StartDate: 2023-06-19 19:04:30+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa CommitTime: 2023-06-19 17:14:50 +0200 CommitAuthor: Frederick Stein CommitSubject: Bump to Libxc 6.2.2 (#2830) #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa Build-Cache: Yes Populating docker build cache... done. DEPRECATED: The legacy builder is deprecated and will be removed in a future release. BuildKit is currently disabled; enable it by removing the DOCKER_BUILDKIT=0 environment-variable. Sending build context to Docker daemon 371MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 6b851dcae6ca: Pulling fs layer 6b851dcae6ca: Verifying Checksum 6b851dcae6ca: Download complete 6b851dcae6ca: Pull complete Digest: sha256:6120be6a2b7ce665d0cbddc3ce6eae60fe94637c6a66985312d1f02f63cc0bcd Status: Downloaded newer image for ubuntu:22.04 ---> 99284ca6cea0 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> a4b0c172f62f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 6bb3b047e99c Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 73d80ef9e4a3 Step 5/42 : RUN mkdir scripts ---> Using cache ---> b7df9fba15d6 Step 6/42 : COPY ./tools/toolchain/scripts/VERSION ./tools/toolchain/scripts/parse_if.py ./tools/toolchain/scripts/tool_kit.sh ./tools/toolchain/scripts/common_vars.sh ./tools/toolchain/scripts/signal_trap.sh ./tools/toolchain/scripts/get_openblas_arch.sh ./scripts/ ---> Using cache ---> 5c15e99590c4 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> d49e3391ce09 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> fda0d3a90bfc Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 11c1a44a6047 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> c0966e1e9481 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 2ca131548388 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> e81a3481b9f8 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> e4cc5157ace6 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> fce6a9f1c0f0 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 20082ea74ce0 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 1ed0f8ec5ae4 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 0d45c2699d8d Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 786587ed7b92 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> b117d04fe9c9 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 2089654a5431 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> a2413d2964a0 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> f37288abb7ef Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> bad1ddb6076e Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 1281072d1860 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> dd1a8cf997d1 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 651a0762955e Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 8754272b0a19 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> adb5af6166e4 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> e41b12ebf40c Step 30/42 : COPY ./Makefile . ---> Using cache ---> f6260b8939fb Step 31/42 : COPY ./src ./src ---> Using cache ---> a37bb04e5e35 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> aad2cf4059eb Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 6a65d62bf3a1 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 743cd92558af './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 743cd92558af ---> 8853fb777f4c Step 35/42 : COPY ./data ./data ---> 33c215001910 Step 36/42 : COPY ./tests ./tests ---> be598ffad707 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 272e54bf6e01 Step 38/42 : COPY ./benchmarks ./benchmarks ---> fb44acb550fd Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 13b7167ccba7 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 889d7f648b36 ========== 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 0.037 0.037 89.029 89.029 qs_mol_dyn_low 1 2.0 0.003 0.003 88.378 88.378 qs_forces 11 3.9 0.001 0.001 88.336 88.336 qs_energies 11 4.9 0.001 0.001 82.142 82.142 scf_env_do_scf 11 5.9 0.001 0.001 70.999 70.999 velocity_verlet 10 3.0 0.002 0.002 57.881 57.881 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 54.362 54.362 rebuild_ks_matrix 119 8.3 0.001 0.001 20.937 20.937 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.937 20.937 dbcsr_multiply_generic 2286 12.5 0.160 0.160 19.871 19.871 qs_scf_new_mos 108 7.5 0.001 0.001 19.653 19.653 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.652 19.652 qs_ks_update_qs_env 119 7.6 0.001 0.001 19.293 19.293 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.227 19.227 calculate_rho_elec 119 8.7 0.955 0.955 19.226 19.226 ot_scf_mini 108 9.5 0.002 0.002 18.292 18.292 init_scf_loop 11 6.9 0.000 0.000 16.437 16.437 grid_collocate_task_list 119 9.7 15.077 15.077 15.077 15.077 prepare_preconditioner 11 7.9 0.000 0.000 13.960 13.960 make_preconditioner 11 8.9 0.000 0.000 13.960 13.960 sum_up_and_integrate 119 10.3 0.793 0.793 13.746 13.746 integrate_v_rspace 119 11.3 0.092 0.092 12.953 12.953 make_full_inverse_cholesky 11 9.9 0.024 0.024 12.805 12.805 ot_mini 108 10.5 0.001 0.001 11.826 11.826 make_m2s 4572 13.5 0.046 0.046 10.836 10.836 grid_integrate_task_list 119 12.3 10.730 10.730 10.730 10.730 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.567 6.567 qs_ot_get_derivative 108 11.5 0.001 0.001 6.296 6.296 pw_transfer 1439 11.6 0.066 0.066 5.920 5.920 dbcsr_make_dense_low 5837 15.5 0.069 0.069 5.836 5.836 make_dense_data 5837 16.5 5.219 5.219 5.752 5.752 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.706 5.706 ot_diis_step 108 11.5 0.004 0.004 5.527 5.527 make_images 4572 14.5 2.159 2.159 5.465 5.465 multiply_cannon 2286 13.5 0.182 0.182 5.210 5.210 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.075 5.075 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.043 5.043 apply_single 119 13.6 0.000 0.000 5.043 5.043 multiply_cannon_loop 2286 14.5 0.046 0.046 4.728 4.728 fft_wrap_pw1pw2_140 487 13.2 0.426 0.426 4.714 4.714 multiply_cannon_multrec 2286 15.5 4.632 4.632 4.682 4.682 cp_fm_cholesky_decompose 22 10.9 4.474 4.474 4.474 4.474 cp_fm_cholesky_invert 11 10.9 4.144 4.144 4.144 4.144 init_scf_run 11 5.9 0.002 0.002 3.919 3.919 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.917 3.917 dbcsr_complete_redistribute 329 12.2 1.922 1.922 3.705 3.705 dbcsr_copy 2102 12.0 0.210 0.210 3.628 3.628 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.597 3.597 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.587 3.587 wfi_extrapolate 11 7.9 0.001 0.001 3.398 3.398 dbcsr_copy_into_existing 22 7.9 3.385 3.385 3.385 3.385 qs_create_task_list 11 7.9 0.000 0.000 3.222 3.222 generate_qs_task_list 11 8.9 1.959 1.959 3.222 3.222 density_rs2pw 119 9.7 0.005 0.005 3.195 3.195 copy_dbcsr_to_fm 153 11.3 0.002 0.002 3.146 3.146 qs_ot_get_p 119 10.4 0.001 0.001 2.945 2.945 fft3d_s 1202 14.6 2.922 2.922 2.926 2.926 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.605 2.605 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.560 2.560 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.363 2.363 potential_pw2rs 119 12.3 0.047 0.047 2.131 2.131 dbcsr_data_release 279532 16.0 2.100 2.100 2.100 2.100 pw_poisson_solve 119 10.3 0.346 0.346 2.019 2.019 