StartDate: 2023-08-25 20:51:14+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 967ffb23fcb37d756e27952afc52a46e8dcd503a CommitTime: 2023-08-25 13:16:27 +0200 CommitAuthor: Stefano Battaglia CommitSubject: Fix compilation errors without HDF5 library (#2947) #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=967ffb23fcb37d756e27952afc52a46e8dcd503a 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 384MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu b237fe92c417: Pulling fs layer 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 ---> 681ecfd46f6d Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 076f3cb6b0aa Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 8db0716827e4 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 67be6bd9dd89 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 429fb98f5e86 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 2238d14a585d Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> becb37b73d35 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 8ba4e482f6c2 Step 31/42 : COPY ./src ./src ---> Using cache ---> 6bea6392af8b Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 89cf3d87dd13 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 022640e11a81 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 cf1267839f36 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container cf1267839f36 ---> 31d262dfb1e7 Step 35/42 : COPY ./data ./data ---> b3e00dbaf365 Step 36/42 : COPY ./tests ./tests ---> 2f8397c66eee Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 199272241c03 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 300adefc2338 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 1315d20b38da Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in bb962511c295 ========== 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 0.045 0.045 98.174 98.174 qs_mol_dyn_low 1 2.0 0.003 0.003 97.423 97.423 qs_forces 11 3.9 0.001 0.001 97.379 97.379 qs_energies 11 4.9 0.001 0.001 90.971 90.971 scf_env_do_scf 11 5.9 0.002 0.002 79.056 79.056 scf_env_do_scf_inner_loop 108 6.5 0.013 0.013 61.590 61.590 velocity_verlet 10 3.0 0.002 0.002 60.339 60.339 qs_scf_new_mos 108 7.5 0.001 0.001 23.217 23.217 qs_scf_loop_do_ot 108 8.5 0.001 0.001 23.216 23.216 qs_ks_update_qs_env 119 7.6 0.001 0.001 23.208 23.208 rebuild_ks_matrix 119 8.3 0.001 0.001 23.050 23.050 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 23.050 23.050 dbcsr_multiply_generic 2286 12.5 0.160 0.160 22.521 22.521 ot_scf_mini 108 9.5 0.002 0.002 21.650 21.650 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.198 19.198 calculate_rho_elec 119 8.7 1.090 1.090 19.197 19.197 init_scf_loop 11 6.9 0.000 0.000 17.281 17.281 grid_collocate_task_list 119 9.7 14.818 14.818 14.818 14.818 prepare_preconditioner 11 7.9 0.000 0.000 14.409 14.409 make_preconditioner 11 8.9 0.000 0.000 14.409 14.409 ot_mini 108 10.5 0.001 0.001 14.232 14.232 make_full_inverse_cholesky 11 9.9 0.030 0.030 12.982 12.982 sum_up_and_integrate 119 10.3 0.001 0.001 12.609 12.609 integrate_v_rspace 119 11.3 0.118 0.118 12.545 12.545 make_m2s 4572 13.5 0.045 0.045 11.430 11.430 grid_integrate_task_list 119 12.3 10.535 10.535 10.535 10.535 qs_ot_get_derivative 108 11.5 0.001 0.001 7.307 7.307 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.244 7.244 ot_diis_step 108 11.5 0.004 0.004 6.921 6.921 multiply_cannon 2286 13.5 0.178 0.178 6.795 6.795 make_images 4572 14.5 2.660 2.660 6.347 6.347 multiply_cannon_loop 2286 14.5 0.074 0.074 6.333 6.333 multiply_cannon_multrec 2286 15.5 6.204 6.204 6.258 6.258 pw_transfer 1439 11.6 0.062 0.062 5.804 5.804 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.547 5.547 apply_single 119 13.6 0.000 0.000 5.546 5.546 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.519 5.519 dbcsr_make_dense_low 5837 15.5 0.072 0.072 5.470 5.470 make_dense_data 5837 16.5 4.929 4.929 5.385 5.385 dbcsr_make_images_dense 3978 14.8 0.016 0.016 4.709 4.709 cp_fm_cholesky_decompose 22 10.9 4.672 4.672 4.672 4.672 fft_wrap_pw1pw2_140 487 13.2 0.418 0.418 4.638 4.638 dbcsr_dot_sd 1205 11.9 4.525 4.525 4.528 4.528 dbcsr_complete_redistribute 329 12.2 2.347 2.347 4.220 4.220 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.056 4.056 init_scf_run 11 5.9 0.003 0.003 4.019 4.019 scf_env_initial_rho_setup 11 6.9 0.002 0.002 4.016 4.016 pw_poisson_solve 119 10.3 1.046 1.046 4.001 4.001 cp_fm_cholesky_invert 11 10.9 3.787 3.787 3.787 3.787 dbcsr_copy 2102 12.0 0.250 0.250 3.696 3.696 qs_create_task_list 11 7.9 0.000 0.000 3.670 3.670 generate_qs_task_list 11 8.9 2.089 2.089 3.670 3.670 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.543 3.543 qs_ot_get_p 119 10.4 0.001 0.001 3.490 3.490 copy_dbcsr_to_fm 153 11.3 0.002 0.002 3.420 3.420 wfi_extrapolate 11 7.9 0.001 0.001 3.411 3.411 dbcsr_copy_into_existing 22 7.9 3.405 3.405 3.405 3.405 density_rs2pw 119 9.7 0.005 0.005 3.289 3.289 evaluate_core_matrix_traces 119 8.3 0.001 0.001 3.019 3.019 calculate_ptrace_kp 238 9.3 0.001 0.001 3.019 3.019 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.863 2.863 fft3d_s 1202 14.6 2.811 2.811 2.816 2.816 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.738 2.738 pw_integral_ab 119 11.3 2.709 2.709 2.709 2.709 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.627 2.627 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.515 2.515 dbcsr_data_release 279532 16.0 2.484 2.484 2.484 2.484 copy_fm_to_dbcsr 176 11.2 0.001 0.001 2.228 2.228 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 2.068 2.068 qs_vxc_create 119 10.3 0.001 0.001 2.012 2.012 xc_vxc_pw_create 119 11.3 1.000 1.000 2.010 2.010 qs_ot_p2m_diag 50 11.0 0.160 0.160 1.998 1.998 ------------------------------------------------------------------------------- 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 0.012 0.039 55.778 55.797 qs_mol_dyn_low 1 2.0 0.003 0.003 55.640 55.646 qs_forces 11 3.9 0.002 0.003 55.575 55.576 qs_energies 11 4.9 0.001 0.001 52.048 52.054 scf_env_do_scf 11 5.9 0.000 0.003 47.894 47.895 scf_env_do_scf_inner_loop 108 6.5 0.003 0.026 43.970 43.970 velocity_verlet 10 3.0 0.002 0.004 33.257 33.262 rebuild_ks_matrix 119 8.3 0.001 0.001 19.555 19.626 qs_ks_build_kohn_sham_matrix 119 9.3 0.017 0.021 19.554 19.625 qs_ks_update_qs_env 119 7.6 0.001 0.001 17.465 17.533 dbcsr_multiply_generic 2286 12.5 0.088 0.096 16.965 17.083 qs_rho_update_rho_low 119 7.7 0.001 0.001 15.535 15.546 calculate_rho_elec 119 8.7 0.033 0.035 15.534 15.546 sum_up_and_integrate 119 10.3 0.002 0.002 14.286 14.317 integrate_v_rspace 119 11.3 0.004 0.006 14.251 14.284 qs_scf_new_mos 108 7.5 0.001 0.001 14.173 14.266 qs_scf_loop_do_ot 108 8.5 0.001 0.001 14.173 14.265 ot_scf_mini 108 9.5 0.002 0.003 13.311 13.392 multiply_cannon 2286 13.5 0.153 0.167 11.901 12.187 multiply_cannon_loop 2286 14.5 0.105 0.110 11.064 11.366 grid_collocate_task_list 119 9.7 10.074 10.551 10.074 10.551 