energies 1 2.0 0.000 0.000 200.310 200.310 mp2_main 1 3.0 0.000 0.000 195.427 195.427 mp2_gpw_main 1 4.0 0.001 0.001 195.014 195.014 mp2_ri_gpw_compute_in 1 5.0 0.393 0.393 142.354 142.354 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 133.580 133.580 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 105.641 105.641 integrate_v_rspace 2666 8.0 0.604 0.604 92.949 92.949 grid_integrate_task_list 2666 9.0 90.409 90.409 90.409 90.409 mp2_ri_gpw_compute_en 1 5.0 0.086 0.086 52.635 52.635 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.331 9.331 50.727 50.727 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.041 2.041 33.997 33.997 local_gemm 2080 8.0 31.956 31.956 31.956 31.956 dbcsr_multiply_generic 5322 8.0 0.182 0.182 21.242 21.242 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 21.088 21.088 pw_transfer 63872 10.6 0.978 0.978 11.623 11.623 calculate_wavefunction 2656 8.0 7.872 7.872 11.364 11.364 multiply_cannon 5322 9.0 0.454 0.454 10.732 10.732 fft_wrap_pw1pw2 53228 11.4 0.108 0.108 10.399 10.399 multiply_cannon_loop 5322 10.0 0.176 0.176 9.372 9.372 get_2c_integrals 1 6.0 0.000 0.000 8.381 8.381 make_m2s 10644 9.0 0.060 0.060 8.058 8.058 multiply_cannon_multrec 5322 11.0 7.823 7.823 7.863 7.863 make_images 10644 10.0 3.236 3.236 7.726 7.726 compute_2c_integrals 1 7.0 0.005 0.005 7.550 7.550 compute_2c_integrals_loop_lm 1 8.0 0.012 0.012 7.537 7.537 mp2_eri_2c_integrate_gpw 1 9.0 0.808 0.808 7.525 7.525 fft_wrap_pw1pw2_20 21271 12.4 0.476 0.476 7.310 7.310 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.373 2.373 6.737 6.737 fft3d_s 53229 13.4 6.341 6.341 6.380 6.380 mp2_ri_gpw_compute_en_ener 2080 7.0 5.609 5.609 5.609 5.609 copy_dbcsr_to_fm 2679 8.0 0.029 0.029 4.861 4.861 scf_env_do_scf 1 3.0 0.000 0.000 4.464 4.464 scf_env_do_scf_inner_loop 10 4.0 0.002 0.002 4.464 4.464 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.038 40.191 40.211 qs_energies 1 2.0 0.000 0.000 39.778 39.779 mp2_main 1 3.0 0.000 0.001 37.673 37.674 mp2_gpw_main 1 4.0 0.001 0.002 37.570 37.570 mp2_ri_gpw_compute_en 1 5.0 0.242 0.251 19.649 19.895 mp2_ri_gpw_compute_en_RI_loop 1 6.0 3.351 3.759 18.439 18.456 mp2_ri_gpw_compute_in 1 5.0 0.043 0.045 17.831 18.211 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 16.499 16.881 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 14.372 14.701 integrate_v_rspace 93 8.1 0.103 0.111 14.265 14.594 grid_integrate_task_list 93 9.1 13.943 14.276 13.943 14.276 mp2_ri_gpw_compute_en_expansio 65 7.0 0.138 0.161 11.036 11.221 local_gemm 65 8.0 10.898 11.063 10.898 11.063 mp2_ri_gpw_compute_en_comm 30 7.0 0.115 0.155 3.661 4.311 mp_sendrecv_dm3 1860 8.0 2.889 3.685 2.889 3.685 dbcsr_multiply_generic 176 8.0 0.008 0.009 1.799 1.968 scf_env_do_scf 1 3.0 0.000 0.000 1.961 1.962 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.961 1.962 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.782 1.948 get_2c_integrals 1 6.0 0.004 0.011 1.269 1.291 multiply_cannon 176 9.0 0.017 0.018 1.078 1.148 multiply_cannon_loop 176 10.0 0.002 0.002 1.017 1.085 qs_scf_new_mos 10 5.0 0.000 0.000 0.932 0.940 compute_2c_integrals 1 7.0 0.003 0.004 0.911 0.927 multiply_cannon_multrec 246 11.0 0.885 0.917 0.890 0.922 eigensolver 11 5.8 0.001 0.001 0.867 0.868 fill_local_i_aL 1920 8.0 0.702 0.860 0.702 0.860 compute_2c_integrals_loop_lm 1 8.0 0.002 0.003 0.809 0.835 mp2_eri_2c_integrate_gpw 1 9.0 0.208 0.217 0.808 0.834 ------------------------------------------------------------------------------- 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=53.102000000000004, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=90.409, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=31.956, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=9.331, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=7.872, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.823, 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=8.225000000000001, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.943, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.898, 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=3.351, 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=0.885, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=2.889, 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 0.095 0.095 125.635 125.635 qs_energies 1 2.0 0.000 0.000 124.289 124.289 scf_env_do_scf 1 3.0 0.000 0.000 116.004 116.004 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 116.004 116.004 qs_ks_update_qs_env 15 5.0 0.000 0.000 49.001 49.001 rebuild_ks_matrix 15 6.0 0.000 0.000 48.794 48.794 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.794 48.794 qs_scf_new_mos 15 5.0 0.000 0.000 43.148 43.148 eigensolver 15 6.0 0.002 0.002 35.323 35.323 qs_vxc_create 15 8.0 0.050 0.050 33.045 33.045 calculate_dispersion_nonloc 15 9.0 6.678 6.678 29.149 29.149 pw_transfer 1191 10.0 0.064 0.064 22.583 22.583 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.485 22.485 cp_fm_diag_elpa_base 15 8.0 19.929 19.929 22.485 22.485 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 22.383 22.383 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.660 20.660 calculate_rho_elec 16 6.0 0.216 0.216 20.660 20.660 grid_collocate_task_list 16 7.0 19.360 19.360 19.360 19.360 fft_wrap_pw1pw2_150 765 12.0 3.498 3.498 16.748 16.748 sum_up_and_integrate 15 8.0 0.132 0.132 14.776 14.776 integrate_v_rspace 15 9.0 0.019 0.019 14.644 14.644 grid_integrate_task_list 15 10.0 14.007 14.007 14.007 14.007 fft3d_s 1087 13.0 10.867 10.867 10.874 10.874 cp_fm_cholesky_restore 45 7.0 10.558 10.558 10.558 10.558 pw_scatter_s 585 13.1 6.549 6.549 6.549 6.549 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.621 5.621 dbcsr_complete_redistribute 46 8.3 2.260 2.260 5.546 5.546 fft_wrap_pw1pw2_200 197 12.3 0.484 0.484 5.412 5.412 cp_fm_upper_to_full 30 8.0 4.833 4.833 4.833 4.833 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.639 4.639 gspace_mixing 14 5.0 0.171 0.171 4.355 4.355 vdW_energy 15 10.0 4.329 4.329 4.329 4.329 xc_vxc_pw_create 15 9.0 0.217 0.217 3.846 3.846 broyden_mixing 14 6.0 3.775 3.775 3.775 3.775 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 3.463 3.463 init_scf_run 1 3.0 0.000 0.000 3.165 3.165 calculate_dm_sparse 15 6.0 0.022 0.022 2.558 2.558 ------------------------------------------------------------------------------- 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 0.032 60.515 60.528 qs_energies 1 2.0 0.000 0.000 60.091 60.099 scf_env_do_scf 1 3.0 0.000 0.001 55.949 55.949 scf_env_do_scf_inner_loop 15 4.0 0.001 0.005 55.949 55.949 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.695 24.702 rebuild_ks_matrix 15 6.0 0.000 0.000 24.665 24.672 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 24.665 24.672 qs_rho_update_rho_low 16 5.0 0.000 0.000 18.855 18.859 calculate_rho_elec 