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.987 1.987 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.915 1.915 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.901 1.901 ------------------------------------------------------------------------------- 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 0.023 49.829 49.838 qs_mol_dyn_low 1 2.0 0.003 0.004 49.684 49.688 qs_forces 11 3.9 0.002 0.002 49.643 49.643 qs_energies 11 4.9 0.001 0.001 46.318 46.324 scf_env_do_scf 11 5.9 0.000 0.002 42.367 42.367 scf_env_do_scf_inner_loop 108 6.5 0.003 0.019 39.081 39.081 velocity_verlet 10 3.0 0.001 0.003 30.340 30.341 rebuild_ks_matrix 119 8.3 0.001 0.001 17.886 17.983 qs_ks_build_kohn_sham_matrix 119 9.3 0.016 0.019 17.885 17.983 qs_ks_update_qs_env 119 7.6 0.001 0.001 15.776 15.868 qs_rho_update_rho_low 119 7.7 0.001 0.001 14.708 14.716 calculate_rho_elec 119 8.7 0.030 0.032 14.707 14.716 dbcsr_multiply_generic 2286 12.5 0.079 0.083 14.153 14.548 sum_up_and_integrate 119 10.3 0.035 0.038 13.383 13.437 integrate_v_rspace 119 11.3 0.004 0.005 13.348 13.404 qs_scf_new_mos 108 7.5 0.001 0.001 11.579 11.757 qs_scf_loop_do_ot 108 8.5 0.001 0.001 11.578 11.756 ot_scf_mini 108 9.5 0.002 0.002 10.899 11.062 multiply_cannon 2286 13.5 0.147 0.162 10.309 10.748 multiply_cannon_loop 2286 14.5 0.102 0.116 9.749 10.141 grid_collocate_task_list 119 9.7 9.279 9.726 9.279 9.726 grid_integrate_task_list 119 12.3 8.379 8.724 8.379 8.724 mp_waitall_1 158411 16.6 7.789 8.463 7.789 8.463 multiply_cannon_metrocomm3 18288 15.5 0.044 0.052 5.904 6.497 ot_mini 108 10.5 0.001 0.001 6.253 6.433 rs_pw_transfer 974 11.9 0.012 0.016 5.359 5.769 density_rs2pw 119 9.7 0.005 0.006 4.756 5.101 pw_transfer 1439 11.6 0.077 0.083 4.237 4.369 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 4.087 4.206 multiply_cannon_multrec 18288 15.5 3.440 3.746 3.452 3.758 fft_wrap_pw1pw2_140 487 13.2 0.660 0.801 3.482 3.705 potential_pw2rs 119 12.3 0.007 0.008 3.655 3.677 qs_ot_get_derivative 108 11.5 0.001 0.001 3.187 3.352 init_scf_loop 11 6.9 0.000 0.000 3.268 3.269 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.013 3.129 apply_single 119 13.6 0.000 0.001 3.012 3.129 ot_diis_step 108 11.5 0.003 0.004 3.046 3.046 mp_waitany 9880 13.7 2.402 3.008 2.402 3.008 fft3d_ps 1201 14.6 1.341 1.536 2.660 2.837 init_scf_run 11 5.9 0.000 0.004 2.722 2.722 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.722 2.722 make_m2s 4572 13.5 0.046 0.055 2.608 2.666 wfi_extrapolate 11 7.9 0.001 0.001 2.480 2.481 make_images 4572 14.5 0.119 0.127 2.265 2.336 rs_pw_transfer_RS2PW_140 130 11.5 0.192 0.228 1.905 2.313 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.250 2.258 mp_alltoall_d11v 2130 13.8 1.556 1.914 1.556 1.914 qs_ot_get_p 119 10.4 0.001 0.001 1.652 1.882 rs_gather_matrices 119 12.3 0.100 0.113 1.251 1.587 mp_alltoall_z22v 1201 16.6 1.060 1.429 1.060 1.429 make_images_data 4572 15.5 0.035 0.042 1.272 1.428 rs_pw_transfer_PW2RS_140 130 13.9 0.382 0.481 1.338 1.375 mp_sum_l 11298 13.2 0.769 1.336 0.769 1.336 prepare_preconditioner 11 7.9 0.000 0.000 1.309 1.327 make_preconditioner 11 8.9 0.000 0.000 1.309 1.327 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.195 1.226 hybrid_alltoall_any 4725 16.4 0.070 0.217 1.089 1.211 mp_sum_d 4135 12.0 0.721 1.102 0.721 1.102 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.971 1.059 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.959 1.036 rs_pw_transfer_PW2RS_50 119 14.3 0.340 0.415 0.935 1.023 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 1.020 1.021 ------------------------------------------------------------------------------- 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=48.89699999999999, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.077, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.73, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.219, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.632, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.474, 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=18.54, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.279, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.379, 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=3.44, 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=2.402, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.789, 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 0.032 0.032 112.451 112.451 qs_mol_dyn_low 1 2.0 0.003 0.003 111.764 111.764 qs_forces 11 3.9 0.001 0.001 111.725 111.725 qs_energies 11 4.9 0.001 0.001 103.985 103.985 scf_env_do_scf 11 5.9 0.001 0.001 90.535 90.535 velocity_verlet 10 3.0 0.002 0.002 72.369 72.369 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 72.323 72.323 rebuild_ks_matrix 107 8.3 0.001 0.001 33.713 33.713 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.713 33.713 qs_rho_update_rho_low 107 7.7 0.000 0.000 31.217 31.217 calculate_rho_elec 107 8.7 0.857 0.857 31.217 31.217 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.288 30.288 grid_collocate_task_list 107 9.7 27.279 27.279 27.279 27.279 sum_up_and_integrate 107 10.3 0.702 0.702 27.046 27.046 integrate_v_rspace 107 11.3 0.085 0.085 26.343 26.343 grid_integrate_task_list 107 12.3 24.487 24.487 24.487 24.487 dbcsr_multiply_generic 1966 12.4 0.147 0.147 18.067 18.067 init_scf_loop 11 6.9 0.000 0.000 18.039 18.039 qs_scf_new_mos 96 7.5 0.001 0.001 17.534 17.534 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.534 17.534 ot_scf_mini 96 9.5 0.002 0.002 16.285 16.285 prepare_preconditioner 11 7.9 0.000 0.000 14.021 14.021 make_preconditioner 11 8.9 0.000 0.000 14.021 14.021 make_full_inverse_cholesky 11 9.9 0.024 0.024 12.840 12.840 ot_mini 96 10.5 0.001 0.001 10.577 10.577 make_m2s 3932 13.4 0.040 0.040 9.888 9.888 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.031 7.031 init_scf_run 11 5.9 0.002 0.002 5.768 5.768 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.766 5.766 pw_transfer 1295 11.6 0.058 0.058 5.578 5.578 qs_ot_get_derivative 96 11.5 0.001 0.001 5.461 5.461 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.381 5.381 dbcsr_make_dense_low 4961 15.5 0.070 0.070 5.299 5.299 make_dense_data 4961 16.5 4.618 4.618 5.217 5.217 wfi_extrapolate 11 7.9 0.001 0.001 5.152 5.152 ot_diis_step 96 11.5 0.003 0.003 5.114 5.114 make_images 3932 14.4 1.914 1.914 4.915 4.915 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.770 4.770 apply_single 107 13.6 0.000 0.000 4.770 4.770 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.714 4.714 multiply_cannon 1966 13.4 0.155 0.155 4.674 4.674 fft_wrap_pw1pw2_140 439 13.2 0.510 0.510 4.637 4.637 cp_fm_cholesky_decompose 22 10.9 4.530 4.530 4.530 4.530 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.289 4.289 multiply_cannon_loop 1966 14.4 0.038 0.038 4.262 4.262 multiply_cannon_multrec 1966 15.4 4.175 4.175 4.223 4.223 cp_fm_cholesky_invert 11 10.9 4.060 4.060 4.060 4.060 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.053 4.053 dbcsr_complete_redistribute 317 12.2 1.914 1.914 4.045 4.045 dbcsr_copy 1855 11.9 0.232 0.232 3.695 3.695 qs_create_task_list 11 7.9 0.000 0.000 3.673 3.673 generate_qs_task_list 11 8.9 2.389 2.389 3.672 3.672 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.449 