grid_integrate_task_list 119 12.3 9.083 9.277 9.083 9.277 mp_waitall_1 158411 16.6 8.721 9.229 8.721 9.229 ot_mini 108 10.5 0.001 0.002 7.722 7.816 multiply_cannon_metrocomm3 18288 15.5 0.047 0.056 6.538 6.971 density_rs2pw 119 9.7 0.005 0.007 4.953 5.443 pw_transfer 1439 11.6 0.071 0.077 4.955 5.028 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 4.805 4.875 multiply_cannon_multrec 18288 15.5 4.070 4.223 4.083 4.237 potential_pw2rs 119 12.3 0.007 0.007 4.103 4.117 fft_wrap_pw1pw2_140 487 13.2 0.749 0.829 4.002 4.106 qs_ot_get_derivative 108 11.5 0.001 0.001 3.957 4.040 init_scf_loop 11 6.9 0.000 0.000 3.904 3.905 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.681 3.753 apply_single 119 13.6 0.000 0.001 3.680 3.753 ot_diis_step 108 11.5 0.004 0.007 3.732 3.732 make_m2s 4572 13.5 0.052 0.055 3.216 3.302 fft3d_ps 1201 14.6 1.454 1.549 3.003 3.158 transfer_rs2pw 487 10.6 0.007 0.007 2.641 3.094 make_images 4572 14.5 0.129 0.136 2.827 2.915 init_scf_run 11 5.9 0.000 0.006 2.879 2.879 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.879 2.879 transfer_pw2rs 487 13.2 0.006 0.009 2.760 2.772 wfi_extrapolate 11 7.9 0.001 0.001 2.615 2.616 mp_waitany 9880 13.7 2.054 2.502 2.054 2.502 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.280 2.291 qs_ot_get_p 119 10.4 0.001 0.001 2.135 2.256 transfer_rs2pw_140 130 11.5 0.282 0.309 1.662 2.120 mp_alltoall_d11v 2130 13.8 1.380 1.781 1.380 1.781 prepare_preconditioner 11 7.9 0.000 0.000 1.710 1.730 make_preconditioner 11 8.9 0.000 0.000 1.710 1.730 mp_sum_l 11298 13.2 1.256 1.594 1.256 1.594 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.567 1.593 make_images_data 4572 15.5 0.040 0.045 1.434 1.568 transfer_pw2rs_140 130 13.9 0.475 0.517 1.423 1.454 mp_alltoall_z22v 1201 16.6 1.173 1.443 1.173 1.443 rs_gather_matrices 119 12.3 0.094 0.112 1.023 1.437 hybrid_alltoall_any 4725 16.4 0.074 0.198 1.246 1.404 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.210 1.269 mp_sum_d 4135 12.0 0.968 1.244 0.968 1.244 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.195 1.231 ------------------------------------------------------------------------------- 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=57.016000000000005, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.818, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.535, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=6.204, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.929, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.672, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=21.775999999999996, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=10.074, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=9.083, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.07, 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_waitall_1", label="mp_waitall_1", y=8.721, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.054, 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 0.034 0.034 111.034 111.034 qs_mol_dyn_low 1 2.0 0.003 0.003 110.390 110.390 qs_forces 11 3.9 0.001 0.001 110.347 110.347 qs_energies 11 4.9 0.001 0.001 102.763 102.763 scf_env_do_scf 11 5.9 0.002 0.002 89.973 89.973 scf_env_do_scf_inner_loop 96 6.5 0.013 0.013 72.162 72.162 velocity_verlet 10 3.0 0.002 0.002 71.195 71.195 rebuild_ks_matrix 107 8.3 0.001 0.001 33.218 33.218 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.217 33.217 qs_rho_update_rho_low 107 7.7 0.001 0.001 31.153 31.153 calculate_rho_elec 107 8.7 0.856 0.856 31.153 31.153 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.820 29.820 grid_collocate_task_list 107 9.7 27.148 27.148 27.148 27.148 sum_up_and_integrate 107 10.3 0.001 0.001 26.242 26.242 integrate_v_rspace 107 11.3 0.079 0.079 26.119 26.119 grid_integrate_task_list 107 12.3 24.291 24.291 24.291 24.291 dbcsr_multiply_generic 1966 12.4 0.137 0.137 18.297 18.297 qs_scf_new_mos 96 7.5 0.000 0.000 17.845 17.845 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.845 17.845 init_scf_loop 11 6.9 0.000 0.000 17.641 17.641 ot_scf_mini 96 9.5 0.002 0.002 16.688 16.688 prepare_preconditioner 11 7.9 0.000 0.000 13.672 13.672 make_preconditioner 11 8.9 0.000 0.000 13.672 13.672 make_full_inverse_cholesky 11 9.9 0.022 0.022 12.533 12.533 ot_mini 96 10.5 0.001 0.001 10.909 10.909 make_m2s 3932 13.4 0.039 0.039 9.581 9.581 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.914 6.914 qs_ot_get_derivative 96 11.5 0.001 0.001 5.767 5.767 pw_transfer 1295 11.6 0.056 0.056 5.741 5.741 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.522 5.522 init_scf_run 11 5.9 0.004 0.004 5.250 5.250 scf_env_initial_rho_setup 11 6.9 0.002 0.002 5.246 5.246 ot_diis_step 96 11.5 0.003 0.003 5.140 5.140 multiply_cannon 1966 13.4 0.151 0.151 5.097 5.097 make_images 3932 14.4 2.015 2.015 5.015 5.015 dbcsr_make_dense_low 4961 15.5 0.059 0.059 4.895 4.895 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.871 4.871 apply_single 107 13.6 0.000 0.000 4.871 4.871 make_dense_data 4961 16.5 4.436 4.436 4.824 4.824 fft_wrap_pw1pw2_140 439 13.2 0.523 0.523 4.749 4.749 multiply_cannon_loop 1966 14.4 0.057 0.057 4.700 4.700 wfi_extrapolate 11 7.9 0.001 0.001 4.649 4.649 multiply_cannon_multrec 1966 15.4 4.600 4.600 4.642 4.642 cp_fm_cholesky_decompose 22 10.9 4.350 4.350 4.350 4.350 dbcsr_make_images_dense 3386 14.7 0.014 0.014 4.309 4.309 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.261 4.261 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.076 4.076 cp_fm_cholesky_invert 11 10.9 3.962 3.962 3.962 3.962 qs_create_task_list 11 7.9 0.000 0.000 3.696 3.696 generate_qs_task_list 11 8.9 2.393 2.393 3.695 3.695 dbcsr_complete_redistribute 317 12.2 1.906 1.906 3.693 3.693 dbcsr_copy 1855 11.9 0.220 0.220 3.489 3.489 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.321 3.321 dbcsr_copy_into_existing 22 7.9 3.235 3.235 3.235 3.235 density_rs2pw 107 9.7 0.004 0.004 3.149 3.149 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.096 3.096 fft3d_s 1082 14.6 2.839 2.839 2.843 2.843 qs_ot_get_p 107 10.4 0.001 0.001 2.726 2.726 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.438 2.438 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.419 2.419 ------------------------------------------------------------------------------- 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 0.035 73.761 73.778 qs_mol_dyn_low 1 2.0 0.003 0.004 73.622 73.627 qs_forces 11 3.9 0.002 0.002 73.580 73.581 qs_energies 11 4.9 0.001 0.001 68.788 68.789 scf_env_do_scf 11 5.9 0.000 0.002 63.715 63.715 scf_env_do_scf_inner_loop 96 6.5 0.002 0.018 58.653 58.654 velocity_verlet 10 3.0 0.001 0.003 44.038 44.039 rebuild_ks_matrix 107 8.3 0.001 0.001 31.128 31.183 qs_ks_build_kohn_sham_matrix 107 9.3 0.015 0.017 31.127 31.182 qs_ks_update_qs_env 107 7.6 0.001 0.001 27.434 27.488 sum_up_and_integrate 107 10.3 0.002 0.002 26.946 26.975 integrate_v_rspace 107 11.3 