16 6.0 0.007 0.008 18.855 18.858 grid_collocate_task_list 16 7.0 17.562 17.905 17.562 17.905 sum_up_and_integrate 15 8.0 0.016 0.021 13.866 13.915 integrate_v_rspace 15 9.0 0.001 0.001 13.850 13.904 grid_integrate_task_list 15 10.0 13.087 13.170 13.087 13.170 qs_scf_new_mos 15 5.0 0.000 0.000 12.842 12.899 eigensolver 15 6.0 0.001 0.002 11.812 11.834 qs_vxc_create 15 8.0 0.001 0.002 10.468 10.477 calculate_dispersion_nonloc 15 9.0 0.914 0.930 8.444 8.463 pw_transfer 1191 10.0 0.093 0.108 8.325 8.360 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.251 8.257 cp_fm_diag_elpa_base 15 8.0 8.109 8.123 8.249 8.252 fft_wrap_pw1pw2 1086 11.0 0.014 0.015 8.151 8.195 fft3d_ps 1086 13.0 2.924 3.089 5.468 5.694 fft_wrap_pw1pw2_150 765 12.0 0.704 0.760 5.369 5.392 cp_fm_cholesky_restore 45 7.0 3.407 3.458 3.407 3.458 fft_wrap_pw1pw2_200 197 12.3 0.439 0.494 2.679 2.716 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.663 2.663 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.347 2.568 mp_alltoall_z22v 1086 15.0 1.987 2.440 1.987 2.440 xc_vxc_pw_create 15 9.0 0.015 0.019 2.024 2.060 build_core_ppnl 1 5.0 1.451 1.570 1.451 1.570 x_to_yz 585 14.1 0.323 0.344 1.388 1.533 xc_pw_derive 90 11.0 0.001 0.002 1.379 1.468 yz_to_x 501 13.9 0.203 0.253 1.125 1.406 vdW_energy 15 10.0 1.295 1.364 1.295 1.364 density_rs2pw 16 7.0 0.001 0.001 1.149 1.280 init_scf_run 1 3.0 0.000 0.000 1.248 1.249 ------------------------------------------------------------------------------- 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=50.914, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.929, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.36, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.007, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.867, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.558, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=15.426000000000009, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.109, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=17.562, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.087, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.407, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.924, 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 0.093 0.093 297.498 297.498 qs_energies 1 2.0 0.000 0.000 297.344 297.344 ls_scf 1 3.0 0.000 0.000 296.057 296.057 ls_scf_main 1 4.0 0.002 0.002 286.909 286.909 density_matrix_trs4 11 5.0 0.014 0.014 186.108 186.108 ls_scf_dm_to_ks 11 5.0 0.000 0.000 94.389 94.389 matrix_ls_to_qs 11 6.0 0.000 0.000 90.705 90.705 arnoldi_extremal 12 6.1 0.000 0.000 89.758 89.758 arnoldi_normal_ev 12 7.1 0.051 0.051 89.757 89.757 dbcsr_matrix_vector_mult 652 9.0 0.264 0.264 88.281 88.281 build_subspace 23 8.1 0.086 0.086 88.141 88.141 dbcsr_matrix_vector_mult_local 652 10.0 86.755 86.755 86.765 86.765 dbcsr_multiply_generic 185 6.1 0.916 0.916 80.565 80.565 dbcsr_complete_redistribute 23 7.5 34.663 34.663 48.357 48.357 dbcsr_copy_into_existing 11 7.0 46.848 46.848 46.848 46.848 multiply_cannon 185 7.1 0.523 0.523 46.586 46.586 matrix_decluster 11 7.0 0.000 0.000 43.850 43.850 multiply_cannon_loop 185 8.1 0.219 0.219 33.263 33.263 make_m2s 370 7.1 0.039 0.039 28.981 28.981 make_images 370 8.1 12.770 12.770 26.573 26.573 multiply_cannon_multrec 185 9.1 24.173 24.173 24.217 24.217 dbcsr_finalize 646 7.5 0.351 0.351 18.035 18.035 dbcsr_merge_all 597 8.5 2.666 