3.449 dbcsr_copy_into_existing 22 7.9 3.429 3.429 3.430 3.430 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.333 3.333 density_rs2pw 107 9.7 0.004 0.004 3.082 3.082 fft3d_s 1082 14.6 2.728 2.728 2.733 2.733 qs_ot_get_p 107 10.4 0.001 0.001 2.577 2.577 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.553 2.553 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.397 2.397 ------------------------------------------------------------------------------- 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 0.012 0.024 73.367 73.377 qs_mol_dyn_low 1 2.0 0.003 0.003 73.125 73.129 qs_forces 11 3.9 0.002 0.002 73.085 73.086 qs_energies 11 4.9 0.001 0.001 68.262 68.264 scf_env_do_scf 11 5.9 0.000 0.002 63.183 63.184 scf_env_do_scf_inner_loop 96 6.5 0.003 0.018 58.404 58.404 velocity_verlet 10 3.0 0.001 0.003 43.639 43.640 rebuild_ks_matrix 107 8.3 0.000 0.001 31.180 31.278 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.017 31.180 31.278 qs_ks_update_qs_env 107 7.6 0.001 0.002 27.475 27.564 sum_up_and_integrate 107 10.3 0.033 0.038 27.159 27.197 integrate_v_rspace 107 11.3 0.004 0.005 27.126 27.167 qs_rho_update_rho_low 107 7.7 0.001 0.001 26.522 26.535 calculate_rho_elec 107 8.7 0.027 0.029 26.521 26.534 grid_integrate_task_list 107 12.3 22.858 23.303 22.858 23.303 grid_collocate_task_list 107 9.7 21.996 22.477 21.996 22.477 dbcsr_multiply_generic 1966 12.4 0.069 0.073 12.489 12.703 qs_scf_new_mos 96 7.5 0.001 0.001 10.237 10.414 qs_scf_loop_do_ot 96 8.5 0.001 0.001 10.237 10.413 ot_scf_mini 96 9.5 0.002 0.003 9.660 9.835 multiply_cannon 1966 13.4 0.130 0.151 9.193 9.574 multiply_cannon_loop 1966 14.4 0.093 0.107 8.677 9.080 mp_waitall_1 136719 16.5 6.957 7.658 6.957 7.658 multiply_cannon_metrocomm3 15728 15.4 0.040 0.048 5.268 5.804 ot_mini 96 10.5 0.001 0.001 5.571 5.763 rs_pw_transfer 878 11.9 0.011 0.013 4.460 5.071 init_scf_loop 11 6.9 0.000 0.000 4.763 4.763 density_rs2pw 107 9.7 0.005 0.005 3.911 4.524 init_scf_run 11 5.9 0.000 0.004 3.992 3.992 scf_env_initial_rho_setup 11 6.9 0.000 0.004 3.992 3.992 pw_transfer 1295 11.6 0.070 0.077 3.849 3.950 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.850 3.864 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 3.715 3.802 wfi_extrapolate 11 7.9 0.001 0.001 3.631 3.631 potential_pw2rs 107 12.3 0.006 0.007 3.317 3.360 fft_wrap_pw1pw2_140 439 13.2 0.574 0.716 3.138 3.338 multiply_cannon_multrec 15728 15.4 3.019 3.294 3.029 3.306 qs_ot_get_derivative 96 11.5 0.001 0.001 2.826 3.003 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.678 2.798 apply_single 107 13.6 0.000 0.000 2.677 2.798 ot_diis_step 96 11.5 0.003 0.003 2.724 2.724 fft3d_ps 1081 14.6 1.183 1.339 2.445 2.635 mp_waitany 8968 13.7 1.810 2.577 1.810 2.577 make_m2s 3932 13.4 0.041 0.049 2.268 2.347 make_images 3932 14.4 0.106 0.111 1.970 2.046 rs_pw_transfer_RS2PW_140 118 11.5 0.162 0.212 1.309 1.916 mp_alltoall_d11v 1998 13.7 1.177 1.886 1.177 1.886 qs_ot_get_p 107 10.4 0.001 0.001 1.486 1.766 rs_gather_matrices 107 12.3 0.084 0.096 0.890 1.603 ------------------------------------------------------------------------------- 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=47.361999999999995, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.279, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.487, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.618, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.53, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.175, 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=16.727000000000004, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.996, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.858, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.019, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=6.957, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.81, 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 0.201 0.201 107.023 107.023 qs_energies 1 2.0 0.000 0.000 106.171 106.171 scf_env_do_scf 1 3.0 0.000 0.000 104.991 104.991 qs_ks_update_qs_env 8 5.0 0.000 0.000 99.652 99.652 rebuild_ks_matrix 7 6.0 0.000 0.000 99.597 99.597 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 99.597 99.597 hfx_ks_matrix 7 8.0 0.000 0.000 90.499 90.499 integrate_four_center 7 9.0 1.607 1.607 90.452 90.452 integrate_four_center_main 7 10.0 0.498 0.498 82.949 82.949 integrate_four_center_bin 449 11.0 82.450 82.450 82.450 82.450 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 57.462 57.462 init_scf_loop 1 4.0 0.000 0.000 47.515 47.515 integrate_four_center_load 7 10.0 0.000 0.000 5.647 5.647 hfx_load_balance 1 11.0 0.001 0.001 5.647 5.647 qs_vxc_create 14 8.0 0.000 0.000 3.251 3.251 xc_vxc_pw_create 14 9.0 0.161 0.161 3.251 3.251 hfx_load_balance_count 1 12.0 2.819 2.819 2.819 2.819 hfx_load_balance_bin 1 12.0 2.811 2.811 2.811 2.811 prepare_preconditioner 1 5.0 0.000 0.000 2.572 2.572 make_preconditioner 1 6.0 0.000 0.000 2.572 2.572 calculate_rho_elec 15 7.4 0.118 0.118 2.488 2.488 xc_rho_set_and_dset_create 14 10.0 0.104 0.104 2.460 2.460 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.164 2.164 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-hyb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.222 0.241 99.334 99.345 qs_energies 1 2.0 0.000 0.000 98.922 98.928 scf_env_do_scf 1 3.0 0.000 0.000 98.571 98.571 qs_ks_update_qs_env 8 5.0 0.000 0.000 95.697 95.698 rebuild_ks_matrix 7 6.0 0.000 0.000 95.688 95.689 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 95.688 95.689 hfx_ks_matrix 7 8.0 0.000 0.000 89.774 89.775 integrate_four_center 7 9.0 0.055 0.347 89.765 89.765 integrate_four_center_main 7 10.0 0.003 0.003 80.722 82.912 integrate_four_center_bin 448 11.0 80.719 82.909 80.719 82.909 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 54.969 54.969 init_scf_loop 1 4.0 0.000 0.000 43.600 43.600 integrate_four_center_load 7 10.0 0.000 0.000 5.779 5.780 hfx_load_balance 1 11.0 0.001 0.001 5.778 5.780 mp_sync 56 11.2 2.581 3.989 2.581 3.989 hfx_load_balance_bin 1 12.0 2.784 2.888 2.784 2.888 hfx_load_balance_count 1 12.0 2.774 2.874 2.774 2.874 qs_vxc_create 14 8.0 0.000 0.000 2.538 2.538 xc_vxc_pw_create 14 9.0 0.007 0.008 2.537 2.537 xc_rho_set_and_dset_create 14 10.0 0.009 0.011 1.963 2.084 ------------------------------------------------------------------------------- Plot: name="H2O-hyb_timings_32omp", title="Timings of H2O-hyb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32omp", name="rest", label="rest", y=16.636999999999986, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=82.45, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.819, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.811, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.607, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.498, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.201, 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=10.195999999999998, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.719, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.774, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.784, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.055, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.222, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=2.581, yerr=0.0 Running GW_PBE_4benzene.inp with 1 threads and 32 ranks... done. Running GW_PBE_4benzene.