0.004 0.004 26.925 26.955 qs_rho_update_rho_low 107 7.7 0.001 0.001 26.112 26.119 calculate_rho_elec 107 8.7 0.028 0.029 26.111 26.119 grid_integrate_task_list 107 12.3 22.693 23.271 22.693 23.271 grid_collocate_task_list 107 9.7 21.799 22.219 21.799 22.219 dbcsr_multiply_generic 1966 12.4 0.069 0.073 13.589 13.718 qs_scf_new_mos 96 7.5 0.001 0.001 10.883 10.927 qs_scf_loop_do_ot 96 8.5 0.001 0.001 10.882 10.926 ot_scf_mini 96 9.5 0.002 0.002 10.297 10.342 multiply_cannon 1966 13.4 0.124 0.138 10.111 10.314 multiply_cannon_loop 1966 14.4 0.099 0.110 9.569 9.742 mp_waitall_1 136719 16.5 7.647 8.191 7.647 8.191 multiply_cannon_metrocomm3 15728 15.4 0.046 0.051 5.933 6.339 ot_mini 96 10.5 0.001 0.001 6.103 6.154 init_scf_loop 11 6.9 0.000 0.000 5.045 5.045 density_rs2pw 107 9.7 0.005 0.006 3.903 4.447 init_scf_run 11 5.9 0.000 0.006 3.986 3.986 scf_env_initial_rho_setup 11 6.9 0.000 0.004 3.986 3.986 pw_transfer 1295 11.6 0.062 0.071 3.828 3.930 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.816 3.822 fft_wrap_pw1pw2 1081 12.6 0.008 0.010 3.704 3.795 wfi_extrapolate 11 7.9 0.001 0.001 3.628 3.628 multiply_cannon_multrec 15728 15.4 3.252 3.455 3.262 3.465 potential_pw2rs 107 12.3 0.005 0.006 3.336 3.355 fft_wrap_pw1pw2_140 439 13.2 0.561 0.620 3.189 3.333 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.109 3.196 apply_single 107 13.6 0.000 0.000 3.108 3.196 ot_diis_step 96 11.5 0.003 0.003 3.083 3.096 qs_ot_get_derivative 96 11.5 0.001 0.001 3.001 3.049 transfer_rs2pw 439 10.6 0.006 0.006 2.122 2.662 fft3d_ps 1081 14.6 1.247 1.400 2.425 2.576 make_m2s 3932 13.4 0.042 0.052 2.407 2.454 transfer_pw2rs 439 13.2 0.006 0.007 2.371 2.377 mp_waitany 8968 13.7 1.758 2.270 1.758 2.270 make_images 3932 14.4 0.103 0.108 2.106 2.154 transfer_rs2pw_140 118 11.5 0.163 0.182 1.314 1.859 mp_alltoall_d11v 1998 13.7 1.213 1.814 1.213 1.814 prepare_preconditioner 11 7.9 0.000 0.000 1.577 1.603 make_preconditioner 11 8.9 0.000 0.000 1.577 1.603 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.466 1.486 ------------------------------------------------------------------------------- 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=46.209, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.148, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.291, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.6, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.436, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.35, 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=16.611999999999988, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.799, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.693, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.252, 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=7.647, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.758, 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 0.231 0.231 132.877 132.877 qs_energies 1 2.0 0.000 0.000 132.047 132.047 scf_env_do_scf 1 3.0 0.000 0.000 130.853 130.853 qs_ks_update_qs_env 8 5.0 0.000 0.000 125.577 125.577 rebuild_ks_matrix 7 6.0 0.000 0.000 125.521 125.521 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 125.521 125.521 hfx_ks_matrix 7 8.0 0.000 0.000 116.537 116.537 integrate_four_center 7 9.0 1.648 1.648 116.511 116.511 integrate_four_center_main 7 10.0 0.549 0.549 102.747 102.747 integrate_four_center_bin 440 11.0 102.198 102.198 102.198 102.198 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 74.365 74.365 init_scf_loop 1 4.0 0.000 0.000 56.475 56.475 integrate_four_center_load 7 10.0 0.000 0.000 11.812 11.812 hfx_load_balance 1 11.0 0.003 0.003 11.811 11.811 hfx_load_balance_bin 1 12.0 5.967 5.967 5.967 5.967 hfx_load_balance_count 1 12.0 5.824 5.824 5.824 5.824 qs_vxc_create 14 8.0 0.000 0.000 3.300 3.300 xc_vxc_pw_create 14 9.0 0.117 0.117 3.299 3.299 ------------------------------------------------------------------------------- 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 0.202 0.224 128.245 128.258 qs_energies 1 2.0 0.000 0.000 127.858 127.868 scf_env_do_scf 1 3.0 0.000 0.000 127.501 127.506 qs_ks_update_qs_env 8 5.0 0.000 0.000 125.314 125.319 rebuild_ks_matrix 7 6.0 0.000 0.000 125.305 125.310 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 125.305 125.310 hfx_ks_matrix 7 8.0 0.000 0.000 119.749 119.754 integrate_four_center 7 9.0 0.052 0.341 119.740 119.745 integrate_four_center_main 7 10.0 0.003 0.003 100.636 107.182 integrate_four_center_bin 448 11.0 100.633 107.179 100.633 107.179 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 75.564 75.566 init_scf_loop 1 4.0 0.000 0.000 51.936 51.939 mp_sync 56 11.2 6.739 12.764 6.739 12.764 integrate_four_center_load 7 10.0 0.000 0.000 11.687 11.688 hfx_load_balance 1 11.0 0.001 0.001 11.687 11.688 hfx_load_balance_count 1 12.0 5.759 5.841 5.759 5.841 hfx_load_balance_bin 1 12.0 5.759 5.839 5.759 5.839 ------------------------------------------------------------------------------- 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=16.460000000000022, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=102.198, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.967, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.824, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.648, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.549, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.231, 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=9.097999999999999, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=100.633, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.759, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.759, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.052, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.202, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=6.739, 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 80.220 80.220 qs_energies 1 2.0 0.000 0.000 79.846 79.846 mp2_main 1 3.0 0.000 0.000 77.170 77.170 mp2_gpw_main 1 4.0 0.000 0.000 77.069 77.069 rpa_ri_compute_en 1 5.0 0.000 0.000 73.406 73.406 rpa_num_int 1 6.0 0.002 0.002 73.400 73.400 compute_mat_P_omega 1 7.0 0.005 0.005 63.574 63.574 compute_mat_P_omega_contract 10 8.0 8.805 8.805 63.378 63.378 dbt_total 2336 9.6 0.014 0.014 49.898 49.898 dbt_contract 787 11.0 0.043 0.043 42.625 42.625 dbt_tas_total 1149 12.2 0.249 0.249 41.433 41.433 dbt_tas_multiply 807 12.1 0.002 0.002 40.085 40.085 dbt_tas_dbm 807 14.1 0.003 0.003 33.473 33.473 dbm_multiply 807 16.1 33.465 33.465 33.465 33.465 dbt_tas_mm_1N 524 15.1 0.001 0.001 26.301 26.301 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 25.027 25.027 compute_mat_P_omega_calc_M_occ 250 9.0 8.833 8.833 17.175 17.175 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.745 6.745 dbt_copy 1103 10.7 0.160 0.160 5.906 5.906 dbt_tas_mm_2 251 15.0 0.001 0.001 5.748 5.748 compute_QP_energies 1 7.0 0.000 0.000 