2.666 16.619 16.619 setup_rec_index_2d 370 8.1 12.472 12.472 12.472 12.472 tree_to_linear_d 110 9.4 12.358 12.358 12.358 12.358 dbcsr_sort_indices 1103 9.9 11.425 11.425 11.425 11.425 quick_finalize 395 10.0 0.414 0.414 9.856 9.856 dbcsr_special_finalize 370 9.1 0.002 0.002 9.078 9.078 calculate_norms 370 9.1 8.826 8.826 8.826 8.826 ls_scf_init_scf 1 4.0 0.000 0.000 8.414 8.414 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.081 8.081 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.428 7.428 dbcsr_dot_sd 144 6.3 6.943 6.943 6.944 6.944 matrix_qs_to_ls 12 5.1 0.000 0.000 6.561 6.561 matrix_cluster 12 6.1 0.000 0.000 6.561 6.561 ------------------------------------------------------------------------------- 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 0.015 0.032 72.963 72.975 qs_energies 1 2.0 0.000 0.000 72.641 72.642 ls_scf 1 3.0 0.000 0.000 72.588 72.589 ls_scf_main 1 4.0 0.001 0.012 69.781 69.786 density_matrix_trs4 11 5.0 0.007 0.021 67.140 67.210 dbcsr_multiply_generic 185 6.1 0.061 0.070 63.789 64.105 multiply_cannon 185 7.1 0.037 0.039 52.648 53.578 multiply_cannon_loop 185 8.1 0.126 0.138 50.015 50.908 multiply_cannon_multrec 1480 9.1 30.444 32.401 30.713 32.680 mp_waitall_1 11936 10.3 16.880 19.154 16.880 19.154 multiply_cannon_metrocomm3 1480 9.1 0.017 0.020 12.863 15.523 make_m2s 370 7.1 0.036 0.038 7.294 7.359 make_images 370 8.1 0.660 0.765 7.159 7.226 calculate_norms 2960 9.1 5.239 5.708 5.239 5.708 mp_sum_l 1199 5.3 2.964 4.207 2.964 4.207 make_images_data 370 9.1 0.011 0.013 3.288 3.546 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 2.088 3.084 hybrid_alltoall_any 393 9.9 0.245 1.334 2.896 3.079 arnoldi_extremal 12 6.1 0.000 0.001 2.616 2.625 arnoldi_normal_ev 12 7.1 0.002 0.008 2.616 2.625 build_subspace 23 8.1 0.023 0.028 2.515 2.517 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.277 2.336 dbcsr_matrix_vector_mult 652 9.0 0.014 0.052 2.120 2.210 dbcsr_complete_redistribute 23 7.5 1.246 1.330 2.064 2.125 ls_scf_init_scf 1 4.0 0.000 0.000 2.102 2.102 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.072 2.078 matrix_ls_to_qs 11 6.0 0.000 0.000 1.982 2.058 make_images_pack 370 9.1 1.743 2.045 1.747 2.049 matrix_decluster 11 7.0 0.000 0.000 1.857 1.916 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.002 1.888 1.889 multiply_cannon_metrocomm1 1480 9.1 0.007 0.008 1.031 1.873 dbcsr_matrix_vector_mult_local 652 10.0 1.731 1.854 1.733 1.856 buffer_matrices_ensure_size 370 8.1 1.509 1.645 1.509 1.645 ------------------------------------------------------------------------------- Plot: name="bench_dftb_timings_32omp", title="Timings of bench_dftb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32omp", name="rest", label="rest", y=83.46299999999997, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=86.755, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=46.848, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=34.663, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=24.173, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images", label="make_images", y=12.77, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.826, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=12.055999999999997, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.731, 