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.013 0.013 77.799 77.799 qs_energies 1 2.0 0.000 0.000 77.385 77.385 mp2_main 1 3.0 0.000 0.000 74.149 74.149 mp2_gpw_main 1 4.0 0.000 0.000 74.042 74.042 rpa_ri_compute_en 1 5.0 0.000 0.000 70.305 70.305 rpa_num_int 1 6.0 0.001 0.001 70.299 70.299 compute_mat_P_omega 1 7.0 0.003 0.003 60.272 60.272 compute_mat_P_omega_contract 10 8.0 8.887 8.887 60.064 60.064 dbt_total 2336 9.6 0.015 0.015 46.382 46.382 dbt_contract 787 11.0 0.043 0.043 39.379 39.379 dbt_tas_total 1149 12.2 0.209 0.209 38.159 38.159 dbt_tas_multiply 807 12.1 0.002 0.002 36.929 36.929 dbt_tas_dbm 807 14.1 0.003 0.003 30.469 30.469 dbm_multiply 807 16.1 30.461 30.461 30.461 30.461 dbt_tas_mm_1N 524 15.1 0.001 0.001 23.142 23.142 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 21.757 21.757 compute_mat_P_omega_calc_M_occ 250 9.0 8.921 8.921 17.044 17.044 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.798 6.798 dbt_tas_mm_2 251 15.0 0.001 0.001 5.790 5.790 dbt_copy 1103 10.7 0.070 0.070 5.755 5.755 compute_QP_energies 1 7.0 0.000 0.000 5.125 5.125 compute_self_energy_cubic_gw 1 8.0 0.055 0.055 5.124 5.124 contract_cubic_gw 21 9.0 0.000 0.000 4.111 4.111 dbt_tas_reserve_blocks_index 3261 14.3 0.482 0.482 3.769 3.769 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.730 3.730 dbm_reserve_blocks 3628 15.3 3.351 3.351 3.351 3.351 scf_env_do_scf 1 3.0 0.000 0.000 3.075 3.075 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 3.075 3.075 dbt_reserve_blocks_index 2280 13.1 0.059 0.059 2.858 2.858 dbt_reserve_blocks_index_array 2222 12.2 0.011 0.011 2.813 2.813 convert_to_new_pgrid 2421 14.1 0.092 0.092 2.362 2.362 dbt_crop 1042 12.0 1.432 1.432 2.336 2.336 dbt_tas_copy 574 11.4 1.352 1.352 2.284 2.284 dbm_copy 1614 15.1 2.270 2.270 2.270 2.270 compute_W_cubic_GW 10 7.0 0.004 0.004 2.062 2.062 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.997 1.997 dbt_reshape 278 11.9 1.048 1.048 1.941 1.941 dbt_tas_reshape 367 15.0 0.007 0.007 1.925 1.925 get_2c_integrals 1 6.0 0.000 0.000 1.766 1.766 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.573 1.573 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.022 39.501 39.512 qs_energies 1 2.0 0.000 0.001 39.332 39.333 mp2_main 1 3.0 0.000 0.000 38.095 38.097 mp2_gpw_main 1 4.0 0.000 0.000 38.060 38.061 rpa_ri_compute_en 1 5.0 0.000 0.000 36.759 36.760 rpa_num_int 1 6.0 0.000 0.002 36.758 36.759 dbt_total 2336 9.6 0.016 0.016 32.128 32.194 compute_mat_P_omega 1 7.0 0.001 0.005 30.810 30.825 compute_mat_P_omega_contract 10 8.0 0.408 0.431 30.354 30.370 dbt_contract 787 11.0 0.041 0.042 24.019 24.025 dbt_tas_total 1149 12.2 0.080 0.089 21.534 21.539 dbt_tas_multiply 807 12.1 0.002 0.002 21.268 21.273 dbt_tas_dbm 807 14.1 0.003 0.003 15.486 15.492 dbm_multiply 807 16.1 11.358 12.092 11.358 12.092 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 9.518 9.518 mp_sync 8688 11.6 7.615 8.929 7.615 8.929 compute_mat_P_omega_calc_M_occ 250 9.0 0.395 0.418 8.046 8.047 dbt_tas_mm_2 251 15.0 0.001 0.001 7.161 7.166 dbt_copy 1149 10.8 0.014 0.015 6.577 6.869 dbt_reshape 1136 11.8 2.696 2.947 6.177 6.475 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 6.392 6.392 dbt_tas_mm_1N 524 15.1 0.001 0.002 5.113 5.489 compute_QP_energies 1 7.0 0.000 0.000 3.997 3.997 compute_self_energy_cubic_gw 1 8.0 0.003 0.004 3.995 3.996 contract_cubic_gw 21 9.0 0.000 0.000 3.201 3.201 mp_waitall_2 3812 15.3 2.496 2.682 2.496 2.682 dbt_communicate_buffer 1136 12.8 0.051 0.055 2.459 2.630 dbt_reserve_blocks_index 2887 13.1 0.074 0.083 1.787 2.048 dbt_reserve_blocks_index_array 2829 12.2 0.008 0.009 1.776 2.038 dbt_tas_reserve_blocks_index 3347 14.5 0.443 0.500 1.764 2.021 dbt_crop 1042 12.0 0.913 1.044 1.479 1.680 dbm_reserve_blocks 3752 15.4 1.415 1.650 1.415 1.650 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.299 1.300 dbt_tas_replicate 405 14.1 0.545 0.710 1.181 1.237 parallel_gemm_fm 105 8.4 0.000 0.000 1.185 1.191 parallel_gemm_fm_cosma 105 9.4 1.185 1.191 1.185 1.191 mp_max_i 2002 9.8 0.907 1.180 0.907 1.180 scf_env_do_scf 1 3.0 0.000 0.000 1.179 1.179 scf_env_do_scf_inner_loop 17 4.0 0.001 0.002 1.179 1.179 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.154 1.157 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.096 1.098 mp_sum_l 6165 12.9 0.919 1.057 0.919 1.057 convert_to_new_pgrid 2421 14.1 0.027 0.032 0.801 0.945 dbm_copy 1608 15.1 0.768 0.911 0.768 0.911 compute_W_cubic_GW 10 7.0 0.001 0.001 0.897 0.903 ------------------------------------------------------------------------------- Plot: name="GW_PBE_4benzene_timings_32omp", title="Timings of GW_PBE_4benzene with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="rest", label="rest", y=22.861000000000004, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=30.461, 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=8.921, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.887, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.351, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.27, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.048, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=12.349999999999998, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=11.358, 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=0.395, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.408, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.415, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.768, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.696, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=7.615, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.496, 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 0.019 238.365 238.365 qs_forces 1 2.0 0.000 0.000 237.775 237.775 rebuild_ks_matrix 7 6.6 0.000 0.000 236.367 236.367 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 236.367 236.367 hfx_ks_matrix 7 8.6 0.000 0.000 234.547 234.547 hfx_ri_update_ks 7 9.6 0.000 0.000 194.422 194.422 hfx_ri_update_ks_Pmat 7 10.6 31.599 31.599 194.418 194.418 dbt_total 809 11.0 0.006 0.006 180.109 180.109 qs_energies 1 3.0 0.000 0.000 169.965 169.965 scf_env_do_scf 1 4.0 0.000 0.000 169.666 169.666 qs_ks_update_qs_env 8 6.0 0.000 0.000 168.608 168.608 dbt_contract 207 12.4 0.033 0.033 161.246 161.246 dbt_tas_total 343 13.7 1.644 1.644 159.315 159.315 dbt_tas_multiply 216 13.5 0.001 0.001 156.014 156.014 dbt_tas_dbm 216 15.5 0.001 0.001 143.723 143.723 dbm_multiply 216 17.5 143.719 143.719 143.719 143.719 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.000 138.601 138.601 dbt_tas_mm_2 91 16.5 0.001 0.001 130.187 130.187 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 107.026 107.026 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 67.762 67.762 init_scf_loop 2 5.0 0.000 0.000 62.638 62.638 hfx_ri_update_forces 1 7.0 1.604 1.604 40.122 40.122 hfx_ri_forces_Pmat_3c 1 8.0 4.724 4.724 22.824 22.824 dbt_copy 409 11.7 0.027 0.027 15.554 15.554 precalc_derivatives 1 8.0 2.186 2.186 13.233 13.233 dbt_reshape 132 13.2 6.697 6.697 10.763 10.763 