5.057 5.057 compute_self_energy_cubic_gw 1 8.0 0.054 0.054 5.056 5.056 contract_cubic_gw 21 9.0 0.000 0.000 4.086 4.086 dbt_tas_reserve_blocks_index 3261 14.3 0.481 0.481 3.721 3.721 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.656 3.656 dbm_reserve_blocks 3628 15.3 3.302 3.302 3.302 3.302 dbt_reserve_blocks_index 2280 13.1 0.052 0.052 2.766 2.766 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.715 2.715 scf_env_do_scf 1 3.0 0.000 0.000 2.566 2.566 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.566 2.566 dbt_crop 1042 12.0 1.420 1.420 2.420 2.420 dbt_tas_copy 574 11.4 1.360 1.360 2.419 2.419 convert_to_new_pgrid 2421 14.1 0.069 0.069 2.233 2.233 dbm_copy 1614 15.1 2.164 2.164 2.164 2.164 dbt_tas_reshape 367 15.0 0.042 0.042 2.156 2.156 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.014 2.014 compute_W_cubic_GW 10 7.0 0.003 0.003 1.920 1.920 dbt_reshape 278 11.9 1.048 1.048 1.901 1.901 get_2c_integrals 1 6.0 0.000 0.000 1.700 1.700 ------------------------------------------------------------------------------- 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 0.026 33.575 33.588 qs_energies 1 2.0 0.000 0.000 33.454 33.456 mp2_main 1 3.0 0.000 0.001 32.461 32.463 mp2_gpw_main 1 4.0 0.000 0.000 32.345 32.347 rpa_ri_compute_en 1 5.0 0.000 0.000 31.017 31.019 rpa_num_int 1 6.0 0.000 0.003 31.016 31.018 dbt_total 2336 9.6 0.015 0.016 27.513 27.522 compute_mat_P_omega 1 7.0 0.001 0.007 26.697 26.721 compute_mat_P_omega_contract 10 8.0 0.412 0.429 26.484 26.487 dbt_contract 787 11.0 0.039 0.040 20.261 20.267 dbt_tas_total 1149 12.2 0.081 0.089 17.917 17.918 dbt_tas_multiply 807 12.1 0.002 0.002 17.836 17.838 dbt_tas_dbm 807 14.1 0.003 0.003 12.703 12.713 dbm_multiply 807 16.1 10.164 10.809 10.164 10.809 compute_mat_P_omega_calc_M_occ 250 9.0 0.397 0.414 8.014 8.016 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.942 7.954 dbt_copy 1149 10.8 0.013 0.014 6.251 6.389 dbt_tas_mm_2 251 15.0 0.001 0.001 6.212 6.214 dbt_reshape 1136 11.8 2.657 2.855 5.958 6.099 mp_sync 8688 11.6 4.621 5.351 4.621 5.351 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.201 5.201 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.417 4.824 compute_QP_energies 1 7.0 0.000 0.000 2.734 2.736 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 2.733 2.734 mp_waitall_2 3812 15.3 2.412 2.666 2.412 2.666 dbt_communicate_buffer 1136 12.8 0.053 0.057 2.386 2.553 contract_cubic_gw 21 9.0 0.000 0.000 2.118 2.119 dbt_reserve_blocks_index 2887 13.1 0.066 0.071 1.743 1.882 dbt_reserve_blocks_index_array 2829 12.2 0.009 0.010 1.736 1.873 dbt_tas_reserve_blocks_index 3347 14.5 0.434 0.472 1.726 1.862 dbt_crop 1042 12.0 0.912 1.003 1.459 1.588 dbm_reserve_blocks 3752 15.4 1.384 1.499 1.384 1.499 mp2_ri_gpw_compute_in 1 5.0 0.003 0.004 1.287 1.288 dbt_tas_replicate 405 14.1 0.542 0.708 1.124 1.183 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.088 1.093 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.045 1.055 parallel_gemm_fm 105 8.4 0.000 0.000 0.965 0.973 parallel_gemm_fm_cosma 105 9.4 0.965 0.972 0.965 0.972 scf_env_do_scf 1 3.0 0.000 0.000 0.944 0.944 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.944 0.944 convert_to_new_pgrid 2421 14.1 0.026 0.028 0.808 0.932 dbm_copy 1608 15.1 0.775 0.899 0.775 0.899 mp_sum_l 6165 12.9 0.803 0.852 0.803 0.852 mp_max_i 2004 9.8 0.628 0.787 0.628 0.787 compute_W_cubic_GW 10 7.0 0.001 0.001 0.723 0.727 ------------------------------------------------------------------------------- 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=22.602999999999994, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=33.465, 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=8.833, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.805, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.302, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.164, 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=10.753, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.164, 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=0.397, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.412, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.384, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.775, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.657, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.621, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.412, 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 0.037 0.037 247.496 247.496 qs_forces 1 2.0 0.000 0.000 246.954 246.954 rebuild_ks_matrix 7 6.6 0.000 0.000 245.527 245.527 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 245.527 245.527 hfx_ks_matrix 7 8.6 0.000 0.000 243.575 243.575 hfx_ri_update_ks 7 9.6 0.000 0.000 202.808 202.808 hfx_ri_update_ks_Pmat 7 10.6 37.797 37.797 202.803 202.803 dbt_total 809 11.0 0.006 0.006 182.332 182.332 qs_energies 1 3.0 0.000 0.000 180.549 180.549 scf_env_do_scf 1 4.0 0.001 0.001 180.249 180.249 qs_ks_update_qs_env 8 6.0 0.000 0.000 179.173 179.173 dbt_contract 207 12.4 0.088 0.088 162.322 162.322 dbt_tas_total 343 13.7 1.557 1.557 160.328 160.328 dbt_tas_multiply 216 13.5 0.001 0.001 156.705 156.705 dbt_tas_dbm 216 15.5 0.001 0.001 145.111 145.111 dbm_multiply 216 17.5 145.108 145.108 145.108 145.108 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 139.379 139.379 dbt_tas_mm_2 91 16.5 0.001 0.001 130.323 130.323 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 111.820 111.820 init_scf_loop 2 5.0 0.000 0.000 68.426 68.426 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 66.359 66.359 hfx_ri_update_forces 1 7.0 1.638 1.638 40.764 40.764 hfx_ri_forces_Pmat_3c 1 8.0 4.726 4.726 23.010 23.010 dbt_copy 409 11.7 0.068 0.068 16.378 16.378 precalc_derivatives 1 8.0 2.271 2.271 13.945 13.945 dbt_reshape 132 13.2 7.087 7.087 11.320 11.320 dbt_tas_mm_3T 77 17.1 0.000 0.000 10.412 10.412 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.513 9.513 dbt_tas_reserve_blocks_index 1255 15.4 1.031 1.031 8.231 8.231 build_3c_derivatives 3 9.0 2.661 2.661 8.011 8.011 dbm_reserve_blocks 1397 16.3 7.432 7.432 7.432 7.432 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.387 7.387 dbt_reserve_blocks_index 818 14.4 0.114 0.114 6.429 6.429 dbt_reserve_blocks_index_array 795 13.4 0.007 0.007 6.314 6.314 dbt_crop 372 13.7 3.140 3.140 5.287 5.287 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 5.244 5.244 ------------------------------------------------------------------------------- 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 0.034 48.807 48.826 qs_forces 1 2.0 0.000 0.000 48.213 48.214 rebuild_ks_matrix 7 6.6 0.000 0.000 47.444 47.445 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 47.444 47.445 hfx_ks_matrix 7 8.6 0.000 0.000 46.409 46.417 dbt_total 809 11.0 0.006 0.006 41.403 41.410 dbt_contract 207 12.4 0.024 0.025 32.237 32.246 dbt_tas_total 343 13.7 0.087 0.213 28.387 28.391 