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=1.246, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=30.444, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images", label="make_images", y=0.66, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.239, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.964, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.743, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=16.88, 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 0.010 0.010 75.537 75.537 lib_test 1 2.0 0.000 0.000 75.526 75.526 dbcsr_run_tests 3 3.0 0.003 0.003 75.526 75.526 test_multiplies_multiproc 3 4.0 0.001 0.001 59.176 59.176 dbcsr_redistribute 9 5.0 35.915 35.915 37.557 37.557 dbcsr_multiply_generic 9 5.0 0.002 0.002 20.011 20.011 dbcsr_make_random_matrix 9 4.0 13.158 13.158 16.239 16.239 multiply_cannon 9 6.0 0.002 0.002 14.084 14.084 multiply_cannon_loop 9 7.0 0.038 0.038 13.686 13.686 multiply_cannon_multrec 9 8.0 13.647 13.647 13.648 13.648 dbcsr_finalize 27 5.7 0.045 0.045 6.059 6.059 dbcsr_merge_all 18 6.5 2.330 2.330 5.221 5.221 dbcsr_data_release 975 7.6 3.155 3.155 3.155 3.155 make_m2s 18 6.0 0.001 0.001 2.184 2.184 make_images 18 7.0 0.808 0.808 2.031 2.031 tree_to_linear_d 9 7.0 1.974 1.974 1.974 1.974 dbcsr_destroy 93 5.8 0.000 0.000 1.583 1.583 ------------------------------------------------------------------------------- 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 0.005 0.017 21.059 21.066 lib_test 1 2.0 0.000 0.000 21.024 21.041 dbcsr_run_tests 3 3.0 0.000 0.001 21.022 21.040 test_multiplies_multiproc 3 4.0 0.000 0.003 20.100 20.160 dbcsr_multiply_generic 9 5.0 0.001 0.001 18.512 18.620 multiply_cannon 9 6.0 0.002 0.002 16.324 16.570 multiply_cannon_loop 9 7.0 0.002 0.003 16.005 16.288 multiply_cannon_multrec 72 8.0 12.121 12.402 12.122 12.403 mp_waitall_1 576 9.2 4.275 4.814 4.275 4.814 multiply_cannon_metrocomm1 72 8.0 0.001 0.002 3.726 4.267 mp_sum_l 470 2.5 0.791 1.184 0.791 1.184 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.731 1.134 dbcsr_make_random_matrix 9 4.0 0.715 0.729 0.885 0.917 make_m2s 18 6.0 0.001 0.001 0.838 0.874 make_images 18 7.0 0.022 0.026 0.834 0.871 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.152 0.809 dbcsr_finalize 27 5.7 0.000 0.000 0.600 0.709 dbcsr_data_release 444 7.6 0.603 0.695 0.603 0.695 dbcsr_redistribute 9 5.0 0.266 0.304 0.639 0.666 dbcsr_destroy 111 5.9 0.004 0.057 0.531 0.629 dbcsr_merge_all 18 6.5 0.092 0.113 0.523 0.619 make_images_data 18 8.0 0.001 0.001 0.446 0.515 hybrid_alltoall_any 18 9.0 0.045 0.201 0.389 0.461 ------------------------------------------------------------------------------- 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=7.332000000000008, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.915, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=13.647, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.158, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=3.155, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.33, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=2.195999999999998, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.266, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=12.121, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.715, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.603, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.092, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=4.275, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.791, 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 