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.505 9.505 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.150 9.150 dbt_tas_reserve_blocks_index 1255 15.4 1.028 1.028 7.906 7.906 build_3c_derivatives 3 9.0 2.980 2.980 7.376 7.376 dbm_reserve_blocks 1397 16.3 7.092 7.092 7.092 7.092 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.699 6.699 dbt_reserve_blocks_index 818 14.4 0.097 0.097 6.139 6.139 dbt_reserve_blocks_index_array 795 13.4 0.007 0.007 6.032 6.032 dbt_crop 372 13.7 2.822 2.822 4.926 4.926 ------------------------------------------------------------------------------- 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 0.027 56.415 56.425 qs_forces 1 2.0 0.000 0.000 56.213 56.214 rebuild_ks_matrix 7 6.6 0.000 0.000 55.317 55.318 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 55.317 55.318 hfx_ks_matrix 7 8.6 0.000 0.000 54.143 54.149 dbt_total 809 11.0 0.006 0.006 48.313 48.337 dbt_contract 207 12.4 0.025 0.027 37.971 37.989 dbt_tas_total 343 13.7 0.086 0.219 33.560 33.568 dbt_tas_multiply 216 13.5 0.001 0.001 33.179 33.184 hfx_ri_update_ks 7 9.6 0.000 0.000 33.133 33.133 hfx_ri_update_ks_Pmat 7 10.6 1.252 1.393 33.129 33.130 qs_energies 1 3.0 0.000 0.000 30.800 30.800 scf_env_do_scf 1 4.0 0.000 0.001 30.587 30.587 qs_ks_update_qs_env 8 6.0 0.000 0.000 29.915 29.916 dbt_tas_dbm 216 15.5 0.001 0.001 25.734 25.750 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 25.403 25.403 dbm_multiply 216 17.5 21.233 22.251 21.233 22.251 hfx_ri_update_forces 1 7.0 0.057 0.059 21.009 21.015 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 17.362 17.362 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 16.656 16.669 hfx_ri_forces_Pmat_3c 1 8.0 0.161 0.188 15.575 15.576 init_scf_loop 2 5.0 0.000 0.000 13.224 13.225 dbt_tas_mm_2 91 16.5 0.001 0.001 13.172 13.181 mp_sync 2769 12.9 8.295 9.733 8.295 9.733 dbt_copy 497 12.3 0.011 0.013 8.920 9.345 dbt_reshape 365 13.6 3.611 3.736 6.980 7.284 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.817 6.559 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.578 5.579 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.509 4.742 precalc_derivatives 1 8.0 0.080 0.091 3.850 3.850 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.603 3.603 dbt_tas_reserve_blocks_index 1380 15.8 0.908 0.965 3.147 3.516 mp_waitall_2 1234 16.4 2.979 3.251 2.979 3.251 dbt_reserve_blocks_index 1051 14.7 0.117 0.127 2.621 2.890 dbt_reserve_blocks_index_array 1028 13.8 0.005 0.006 2.594 2.859 dbm_reserve_blocks 1529 16.7 2.439 2.845 2.439 2.845 dbt_crop 372 13.7 1.789 1.912 2.588 2.720 dbt_communicate_buffer 365 14.6 0.012 0.013 2.115 2.355 build_3c_derivatives 3 9.0 0.227 0.256 2.185 2.194 mp_sum_l 6385 13.7 1.831 2.091 1.831 2.091 dbt_tas_replicate 149 15.4 0.648 0.692 1.712 1.818 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.810 1.811 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.783 1.786 convert_to_new_pgrid 648 15.5 0.039 0.093 1.400 1.583 dbm_copy 452 16.3 1.221 1.405 1.221 1.405 dbt_tas_copy 132 12.5 0.624 0.675 1.216 1.347 ------------------------------------------------------------------------------- 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=44.53400000000002, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=143.719, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.599, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.092, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.697, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.724, 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=16.445, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=21.233, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.252, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.439, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.611, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.161, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.979, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=8.295, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.015 0.015 177.426 177.426 qs_energies 1 2.0 0.000 0.000 177.235 177.235 mp2_main 1 3.0 0.000 0.000 172.530 172.530 mp2_gpw_main 1 4.0 0.001 0.001 172.101 172.101 mp2_ri_gpw_compute_in 1 5.0 0.390 0.390 122.571 122.571 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 113.631 113.631 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 82.399 82.399 integrate_v_rspace 2666 8.0 0.614 0.614 69.697 69.697 grid_integrate_task_list 2666 9.0 67.101 67.101 67.101 67.101 mp2_ri_gpw_compute_en 1 5.0 0.089 0.089 49.505 49.505 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.485 9.485 47.654 47.654 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.221 2.221 30.944 30.944 local_gemm 2080 8.0 28.723 28.723 28.723 28.723 dbcsr_multiply_generic 5322 8.0 0.184 0.184 21.523 21.523 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 21.502 21.502 pw_transfer 63872 10.6 1.039 1.039 11.736 11.736 calculate_wavefunction 2656 8.0 8.012 8.012 11.368 11.368 multiply_cannon 5322 9.0 0.444 0.444 11.072 11.072 fft_wrap_pw1pw2 53228 11.4 0.118 0.118 10.482 10.482 multiply_cannon_loop 5322 10.0 0.121 0.121 9.724 9.724 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.389 2.389 9.616 9.616 get_2c_integrals 1 6.0 0.000 0.000 8.549 8.549 make_m2s 10644 9.0 0.059 0.059 8.275 8.275 multiply_cannon_multrec 5322 11.0 8.183 8.183 8.221 8.221 make_images 10644 10.0 3.250 3.250 7.957 7.957 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 7.734 7.734 compute_2c_integrals 1 7.0 0.006 0.006 7.709 7.709 compute_2c_integrals_loop_lm 1 8.0 0.013 0.013 7.697 7.697 mp2_eri_2c_integrate_gpw 1 9.0 0.831 0.831 7.685 7.685 fft_wrap_pw1pw2_20 21271 12.4 0.454 0.454 7.527 7.527 fft3d_s 53229 13.4 6.427 6.427 6.465 6.465 dbcsr_complete_redistribute 2689 9.0 1.118 1.118 6.192 6.192 mp2_ri_gpw_compute_en_ener 2080 7.0 5.418 5.418 5.418 5.418 dbcsr_finalize 10708 9.5 0.164 0.164 5.318 5.318 dbcsr_merge_all 8011 10.3 3.616 3.616 4.691 4.691 scf_env_do_scf 1 3.0 0.000 0.000 4.299 4.299 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.299 4.299 potential_pw2rs 5322 10.0 0.149 0.149 3.907 3.907 ------------------------------------------------------------------------------- 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 0.028 39.965 39.975 qs_energies 1 2.0 0.000 0.000 39.528 39.528 mp2_main 1 3.0 0.000 0.001 37.453 37.453 mp2_gpw_main 1 4.0 0.001 0.002 37.348 37.348 mp2_ri_gpw_compute_en 1 5.0 0.277 0.291 19.932 20.304 mp2_ri_gpw_compute_in 1 5.0 0.052 0.052 17.328 18.191 mp2_ri_gpw_compute_en_RI_loop 1 6.0 3.381 3.853 18.110 18.120 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 16.038 16.905 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.919 14.721 integrate_v_rspace 93 8.1 0.100 0.105 13.808 14.578 grid_integrate_task_list 93 9.1 13.491 14.253 13.491 14.253 mp2_ri_gpw_compute_en_expansio 65 7.0 0.131 0.158 10.946 11.079 local_gemm 65 8.0 10.815 10.921 10.815 10.921 mp2_ri_gpw_compute_en_comm 30 7.0 0.112 0.165 3.400 4.062 mp_sendrecv_dm3 1860 8.0 2.646 3.438 2.646 3.438 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.813 1.977 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.797 1.959 scf_env_do_scf 1 3.0 0.000 0.000 1.944 1.945 