dbt_tas_multiply 216 13.5 0.001 0.001 28.110 28.113 hfx_ri_update_ks 7 9.6 0.000 0.000 26.986 26.986 hfx_ri_update_ks_Pmat 7 10.6 1.225 1.270 26.981 26.983 qs_energies 1 3.0 0.000 0.000 25.437 25.437 scf_env_do_scf 1 4.0 0.000 0.001 25.288 25.289 qs_ks_update_qs_env 8 6.0 0.000 0.000 24.678 24.678 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 22.768 22.768 dbt_tas_dbm 216 15.5 0.001 0.001 21.635 21.639 dbm_multiply 216 17.5 19.757 20.296 19.757 20.296 hfx_ri_update_forces 1 7.0 0.057 0.061 19.423 19.431 hfx_ri_forces_Pmat_3c 1 8.0 0.159 0.168 14.736 14.736 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 14.581 14.581 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 12.453 12.453 init_scf_loop 2 5.0 0.000 0.000 10.707 10.707 dbt_tas_mm_2 91 16.5 0.001 0.001 10.153 10.155 dbt_copy 497 12.3 0.011 0.013 8.433 8.616 dbt_reshape 365 13.6 3.549 3.634 6.581 6.702 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.828 6.135 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.033 5.033 mp_sync 2769 12.9 4.390 4.979 4.390 4.979 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.124 4.210 precalc_derivatives 1 8.0 0.085 0.093 3.516 3.516 dbt_tas_reserve_blocks_index 1380 15.8 0.887 0.912 3.038 3.188 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.099 3.099 mp_waitall_2 1234 16.4 2.748 2.843 2.748 2.843 dbt_reserve_blocks_index 1051 14.7 0.104 0.111 2.532 2.658 dbt_reserve_blocks_index_array 1028 13.8 0.005 0.006 2.508 2.633 dbt_crop 372 13.7 1.706 1.746 2.478 2.566 dbm_reserve_blocks 1529 16.7 2.353 2.476 2.353 2.476 dbt_communicate_buffer 365 14.6 0.013 0.014 1.950 2.030 build_3c_derivatives 3 9.0 0.223 0.239 1.959 1.968 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.702 1.708 dbt_tas_replicate 149 15.4 0.658 0.686 1.648 1.688 convert_to_new_pgrid 648 15.5 0.035 0.090 1.347 1.657 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.562 1.567 dbm_copy 452 16.3 1.182 1.493 1.182 1.493 dbt_tas_copy 132 12.5 0.614 0.639 1.168 1.250 mp_sum_l 6385 13.7 1.040 1.144 1.040 1.144 ------------------------------------------------------------------------------- Plot: name="RI-HFX_H2O-32_timings_32omp", title="Timings of RI-HFX_H2O-32 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="rest", label="rest", y=45.34600000000003, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=145.108, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=37.797, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.432, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=7.087, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.726, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=14.625999999999998, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=19.757, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.225, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.353, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.549, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.159, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.39, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.748, 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 0.017 0.017 175.797 175.797 qs_energies 1 2.0 0.000 0.000 175.619 175.619 mp2_main 1 3.0 0.000 0.000 170.866 170.866 mp2_gpw_main 1 4.0 0.001 0.001 170.482 170.482 mp2_ri_gpw_compute_in 1 5.0 0.377 0.377 128.497 128.497 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 119.835 119.835 mp2_eri_3c_integrate_gpw 2656 7.0 0.014 0.014 92.870 92.870 integrate_v_rspace 2666 8.0 0.620 0.620 79.849 79.849 grid_integrate_task_list 2666 9.0 77.125 77.125 77.125 77.125 mp2_ri_gpw_compute_en 1 5.0 0.085 0.085 41.960 41.960 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.849 9.849 40.122 40.122 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.009 2.009 22.663 22.663 local_gemm 2080 8.0 20.655 20.655 20.655 20.655 dbcsr_multiply_generic 5322 8.0 0.184 0.184 20.549 20.549 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.526 20.526 pw_transfer 63872 10.6 0.976 0.976 11.761 11.761 calculate_wavefunction 2656 8.0 7.932 7.932 11.620 11.620 fft_wrap_pw1pw2 53228 11.4 0.106 0.106 10.560 10.560 multiply_cannon 5322 9.0 0.433 0.433 10.370 10.370 multiply_cannon_loop 5322 10.0 0.183 0.183 9.020 9.020 get_2c_integrals 1 6.0 0.000 0.000 8.250 8.250 make_m2s 10644 9.0 0.063 0.063 7.948 7.948 make_images 10644 10.0 3.197 3.197 7.631 7.631 fft_wrap_pw1pw2_20 21271 12.4 0.518 0.518 7.533 7.533 multiply_cannon_multrec 5322 11.0 7.461 7.461 7.502 7.502 compute_2c_integrals 1 7.0 0.005 0.005 7.404 7.404 compute_2c_integrals_loop_lm 1 8.0 0.013 0.013 7.391 7.391 mp2_eri_2c_integrate_gpw 1 9.0 0.798 0.798 7.377 7.377 fft3d_s 53229 13.4 6.508 6.508 6.550 6.550 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.442 2.442 6.326 6.326 mp2_ri_gpw_compute_en_ener 2080 7.0 5.792 5.792 5.792 5.792 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 4.393 4.393 scf_env_do_scf 1 3.0 0.000 0.000 4.340 4.340 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.340 4.340 potential_pw2rs 5322 10.0 0.145 0.145 3.981 3.981 ------------------------------------------------------------------------------- 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 0.039 37.652 37.672 qs_energies 1 2.0 0.000 0.000 37.494 37.495 mp2_main 1 3.0 0.000 0.001 35.645 35.646 mp2_gpw_main 1 4.0 0.001 0.001 35.556 35.557 mp2_ri_gpw_compute_en 1 5.0 0.248 0.256 18.773 19.105 mp2_ri_gpw_compute_en_RI_loop 1 6.0 3.590 3.676 17.696 17.701 mp2_ri_gpw_compute_in 1 5.0 0.042 0.043 16.701 16.954 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.484 15.738 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.497 13.773 integrate_v_rspace 93 8.1 0.097 0.105 13.372 13.649 grid_integrate_task_list 93 9.1 13.083 13.366 13.083 13.366 mp2_ri_gpw_compute_en_expansio 65 7.0 0.148 0.159 10.694 10.908 local_gemm 65 8.0 10.546 10.760 10.546 10.760 mp2_ri_gpw_compute_en_comm 30 7.0 0.146 0.158 2.978 3.286 mp_sendrecv_dm3 1860 8.0 2.061 2.459 2.061 2.459 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.683 1.839 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.667 1.821 scf_env_do_scf 1 3.0 0.000 0.000 1.717 1.718 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.717 1.718 get_2c_integrals 1 6.0 0.003 0.009 1.148 1.185 multiply_cannon 176 9.0 0.015 0.016 0.999 1.070 multiply_cannon_loop 176 10.0 0.002 0.002 0.944 1.012 fill_local_i_aL 1920 8.0 0.821 0.884 0.821 0.884 multiply_cannon_multrec 246 11.0 0.816 0.853 0.821 0.859 compute_2c_integrals 1 7.0 0.003 0.004 0.833 0.849 qs_scf_new_mos 10 5.0 0.000 0.000 0.783 0.787 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.755 0.767 mp2_eri_2c_integrate_gpw 1 9.0 0.196 0.200 0.753 0.766 pw_transfer 2120 10.5 0.039 0.040 0.737 0.754 ------------------------------------------------------------------------------- 