0.059 0.059 133.052 133.052 qs_mol_dyn_low 1 2.0 0.004 0.004 131.660 131.660 velocity_verlet 5 3.0 0.003 0.003 107.286 107.286 qmmm_el_coupling 6 3.8 0.000 0.000 87.721 87.721 qmmm_elec_with_gaussian 6 4.8 0.014 0.014 87.717 87.717 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.077 87.077 qmmm_elec_gaussian_low_G 6 6.8 86.198 86.198 86.198 86.198 qs_forces 6 3.8 0.001 0.001 35.363 35.363 qs_energies 6 4.8 0.000 0.000 31.390 31.390 scf_env_do_scf 6 5.8 0.001 0.001 29.019 29.019 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 25.314 25.314 rebuild_ks_matrix 45 8.4 0.000 0.000 24.404 24.404 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.403 24.403 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.862 20.862 pw_transfer 966 12.3 0.052 0.052 17.575 17.575 fft_wrap_pw1pw2 801 13.6 0.006 0.006 17.380 17.380 fft_wrap_pw1pw2_150 507 15.2 2.384 2.384 16.972 16.972 qs_vxc_create 45 10.4 0.001 0.001 13.456 13.456 xc_vxc_pw_create 45 11.4 0.637 0.637 13.455 13.455 xc_pw_derive 270 13.4 0.002 0.002 9.537 9.537 fft3d_s 802 15.6 8.313 8.313 8.321 8.321 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.356 7.356 calculate_rho_elec 45 8.9 0.563 0.563 7.356 7.356 xc_rho_set_and_dset_create 45 12.4 0.603 0.603 6.959 6.959 xc_pw_divergence 45 12.4 0.001 0.001 5.804 5.804 pw_scatter_s 429 15.8 5.618 5.618 5.618 5.618 qmmm_forces 6 3.8 0.001 0.001 5.502 5.502 qmmm_forces_with_gaussian 6 4.8 0.018 0.018 5.155 5.155 pw_integral_ab 2539 7.4 4.465 4.465 4.465 4.465 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.419 4.419 qs_ks_ddapc 45 10.4 0.001 0.001 4.303 4.303 init_scf_loop 6 6.8 0.000 0.000 3.700 3.700 qmmm_forces_gaussian_low_G 6 6.8 3.681 3.681 3.681 3.681 sum_up_and_integrate 45 10.4 0.482 0.482 3.555 3.555 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.549 3.549 grid_collocate_task_list 45 9.9 3.419 3.419 3.419 3.419 density_rs2pw 45 9.9 0.002 0.002 3.374 3.374 integrate_v_rspace 45 11.4 0.006 0.006 3.072 3.072 ------------------------------------------------------------------------------- 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 0.033 0.051 65.668 65.681 qs_mol_dyn_low 1 2.0 0.003 0.005 64.461 64.525 qs_forces 6 3.8 0.001 0.001 46.541 46.541 qs_energies 6 4.8 0.000 0.000 44.470 44.471 scf_env_do_scf 6 5.8 0.000 0.001 43.419 43.420 scf_env_do_scf_inner_loop 113 6.2 0.003 0.022 41.566 41.568 rebuild_ks_matrix 119 8.1 0.000 0.000 31.615 31.626 qs_ks_build_kohn_sham_matrix 119 9.1 0.013 0.014 31.615 31.626 qs_ks_update_qs_env 119 7.3 0.001 0.001 29.835 29.844 velocity_verlet 5 3.0 0.002 0.003 27.628 27.632 pw_transfer 2446 12.3 0.113 0.122 22.361 23.043 fft_wrap_pw1pw2 2059 13.4 0.015 0.017 22.010 22.691 fft_wrap_pw1pw2_150 1321 14.9 3.743 3.888 21.369 22.038 qs_vxc_create 119 10.1 0.002 0.002 18.303 18.313 xc_vxc_pw_create 119 11.1 0.311 0.370 18.301 18.311 fft3d_ps 2059 15.4 7.183 7.512 12.940 13.792 xc_pw_derive 714 13.1 0.005 0.005 13.074 13.639 qs_rho_update_rho_low 119 7.3 0.001 0.001 11.571 11.574 calculate_rho_elec 119 8.3 0.049 0.057 11.571 11.573 xc_rho_set_and_dset_create 119 12.1 0.636 0.762 9.011 9.425 sum_up_and_integrate 119 10.1 0.137 0.150 9.359 9.392 xc_pw_divergence 119 12.1 0.003 0.003 8.718 9.250 integrate_v_rspace 119 11.1 0.003 0.003 9.222 9.247 qmmm_forces 6 3.8 0.003 0.003 9.168 9.168 qmmm_forces_with_gaussian 6 4.8 0.008 0.009 8.747 8.969 qmmm_el_coupling 6 3.8 0.000 0.000 7.735 