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.944 1.945 mp_min_d 2 7.0 0.888 1.281 0.888 1.281 get_2c_integrals 1 6.0 0.004 0.010 1.216 1.254 mp2_ri_get_integ_group_size 1 6.0 0.000 0.000 0.866 1.238 multiply_cannon 176 9.0 0.016 0.017 1.135 1.207 multiply_cannon_loop 176 10.0 0.002 0.002 1.080 1.152 multiply_cannon_multrec 246 11.0 0.955 1.029 0.960 1.033 qs_scf_new_mos 10 5.0 0.000 0.000 0.942 0.951 eigensolver 11 5.8 0.001 0.001 0.904 0.905 fill_local_i_aL 1920 8.0 0.687 0.888 0.687 0.888 compute_2c_integrals 1 7.0 0.003 0.004 0.868 0.884 ------------------------------------------------------------------------------- Plot: name="RI-MP2_ammonia_timings_32omp", title="Timings of RI-MP2_ammonia with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="rest", label="rest", y=55.922, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=67.101, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=28.723, 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=9.485, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.183, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.012, 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=8.677000000000007, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.491, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.815, 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=3.381, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.955, 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=2.646, 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 0.092 0.092 122.568 122.568 qs_energies 1 2.0 0.000 0.000 121.115 121.115 scf_env_do_scf 1 3.0 0.000 0.000 114.527 114.527 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 114.527 114.527 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.822 48.822 rebuild_ks_matrix 15 6.0 0.000 0.000 48.614 48.614 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.614 48.614 qs_scf_new_mos 15 5.0 0.000 0.000 42.738 42.738 eigensolver 15 6.0 0.001 0.001 34.969 34.969 qs_vxc_create 15 8.0 0.027 0.027 33.166 33.166 calculate_dispersion_nonloc 15 9.0 6.708 6.708 28.800 28.800 pw_transfer 1191 10.0 0.058 0.058 22.948 22.948 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 22.780 22.780 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.272 22.272 cp_fm_diag_elpa_base 15 8.0 19.676 19.676 22.272 22.272 qs_rho_update_rho_low 16 5.0 0.000 0.000 19.883 19.883 calculate_rho_elec 16 6.0 0.216 0.216 19.883 19.883 grid_collocate_task_list 16 7.0 18.461 18.461 18.461 18.461 fft_wrap_pw1pw2_150 765 12.0 3.570 3.570 16.447 16.447 sum_up_and_integrate 15 8.0 0.139 0.139 14.246 14.246 integrate_v_rspace 15 9.0 0.018 0.018 14.107 14.107 grid_integrate_task_list 15 10.0 13.578 13.578 13.578 13.578 cp_fm_cholesky_restore 45 7.0 10.387 10.387 10.387 10.387 fft3d_s 1087 13.0 10.010 10.010 10.017 10.017 pw_scatter_s 585 13.1 7.246 7.246 7.246 7.246 fft_wrap_pw1pw2_200 197 12.3 0.807 0.807 6.146 6.146 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.632 5.632 dbcsr_complete_redistribute 46 8.3 2.240 2.240 5.531 5.531 cp_fm_upper_to_full 30 8.0 4.905 4.905 4.905 4.905 xc_vxc_pw_create 15 9.0 0.217 0.217 4.339 4.339 vdW_energy 15 10.0 4.316 4.316 4.316 4.316 gspace_mixing 14 5.0 0.171 0.171 4.160 4.160 broyden_mixing 14 6.0 3.526 3.526 3.526 3.526 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.102 3.102 init_scf_run 1 3.0 0.000 0.000 3.015 3.015 xc_pw_derive 90 11.0 0.001 0.001 2.835 2.835 calculate_dm_sparse 15 6.0 0.016 0.016 2.497 2.497 ------------------------------------------------------------------------------- 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 0.023 67.747 67.757 qs_energies 1 2.0 0.000 0.000 67.444 67.449 scf_env_do_scf 1 3.0 0.000 0.001 63.448 63.448 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 63.448 63.448 qs_ks_update_qs_env 15 5.0 0.000 0.000 26.897 26.986 rebuild_ks_matrix 15 6.0 0.000 0.000 26.865 26.954 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 26.865 26.954 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.885 20.891 calculate_rho_elec 16 6.0 0.007 0.008 20.885 20.891 grid_collocate_task_list 16 7.0 17.517 18.356 17.517 18.356 qs_scf_new_mos 15 5.0 0.000 0.000 16.140 16.613 sum_up_and_integrate 15 8.0 0.015 0.020 16.256 16.389 integrate_v_rspace 15 9.0 0.001 0.001 16.241 16.379 eigensolver 15 6.0 0.001 0.002 15.037 15.074 grid_integrate_task_list 15 10.0 13.340 14.013 13.340 14.013 qs_vxc_create 15 8.0 0.001 0.001 10.285 10.298 cp_fm_diag_elpa 15 7.0 0.000 0.000 10.279 10.290 cp_fm_diag_elpa_base 15 8.0 10.132 10.154 10.270 10.274 calculate_dispersion_nonloc 15 9.0 0.909 0.939 8.213 8.237 pw_transfer 1191 10.0 0.085 0.101 8.071 8.135 fft_wrap_pw1pw2 1086 11.0 0.012 0.014 7.909 7.994 fft3d_ps 1086 13.0 2.675 3.096 5.411 5.902 fft_wrap_pw1pw2_150 765 12.0 0.610 0.750 5.080 5.110 cp_fm_cholesky_restore 45 7.0 4.604 4.663 4.604 4.663 density_rs2pw 16 7.0 0.001 0.001 3.146 3.507 rs_pw_transfer 158 9.4 0.002 0.002 3.108 3.468 mp_alltoall_z22v 1086 15.0 2.170 3.118 2.170 3.118 mp_waitany 520 11.3 2.213 3.011 2.213 3.011 mp_alltoall_d11v 217 9.2 2.608 2.885 2.608 2.885 fft_wrap_pw1pw2_200 197 12.3 0.436 0.553 2.718 2.752 rs_gather_matrices 15 10.0 0.027 0.034 2.352 2.628 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.476 2.476 rs_pw_transfer_RS2PW_200 18 8.8 0.024 0.034 1.541 2.427 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.179 2.369 xc_vxc_pw_create 15 9.0 0.015 0.021 2.071 2.112 yz_to_x 501 13.9 0.207 0.267 1.311 1.810 x_to_yz 585 14.1 0.334 0.362 1.400 1.804 xc_pw_derive 90 11.0 0.001 0.002 1.429 1.503 build_core_ppnl 1 5.0 1.278 1.499 1.278 1.499 rs_pw_transfer_RS2PW_30 16 9.0 0.009 0.010 0.699 1.417 mp_sendrecv_dv 1488 10.0 0.696 1.413 0.696 1.413 vdW_energy 15 10.0 1.301 1.356 1.301 1.356 ------------------------------------------------------------------------------- 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=50.45599999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.676, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=18.461, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.578, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.387, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.01, 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=19.479, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=10.132, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=17.517, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.34, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=4.604, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.675, 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 0.074 0.074 273.698 273.698 qs_energies 1 2.0 0.000 0.000 273.564 273.564 ls_scf 1 3.0 0.000 0.000 272.328 272.328 ls_scf_main 1 4.0 0.002 0.002 263.228 263.228 density_matrix_trs4 11 5.0 0.012 0.012 164.444 164.444 ls_scf_dm_to_ks 11 5.0 0.000 0.000 92.855 92.855 matrix_ls_to_qs 11 6.0 0.000 0.000 89.280 89.280 dbcsr_multiply_generic 185 6.1 0.947 0.947 80.934 80.934 arnoldi_extremal 12 6.1 0.000 0.000 66.464 66.464 arnoldi_normal_ev 12 7.1 0.052 0.052 66.464 66.464 build_subspace 23 8.1 0.084 0.084 65.210 65.210 dbcsr_matrix_vector_mult 652 9.0 0.239 0.239 64.434 64.434 dbcsr_matrix_vector_mult_local 652 10.0 62.664 