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=52.77499999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=77.125, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=20.655, 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=9.849, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=7.932, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.461, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="fill_local_i_aL", label="fill_local_i_aL", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 Plot: name="RI-MP2_ammonia_timings_32mpi", title="Timings of RI-MP2_ammonia with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="rest", label="rest", y=6.735000000000003, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.083, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.546, 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=3.59, 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=0.816, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="fill_local_i_aL", label="fill_local_i_aL", y=0.821, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=2.061, 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 0.095 123.067 123.067 qs_energies 1 2.0 0.000 0.000 121.787 121.787 scf_env_do_scf 1 3.0 0.000 0.000 113.731 113.731 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 113.731 113.731 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.505 48.505 rebuild_ks_matrix 15 6.0 0.000 0.000 48.298 48.298 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.298 48.298 qs_scf_new_mos 15 5.0 0.000 0.000 41.702 41.702 eigensolver 15 6.0 0.001 0.001 34.017 34.017 qs_vxc_create 15 8.0 0.037 0.037 33.504 33.504 calculate_dispersion_nonloc 15 9.0 6.831 6.831 29.193 29.193 pw_transfer 1191 10.0 0.056 0.056 23.366 23.366 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 23.194 23.194 cp_fm_diag_elpa 15 7.0 0.000 0.000 21.543 21.543 cp_fm_diag_elpa_base 15 8.0 18.906 18.906 21.542 21.542 qs_rho_update_rho_low 16 5.0 0.000 0.000 19.845 19.845 calculate_rho_elec 16 6.0 0.215 0.215 19.845 19.845 grid_collocate_task_list 16 7.0 18.320 18.320 18.320 18.320 fft_wrap_pw1pw2_150 765 12.0 3.611 3.611 16.796 16.796 sum_up_and_integrate 15 8.0 0.000 0.000 13.596 13.596 integrate_v_rspace 15 9.0 0.021 0.021 13.586 13.586 grid_integrate_task_list 15 10.0 13.066 13.066 13.066 13.066 fft3d_s 1087 13.0 10.438 10.438 10.494 10.494 cp_fm_cholesky_restore 45 7.0 10.163 10.163 10.163 10.163 pw_scatter_s 585 13.1 7.330 7.330 7.330 7.330 fft_wrap_pw1pw2_200 197 12.3 0.800 0.800 6.131 6.131 copy_dbcsr_to_fm 16 5.9 0.000 0.000 5.528 5.528 dbcsr_complete_redistribute 46 8.3 2.250 2.250 5.466 5.466 gspace_mixing 14 5.0 0.171 0.171 4.951 4.951 cp_fm_upper_to_full 30 8.0 4.946 4.946 4.946 4.946 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.457 4.457 xc_vxc_pw_create 15 9.0 0.210 0.210 4.274 4.274 broyden_mixing 14 6.0 4.265 4.265 4.265 4.265 vdW_energy 15 10.0 4.227 4.227 4.227 4.227 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 3.324 3.324 init_scf_run 1 3.0 0.000 0.000 3.134 3.134 xc_pw_derive 90 11.0 0.001 0.001 2.824 2.824 calculate_dm_sparse 15 6.0 0.013 0.013 2.518 2.518 ------------------------------------------------------------------------------- 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 0.015 0.033 58.013 58.024 qs_energies 1 2.0 0.000 0.000 57.612 57.620 scf_env_do_scf 1 3.0 0.000 0.001 53.486 53.486 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 53.485 53.486 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.008 24.015 rebuild_ks_matrix 15 6.0 0.000 0.000 23.978 23.986 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 23.978 23.986 qs_rho_update_rho_low 16 5.0 0.000 0.000 18.146 18.149 calculate_rho_elec 16 6.0 0.007 0.007 18.146 18.149 grid_collocate_task_list 16 7.0 16.996 17.248 16.996 17.248 sum_up_and_integrate 15 8.0 0.000 0.001 13.570 13.612 integrate_v_rspace 15 9.0 0.001 0.001 13.560 13.605 grid_integrate_task_list 15 10.0 12.591 12.813 12.591 12.813 qs_scf_new_mos 15 5.0 0.000 0.000 11.826 11.869 eigensolver 15 6.0 0.001 0.002 10.832 10.853 qs_vxc_create 15 8.0 0.001 0.001 10.084 10.092 calculate_dispersion_nonloc 15 9.0 0.901 0.915 8.095 8.114 pw_transfer 1191 10.0 0.087 0.104 8.031 8.066 fft_wrap_pw1pw2 1086 11.0 0.013 0.015 7.868 7.920 cp_fm_diag_elpa 15 7.0 0.000 0.000 7.455 7.461 cp_fm_diag_elpa_base 15 8.0 7.326 7.341 7.453 7.459 fft3d_ps 1086 13.0 2.786 3.075 5.307 5.623 fft_wrap_pw1pw2_150 765 12.0 0.632 0.720 5.125 5.163 cp_fm_cholesky_restore 45 7.0 3.232 3.278 3.232 3.278 fft_wrap_pw1pw2_200 197 12.3 0.410 0.506 2.628 2.658 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.642 2.642 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.333 2.543 mp_alltoall_z22v 1086 15.0 1.962 2.541 1.962 2.541 xc_vxc_pw_create 15 9.0 0.015 0.021 1.988 2.023 x_to_yz 585 14.1 0.320 0.347 1.334 1.608 build_core_ppnl 1 5.0 1.442 1.573 1.442 1.573 yz_to_x 501 13.9 0.210 0.245 1.158 1.450 xc_pw_derive 90 11.0 0.001 0.002 1.360 1.433 vdW_energy 15 10.0 1.246 1.292 1.246 1.292 init_scf_run 1 3.0 0.000 0.001 1.258 1.259 density_rs2pw 16 7.0 0.001 0.001 1.011 1.204 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.165 1.166 ------------------------------------------------------------------------------- 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=52.17399999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=18.906, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=18.32, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.066, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.438, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.163, 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=15.082, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=7.326, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=16.996, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.591, 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=3.232, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.786, yerr=0.0 Running bench_dftb.inp with 1 threads and 32 ranks... done. Running bench_dftb.