7.885 qmmm_elec_with_gaussian 6 4.8 0.004 0.005 7.733 7.883 density_rs2pw 119 9.3 0.004 0.005 7.029 7.344 potential_pw2rs 119 12.1 0.005 0.006 5.480 5.496 mp_alltoall_z22v 2059 17.4 4.167 5.097 4.167 5.097 grid_collocate_task_list 119 9.3 4.362 4.613 4.362 4.613 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.066 4.125 pw_restrict_s3 18 5.8 2.175 2.262 3.892 4.101 grid_integrate_task_list 119 12.1 3.425 3.672 3.425 3.672 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 3.361 3.510 pw_prolongate_s3 18 6.8 1.881 1.964 3.361 3.510 yz_to_x 964 16.0 0.703 0.848 2.791 3.483 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.380 3.427 qmmm_forces_gaussian_low_G 6 6.8 3.354 3.407 3.354 3.407 transfer_pw2rs 500 12.8 0.004 0.004 3.322 3.331 x_to_yz 1095 16.8 0.841 0.910 2.921 3.193 transfer_rs2pw 488 10.2 0.005 0.006 2.831 3.100 pw_scatter_p 1095 15.8 2.918 2.980 2.918 2.980 qmmm_elec_gaussian_low_G 6 6.8 2.783 2.832 2.783 2.832 qs_ks_ddapc 119 10.1 0.001 0.002 2.524 2.562 mp_waitany 4028 12.8 2.102 2.546 2.102 2.546 pw_gather_p 964 15.0 2.328 2.421 2.328 2.421 transfer_pw2rs_150 125 13.9 0.959 1.027 2.334 2.353 qs_scf_new_mos 113 7.2 0.000 0.001 2.323 2.329 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.322 2.329 ot_scf_mini 113 9.2 0.001 0.001 2.239 2.245 pw_integral_ab 2761 7.7 1.906 2.005 2.133 2.238 transfer_rs2pw_150 125 11.2 0.863 0.927 1.942 2.209 dbcsr_multiply_generic 2588 12.3 0.062 0.064 1.889 1.944 xc_functional_eval 238 13.1 0.002 0.002 1.558 1.888 init_scf_loop 6 6.8 0.000 0.000 1.849 1.849 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.795 1.795 mp_sum_dm3 33 5.7 1.687 1.717 1.687 1.717 ------------------------------------------------------------------------------- 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=18.974000000000004, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.198, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.313, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.618, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.465, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.681, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.419, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=2.384, 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 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=34.745000000000005, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.783, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_scatter_s", label="pw_scatter_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=1.906, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.354, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.362, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=3.743, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.167, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.183, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.425, yerr=0.0 Summary: Performance test took 35 minutes. Status: OK Removing intermediate container 7cc304de1722 ---> 9f3e86dc9339 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in a731e0fbaa25 Removing intermediate container a731e0fbaa25 ---> 39b94cf54770 Step 42/42 : ENTRYPOINT [] ---> Running in b90928644e67 Removing intermediate container b90928644e67 ---> 1711bed86ae2 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 1711bed86ae2 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: 2023-08-22 20:08:31+00:00