62.664 62.673 62.673 dbcsr_complete_redistribute 23 7.5 33.793 33.793 47.506 47.506 multiply_cannon 185 7.1 0.376 0.376 46.354 46.354 dbcsr_copy_into_existing 11 7.0 45.903 45.903 45.904 45.904 matrix_decluster 11 7.0 0.000 0.000 43.375 43.375 multiply_cannon_loop 185 8.1 0.241 0.241 33.301 33.301 make_m2s 370 7.1 0.039 0.039 29.467 29.467 make_images 370 8.1 13.137 13.137 27.052 27.052 multiply_cannon_multrec 185 9.1 23.791 23.791 23.930 23.930 dbcsr_finalize 646 7.5 0.232 0.232 17.931 17.931 dbcsr_merge_all 597 8.5 2.634 2.634 16.600 16.600 setup_rec_index_2d 370 8.1 12.565 12.565 12.565 12.565 tree_to_linear_d 110 9.4 12.377 12.377 12.377 12.377 dbcsr_sort_indices 1103 9.9 11.879 11.879 11.879 11.879 quick_finalize 395 10.0 0.468 0.468 10.293 10.293 dbcsr_special_finalize 370 9.1 0.002 0.002 9.549 9.549 calculate_norms 370 9.1 9.130 9.130 9.130 9.130 ls_scf_init_scf 1 4.0 0.000 0.000 8.397 8.397 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.061 8.061 dbcsr_dot_sd 144 6.3 7.909 7.909 7.909 7.909 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.410 7.410 dbcsr_frobenius_norm 142 6.1 6.124 6.124 6.126 6.126 matrix_qs_to_ls 12 5.1 0.000 0.000 6.101 6.101 matrix_cluster 12 6.1 0.000 0.000 6.101 6.101 ------------------------------------------------------------------------------- From /workspace/artifacts/bench_dftb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.021 69.544 69.554 qs_energies 1 2.0 0.000 0.000 69.424 69.424 ls_scf 1 3.0 0.000 0.000 69.374 69.375 ls_scf_main 1 4.0 0.000 0.006 66.750 66.750 density_matrix_trs4 11 5.0 0.006 0.018 64.208 64.290 dbcsr_multiply_generic 185 6.1 0.058 0.074 60.870 61.136 multiply_cannon 185 7.1 0.032 0.036 50.143 51.129 multiply_cannon_loop 185 8.1 0.107 0.123 47.735 48.573 multiply_cannon_multrec 1480 9.1 28.710 33.334 28.954 33.586 mp_waitall_1 11936 10.3 16.938 21.738 16.938 21.738 multiply_cannon_metrocomm3 1480 9.1 0.014 0.017 12.817 17.802 make_m2s 370 7.1 0.034 0.036 6.982 7.051 make_images 370 8.1 0.631 0.653 6.853 6.923 calculate_norms 2960 9.1 4.642 5.418 4.642 5.418 mp_sum_l 1199 5.3 2.863 3.753 2.863 3.753 make_images_data 370 9.1 0.010 0.014 3.212 3.437 hybrid_alltoall_any 393 9.9 0.223 0.982 2.777 3.099 multiply_cannon_metrocomm1 1480 9.1 0.006 0.007 1.179 2.686 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.978 2.685 arnoldi_extremal 12 6.1 0.000 0.001 2.505 2.536 arnoldi_normal_ev 12 7.1 0.001 0.008 2.505 2.535 build_subspace 23 8.1 0.020 0.025 2.400 2.402 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.194 2.313 dbcsr_matrix_vector_mult 652 9.0 0.013 0.049 2.027 2.095 dbcsr_complete_redistribute 23 7.5 1.185 1.272 1.979 2.063 matrix_ls_to_qs 11 6.0 0.000 0.000 1.920 2.001 ls_scf_init_scf 1 4.0 0.000 0.000 1.997 1.999 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.964 1.971 matrix_decluster 11 7.0 0.000 0.000 1.779 1.861 make_images_pack 370 9.1 1.646 1.825 1.650 1.829 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.782 1.785 dbcsr_matrix_vector_mult_local 652 10.0 1.617 1.776 1.619 1.777 buffer_matrices_ensure_size 370 8.1 1.349 1.625 1.349 1.625 ------------------------------------------------------------------------------- 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=85.27999999999997, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=62.664, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=45.903, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=33.793, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.791, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images", label="make_images", y=13.137, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.13, 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 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=11.311999999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.617, 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=1.185, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=28.71, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images", label="make_images", y=0.631, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.642, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.646, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=16.938, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.863, yerr=0.0 Running dbcsr.inp with 1 threads and 32 ranks... done. Running dbcsr.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/dbcsr_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.007 73.255 73.255 lib_test 1 2.0 0.000 0.000 73.247 73.247 dbcsr_run_tests 3 3.0 0.002 0.002 73.246 73.246 test_multiplies_multiproc 3 4.0 0.001 0.001 57.247 57.247 dbcsr_redistribute 9 5.0 37.474 37.474 39.106 39.106 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.781 16.781 dbcsr_make_random_matrix 9 4.0 12.765 12.765 15.887 15.887 multiply_cannon 9 6.0 0.002 0.002 11.973 11.973 multiply_cannon_loop 9 7.0 0.020 0.020 11.610 11.610 multiply_cannon_multrec 9 8.0 11.589 11.589 11.590 11.590 dbcsr_finalize 27 5.7 0.013 0.013 5.698 5.698 dbcsr_merge_all 18 6.5 2.014 2.014 4.946 4.946 dbcsr_data_release 975 7.6 2.862 2.862 2.862 2.862 tree_to_linear_d 9 7.0 1.959 1.959 1.959 1.959 make_m2s 18 6.0 0.001 0.001 1.668 1.668 make_images 18 7.0 0.573 0.573 1.619 1.619 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.004 0.011 20.049 20.053 lib_test 1 2.0 0.000 0.000 20.012 20.033 dbcsr_run_tests 3 3.0 0.000 0.001 20.011 20.032 test_multiplies_multiproc 3 4.0 0.000 0.002 19.152 19.220 dbcsr_multiply_generic 9 5.0 0.001 0.001 17.424 17.527 multiply_cannon 9 6.0 0.001 0.002 15.343 15.884 multiply_cannon_loop 9 7.0 0.002 0.002 15.057 15.565 multiply_cannon_multrec 72 8.0 11.239 11.809 11.240 11.809 mp_waitall_1 576 9.2 4.171 5.058 4.171 5.058 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 3.711 4.623 mp_sum_l 470 2.5 0.821 1.507 0.821 1.507 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.810 1.495 dbcsr_make_random_matrix 9 4.0 0.664 0.713 0.810 0.845 dbcsr_data_release 444 7.6 0.736 0.839 0.736 0.839 make_m2s 18 6.0 0.001 0.001 0.736 0.787 make_images 18 7.0 0.021 0.023 0.732 0.783 dbcsr_destroy 111 5.9 0.003 0.077 0.645 0.754 dbcsr_finalize 27 5.7 0.000 0.000 0.549 0.665 dbcsr_redistribute 9 5.0 0.257 0.299 0.585 0.620 dbcsr_merge_all 18 6.5 0.081 0.104 0.454 0.537 make_images_data 18 8.0 0.001 0.001 0.398 0.478 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.101 0.414 ------------------------------------------------------------------------------- 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=6.551000000000002, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=37.474, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.765, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.589, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.862, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.014, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=2.0799999999999983, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.257, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.664, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.239, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.736, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.081, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.821, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=4.171, 