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/bench_dftb_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.080 0.080 294.007 294.007 qs_energies 1 2.0 0.000 0.000 293.868 293.868 ls_scf 1 3.0 0.000 0.000 292.644 292.644 ls_scf_main 1 4.0 0.002 0.002 283.392 283.392 density_matrix_trs4 11 5.0 0.014 0.014 188.903 188.903 arnoldi_extremal 12 6.1 0.000 0.000 100.862 100.862 arnoldi_normal_ev 12 7.1 0.031 0.031 100.862 100.862 build_subspace 23 8.1 0.080 0.080 99.123 99.123 dbcsr_matrix_vector_mult 652 9.0 0.211 0.211 98.967 98.967 dbcsr_matrix_vector_mult_local 652 10.0 97.136 97.136 97.145 97.145 ls_scf_dm_to_ks 11 5.0 0.000 0.000 89.220 89.220 matrix_ls_to_qs 11 6.0 0.000 0.000 85.880 85.880 dbcsr_multiply_generic 185 6.1 0.796 0.796 76.443 76.443 dbcsr_copy_into_existing 11 7.0 46.382 46.382 46.382 46.382 multiply_cannon 185 7.1 0.341 0.341 45.624 45.624 dbcsr_complete_redistribute 23 7.5 31.562 31.562 43.197 43.197 matrix_decluster 11 7.0 0.000 0.000 39.497 39.497 multiply_cannon_loop 185 8.1 0.254 0.254 33.153 33.153 make_m2s 370 7.1 0.038 0.038 26.073 26.073 make_images 370 8.1 10.757 10.757 24.425 24.425 multiply_cannon_multrec 185 9.1 23.963 23.963 24.178 24.178 dbcsr_finalize 646 7.5 0.251 0.251 15.522 15.522 dbcsr_merge_all 597 8.5 2.343 2.343 14.294 14.294 setup_rec_index_2d 370 8.1 11.987 11.987 11.987 11.987 dbcsr_sort_indices 1103 9.9 11.451 11.451 11.451 11.451 tree_to_linear_d 110 9.4 10.560 10.560 10.560 10.560 quick_finalize 395 10.0 0.355 0.355 9.894 9.894 dbcsr_special_finalize 370 9.1 0.002 0.002 9.157 9.157 calculate_norms 370 9.1 8.721 8.721 8.721 8.721 ls_scf_init_scf 1 4.0 0.000 0.000 8.583 8.583 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.246 8.246 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.602 7.602 ------------------------------------------------------------------------------- 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 0.025 65.838 65.851 qs_energies 1 2.0 0.000 0.000 65.726 65.727 ls_scf 1 3.0 0.000 0.000 65.676 65.677 ls_scf_main 1 4.0 0.001 0.012 63.179 63.184 density_matrix_trs4 11 5.0 0.006 0.022 60.705 60.782 dbcsr_multiply_generic 185 6.1 0.056 0.070 57.688 58.057 multiply_cannon 185 7.1 0.033 0.036 47.458 48.750 multiply_cannon_loop 185 8.1 0.101 0.121 45.192 46.424 multiply_cannon_multrec 1480 9.1 27.385 30.628 27.615 30.850 mp_waitall_1 11936 10.3 15.832 19.657 15.832 19.657 multiply_cannon_metrocomm3 1480 9.1 0.014 0.017 12.048 16.596 make_m2s 370 7.1 0.034 0.037 6.637 6.672 make_images 370 8.1 0.616 0.649 6.514 6.549 calculate_norms 2960 9.1 4.327 5.011 4.327 5.011 mp_sum_l 1199 5.3 2.761 3.673 2.761 3.673 make_images_data 370 9.1 0.010 0.013 2.992 3.244 hybrid_alltoall_any 393 9.9 0.227 1.391 2.565 2.853 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.957 2.736 arnoldi_extremal 12 6.1 0.000 0.001 2.345 2.364 arnoldi_normal_ev 12 7.1 0.001 0.007 2.345 2.364 multiply_cannon_metrocomm1 1480 9.1 0.006 0.007 1.066 2.296 build_subspace 23 8.1 0.018 0.023 2.254 2.256 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.124 2.179 dbcsr_complete_redistribute 23 7.5 1.164 1.240 1.936 2.051 dbcsr_matrix_vector_mult 652 9.0 0.013 0.047 1.960 2.033 matrix_ls_to_qs 11 6.0 0.000 0.000 1.854 1.973 ls_scf_init_scf 1 4.0 0.000 0.000 1.910 1.911 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.886 1.890 make_images_pack 370 9.1 1.614 1.870 1.617 1.874 matrix_decluster 11 7.0 0.000 0.000 1.734 1.851 dbcsr_matrix_vector_mult_local 652 10.0 1.618 1.716 1.619 1.718 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.706 1.708 buffer_matrices_ensure_size 370 8.1 1.226 1.430 1.226 1.430 ------------------------------------------------------------------------------- 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=74.256, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=97.136, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=46.382, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=31.562, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.963, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.987, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.721, 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=12.75099999999999, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.618, 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=1.164, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=27.385, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="setup_rec_index_2d", label="setup_rec_index_2d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.327, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=15.832, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.761, 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 71.085 71.085 lib_test 1 2.0 0.000 0.000 71.074 71.074 dbcsr_run_tests 3 3.0 0.002 0.002 71.073 71.073 test_multiplies_multiproc 3 4.0 0.001 0.001 55.514 55.514 dbcsr_redistribute 9 5.0 35.746 35.746 37.749 37.749 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.291 16.291 dbcsr_make_random_matrix 9 4.0 12.505 12.505 15.450 15.450 multiply_cannon 9 6.0 0.002 0.002 11.535 11.535 multiply_cannon_loop 9 7.0 0.013 0.013 11.178 11.178 multiply_cannon_multrec 9 8.0 11.164 11.164 11.165 11.165 dbcsr_finalize 27 5.7 0.003 0.003 5.449 5.449 dbcsr_merge_all 18 6.5 1.967 1.967 4.727 4.727 dbcsr_data_release 975 7.6 2.752 2.752 2.752 2.752 tree_to_linear_d 9 7.0 1.844 1.844 1.844 1.844 make_m2s 18 6.0 0.001 0.001 1.664 1.664 mp_alltoall_d11v 27 6.0 1.635 1.635 1.635 1.635 make_images 18 7.0 0.595 0.595 1.615 1.615 ------------------------------------------------------------------------------- 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 18.870 18.876 lib_test 1 2.0 0.000 0.000 18.636 18.655 dbcsr_run_tests 3 3.0 0.000 0.001 18.623 18.642 test_multiplies_multiproc 3 4.0 0.000 0.002 17.755 17.809 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.349 16.438 multiply_cannon 9 6.0 0.002 0.002 14.296 14.819 multiply_cannon_loop 9 7.0 0.002 0.002 14.025 14.571 multiply_cannon_multrec 72 8.0 10.619 10.929 10.620 10.929 mp_waitall_1 576 9.2 3.721 4.396 3.721 4.396 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 3.275 4.012 mp_sum_l 470 2.5 0.898 1.572 0.898 1.572 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.872 1.547 dbcsr_make_random_matrix 9 4.0 0.670 0.702 0.801 0.817 make_m2s 18 6.0 0.001 0.001 0.688 0.729 make_images 18 7.0 0.021 0.021 0.685 0.725 dbcsr_data_release 444 7.6 0.581 0.650 0.581 0.650 dbcsr_finalize 27 5.7 0.000 0.000 0.509 0.589 dbcsr_redistribute 9 5.0 0.248 0.292 0.551 0.578 dbcsr_destroy 111 5.9 0.002 0.054 0.509 0.573 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.126 0.561 dbcsr_merge_all 18 6.5 0.078 0.098 0.435 0.503 make_images_data 18 8.0 0.001 0.001 0.359 0.423 hybrid_alltoall_any 18 9.0 0.036 0.147 0.307 0.392 ------------------------------------------------------------------------------- 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=6.950999999999979, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.746, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.505, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.164, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.752, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.967, 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=2.0550000000000033, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.248, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.67, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.619, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.581, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.078, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.898, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.721, 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 0.063 0.063 