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 0.075 0.075 141.347 141.347 qs_mol_dyn_low 1 2.0 0.003 0.003 139.869 139.869 velocity_verlet 5 3.0 0.004 0.004 115.139 115.139 qmmm_el_coupling 6 3.8 0.000 0.000 90.425 90.425 qmmm_elec_with_gaussian 6 4.8 0.031 0.031 90.421 90.421 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 89.459 89.459 qmmm_elec_gaussian_low_G 6 6.8 88.558 88.558 88.558 88.558 qs_forces 6 3.8 0.001 0.001 40.221 40.221 qs_energies 6 4.8 0.000 0.000 35.330 35.330 scf_env_do_scf 6 5.8 0.001 0.001 32.856 32.856 rebuild_ks_matrix 45 8.4 0.000 0.000 28.766 28.766 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 28.765 28.765 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 28.453 28.453 qs_ks_update_qs_env 45 7.8 0.000 0.000 24.324 24.324 pw_transfer 966 12.3 0.054 0.054 17.737 17.737 fft_wrap_pw1pw2 801 13.6 0.006 0.006 17.518 17.518 fft_wrap_pw1pw2_150 507 15.2 2.530 2.530 17.114 17.114 qs_vxc_create 45 10.4 0.001 0.001 14.646 14.646 xc_vxc_pw_create 45 11.4 0.751 0.751 14.645 14.645 xc_pw_derive 270 13.4 0.002 0.002 9.629 9.629 xc_rho_set_and_dset_create 45 12.4 1.101 1.101 7.970 7.970 fft3d_s 802 15.6 7.606 7.606 7.614 7.614 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.571 7.571 calculate_rho_elec 45 8.9 0.625 0.625 7.570 7.570 pw_integral_ab 2539 7.4 7.025 7.025 7.025 7.025 pw_scatter_s 429 15.8 6.048 6.048 6.048 6.048 qmmm_forces 6 3.8 0.003 0.003 6.001 6.001 xc_pw_divergence 45 12.4 0.001 0.001 5.863 5.863 qmmm_forces_with_gaussian 6 4.8 0.043 0.043 5.594 5.594 qs_ks_ddapc 45 10.4 0.001 0.001 5.155 5.155 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 4.457 4.457 init_scf_loop 6 6.8 0.000 0.000 4.398 4.398 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.378 4.378 sum_up_and_integrate 45 10.4 0.859 0.859 4.012 4.012 qmmm_forces_gaussian_low_G 6 6.8 3.654 3.654 3.654 3.654 density_rs2pw 45 9.9 0.002 0.002 3.550 3.550 cp_ddapc_apply_CD 45 11.4 0.005 0.005 3.483 3.483 grid_collocate_task_list 45 9.9 3.396 3.396 3.396 3.396 pw_poisson_solve 51 9.9 0.570 0.570 3.275 3.275 integrate_v_rspace 45 11.4 0.007 0.007 3.153 3.153 ------------------------------------------------------------------------------- From /workspace/artifacts/MQAE_single_node_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.040 0.061 62.564 62.579 qs_mol_dyn_low 1 2.0 0.003 0.004 61.244 61.302 qs_forces 6 3.8 0.001 0.001 45.872 45.873 qs_energies 6 4.8 0.000 0.001 43.812 43.812 scf_env_do_scf 6 5.8 0.000 0.001 42.673 42.673 scf_env_do_scf_inner_loop 113 6.2 0.003 0.017 40.772 40.773 rebuild_ks_matrix 119 8.1 0.000 0.000 30.281 30.290 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.018 30.280 30.290 qs_ks_update_qs_env 119 7.3 0.001 0.001 28.517 28.526 velocity_verlet 5 3.0 0.002 0.004 25.470 25.473 pw_transfer 2446 12.3 0.169 0.207 21.703 22.247 fft_wrap_pw1pw2 2059 13.4 0.022 0.027 21.298 21.905 fft_wrap_pw1pw2_150 1321 14.9 3.415 4.322 20.574 21.116 qs_vxc_create 119 10.1 0.002 0.004 16.401 16.404 xc_vxc_pw_create 119 11.1 0.156 0.228 16.398 16.402 fft3d_ps 2059 15.4 7.592 8.771 14.119 16.150 xc_pw_derive 714 13.1 0.008 0.010 12.697 12.952 qs_rho_update_rho_low 119 7.3 0.001 0.001 11.793 11.794 calculate_rho_elec 119 8.3 0.050 0.065 11.792 11.793 sum_up_and_integrate 119 10.1 0.076 0.097 10.110 10.139 integrate_v_rspace 119 11.1 0.003 0.004 10.034 10.077 xc_pw_divergence 119 12.1 0.004 0.006 8.287 8.550 xc_rho_set_and_dset_create 119 12.1 0.336 0.420 7.704 7.913 qmmm_forces 6 3.8 0.002 0.003 7.886 7.886 qmmm_forces_with_gaussian 6 4.8 0.007 0.008 7.397 7.722 mp_alltoall_z22v 2059 17.4 5.173 7.659 5.173 7.659 rs_pw_transfer 988 11.5 0.012 0.017 7.110 7.473 density_rs2pw 119 9.3 0.006 0.008 7.025 7.335 qmmm_el_coupling 6 3.8 0.000 0.000 6.488 6.708 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 6.486 6.706 potential_pw2rs 119 12.1 0.006 0.007 6.142 6.173 grid_collocate_task_list 119 9.3 4.526 4.965 4.526 4.965 x_to_yz 1095 16.8 0.759 0.861 3.481 4.502 yz_to_x 964 16.0 0.540 0.702 2.991 4.432 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.108 4.163 mp_waitany 4028 12.8 2.978 3.858 2.978 3.858 grid_integrate_task_list 119 12.1 3.597 3.790 3.597 3.790 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.613 3.665 qmmm_forces_gaussian_low_G 6 6.8 3.378 3.431 3.378 3.431 qmmm_elec_gaussian_low_G 6 6.8 3.020 3.066 3.020 3.066 pw_restrict_s3 18 5.8 1.458 1.544 2.723 2.994 rs_pw_transfer_PW2RS_150 125 13.9 0.807 1.073 2.715 2.802 pw_gather_p 964 15.0 2.132 2.629 2.132 2.629 qs_scf_new_mos 113 7.2 0.000 0.001 2.579 2.586 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.578 2.586 rs_pw_transfer_RS2PW_150 125 11.2 0.641 0.826 2.130 2.493 ot_scf_mini 113 9.2 0.001 0.001 2.480 2.485 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.202 2.420 pw_prolongate_s3 18 6.8 1.201 1.256 2.202 2.420 qs_ks_ddapc 119 10.1 0.002 0.003 2.247 2.403 dbcsr_multiply_generic 2588 12.3 0.059 0.063 1.965 2.003 init_scf_loop 6 6.8 0.000 0.000 1.898 1.898 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.774 1.774 pw_integral_ab 2761 7.7 1.194 1.422 1.588 1.751 mp_sum_d 5822 12.2 1.028 1.737 1.028 1.737 pw_scatter_p 1095 15.8 1.564 1.626 1.564 1.626 mp_waitall_1 177795 16.4 1.126 1.424 1.126 1.424 ot_mini 113 10.2 0.000 0.001 1.264 1.270 rs_pw_transfer_PW2RS_40 119 14.1 0.271 0.339 1.100 1.262 ------------------------------------------------------------------------------- Plot: name="MQAE_single_node_timings_32omp", title="Timings of MQAE_single_node with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32omp", name="rest", label="rest", y=22.53, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=88.558, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.606, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=7.025, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=6.048, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.654, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.396, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=2.53, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=30.668999999999997, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=3.02, 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_integral_ab", label="pw_integral_ab", y=1.194, 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=3.378, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.526, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=3.415, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.592, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=5.173, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.597, yerr=0.0 Summary: Performance test took 33 minutes. Status: OK Removing intermediate container 889d7f648b36 ---> 17be2d5a1dd8 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in ed92d8496b46 Removing intermediate container ed92d8496b46 ---> 60444190d1c9 Step 42/42 : ENTRYPOINT [] ---> Running in c333e487f2d9 Removing intermediate container c333e487f2d9 ---> 624b999d7b44 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 624b999d7b44 Successfully tagged us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2023-06-19 19:55:41+00:00