135.629 135.629 qs_mol_dyn_low 1 2.0 0.003 0.003 134.223 134.223 velocity_verlet 5 3.0 0.004 0.004 109.989 109.989 qmmm_el_coupling 6 3.8 0.000 0.000 85.862 85.862 qmmm_elec_with_gaussian 6 4.8 0.031 0.031 85.858 85.858 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 84.870 84.870 qmmm_elec_gaussian_low_G 6 6.8 83.971 83.971 83.971 83.971 qs_forces 6 3.8 0.001 0.001 39.359 39.359 qs_energies 6 4.8 0.000 0.000 34.870 34.870 scf_env_do_scf 6 5.8 0.001 0.001 32.447 32.447 rebuild_ks_matrix 45 8.4 0.000 0.000 28.439 28.439 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 28.439 28.439 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 28.184 28.184 qs_ks_update_qs_env 45 7.8 0.000 0.000 24.385 24.385 pw_transfer 966 12.3 0.053 0.053 17.459 17.459 fft_wrap_pw1pw2 801 13.6 0.006 0.006 17.216 17.216 fft_wrap_pw1pw2_150 507 15.2 2.672 2.672 16.795 16.795 qs_vxc_create 45 10.4 0.001 0.001 14.631 14.631 xc_vxc_pw_create 45 11.4 0.711 0.711 14.630 14.630 xc_pw_derive 270 13.4 0.002 0.002 9.529 9.529 xc_rho_set_and_dset_create 45 12.4 1.235 1.235 8.114 8.114 fft3d_s 802 15.6 7.588 7.588 7.596 7.596 pw_integral_ab 2539 7.4 7.560 7.560 7.560 7.560 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.245 7.245 calculate_rho_elec 45 8.9 0.650 0.650 7.245 7.245 pw_scatter_s 429 15.8 5.861 5.861 5.861 5.861 xc_pw_divergence 45 12.4 0.001 0.001 5.741 5.741 qmmm_forces 6 3.8 0.003 0.003 5.682 5.682 qs_ks_ddapc 45 10.4 0.001 0.001 5.384 5.384 qmmm_forces_with_gaussian 6 4.8 0.041 0.041 5.278 5.278 init_scf_loop 6 6.8 0.000 0.000 4.258 4.258 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.155 4.155 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 4.072 4.072 pw_poisson_solve 51 9.9 0.970 0.970 3.926 3.926 cp_ddapc_apply_CD 45 11.4 0.006 0.006 3.694 3.694 qmmm_forces_gaussian_low_G 6 6.8 3.466 3.466 3.466 3.466 density_rs2pw 45 9.9 0.002 0.002 3.403 3.403 grid_collocate_task_list 45 9.9 3.192 3.192 3.192 3.192 sum_up_and_integrate 45 10.4 0.000 0.000 3.085 3.085 integrate_v_rspace 45 11.4 0.006 0.006 3.045 3.045 ------------------------------------------------------------------------------- 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 0.050 60.603 60.616 qs_mol_dyn_low 1 2.0 0.003 0.003 59.509 59.570 qs_forces 6 3.8 0.001 0.001 45.071 45.072 qs_energies 6 4.8 0.000 0.000 43.200 43.200 scf_env_do_scf 6 5.8 0.000 0.001 42.217 42.217 scf_env_do_scf_inner_loop 113 6.2 0.002 0.020 40.535 40.536 rebuild_ks_matrix 119 8.1 0.000 0.000 29.727 29.737 qs_ks_build_kohn_sham_matrix 119 9.1 0.016 0.018 29.726 29.737 qs_ks_update_qs_env 119 7.3 0.001 0.001 28.149 28.160 velocity_verlet 5 3.0 0.002 0.004 23.461 23.464 pw_transfer 2446 12.3 0.163 0.185 21.534 22.122 fft_wrap_pw1pw2 2059 13.4 0.025 0.029 21.100 21.689 fft_wrap_pw1pw2_150 1321 14.9 3.468 3.802 20.459 21.053 qs_vxc_create 119 10.1 0.002 0.002 16.291 16.305 xc_vxc_pw_create 119 11.1 0.158 0.213 16.289 16.303 fft3d_ps 2059 15.4 8.228 9.093 13.693 14.837 xc_pw_derive 714 13.1 0.011 0.012 12.547 12.817 qs_rho_update_rho_low 119 7.3 0.001 0.001 11.473 11.479 calculate_rho_elec 119 8.3 0.050 0.058 11.473 11.479 sum_up_and_integrate 119 10.1 0.002 0.002 9.684 9.700 integrate_v_rspace 119 11.1 0.003 0.004 9.633 9.656 xc_pw_divergence 119 12.1 0.005 0.006 8.222 8.450 xc_rho_set_and_dset_create 119 12.1 0.346 0.436 7.651 7.886 qmmm_forces 6 3.8 0.002 0.006 7.261 7.261 qmmm_forces_with_gaussian 6 4.8 0.006 0.008 6.969 7.103 density_rs2pw 119 9.3 0.007 0.008 6.857 7.091 qmmm_el_coupling 6 3.8 0.000 0.000 6.341 6.415 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 6.339 6.413 potential_pw2rs 119 12.1 0.006 0.007 5.955 5.966 mp_alltoall_z22v 2059 17.4 3.994 4.930 3.994 4.930 grid_collocate_task_list 119 9.3 4.442 4.656 4.442 4.656 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.833 3.882 transfer_pw2rs 500 12.8 0.006 0.007 3.868 3.882 grid_integrate_task_list 119 12.1 3.405 3.605 3.405 3.605 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.322 3.425 x_to_yz 1095 16.8 0.777 0.877 2.919 3.306 qmmm_forces_gaussian_low_G 6 6.8 3.152 3.202 3.152 3.202 transfer_rs2pw 488 10.2 0.007 0.008 2.898 3.167 mp_waitany 4028 12.8 2.653 3.111 2.653 3.111 yz_to_x 964 16.0 0.630 0.795 2.481 3.058 qs_scf_new_mos 113 7.2 0.000 0.001 2.907 2.912 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.907 2.912 qmmm_elec_gaussian_low_G 6 6.8 2.731 2.834 2.731 2.834 ot_scf_mini 113 9.2 0.001 0.001 2.817 2.828 transfer_pw2rs_150 125 13.9 0.939 1.006 2.619 2.669 pw_restrict_s3 18 5.8 1.352 1.412 2.555 2.657 pw_gather_p 964 15.0 2.138 2.582 2.138 2.582 qs_ks_ddapc 119 10.1 0.003 0.003 2.314 2.396 transfer_rs2pw_150 125 11.2 0.685 0.820 2.046 2.312 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.168 2.241 pw_prolongate_s3 18 6.8 1.156 1.187 2.168 2.241 dbcsr_multiply_generic 2588 12.3 0.059 0.063 1.856 1.888 pw_scatter_p 1095 15.8 1.734 1.858 1.734 1.858 init_scf_loop 6 6.8 0.000 0.000 1.678 1.678 pw_integral_ab 2761 7.7 1.301 1.389 1.535 1.643 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.597 1.598 qs_ot_get_p 119 10.2 0.000 0.000 1.401 1.407 mp_sum_dm3 33 5.7 1.338 1.386 1.338 1.386 ------------------------------------------------------------------------------- Plot: name="MQAE_single_node_timings_32omp", title="Timings of MQAE_single_node with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32omp", name="rest", label="rest", y=21.31899999999999, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=83.971, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.588, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=7.56, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.861, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.466, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.192, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=2.672, 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=29.881999999999998, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.731, 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=1.301, 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=3.152, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.442, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=3.468, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=8.228, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.994, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.405, yerr=0.0 Summary: Performance test took 34 minutes. Status: OK Removing intermediate container bb962511c295 ---> f0fac396945a Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 03bc0ce5969f Removing intermediate container 03bc0ce5969f ---> 3bcc1d42128c Step 42/42 : ENTRYPOINT [] ---> Running in 4d643cdf4fad Removing intermediate container 4d643cdf4fad ---> 0c88d91af120 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 0c88d91af120 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: 2023-08-25 21:43:25+00:00