StartDate: 2022-11-19 19:05:55+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: e284e850b2d0abdb1c432bd76ee473a3cd90b70c CommitTime: 2022-11-19 19:24:34 +0100 CommitAuthor: Matthias Krack CommitSubject: Rename arch files Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=e284e850b2d0abdb1c432bd76ee473a3cd90b70c Sending build context to Docker daemon 365.4MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu e96e057aae67: Already exists Digest: sha256:4b1d0c4a2d2aaf63b37111f34eb9fa89fa1bf53dd6e4ca954d47caebca4005c2 Status: Downloaded newer image for ubuntu:22.04 ---> a8780b506fa4 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 456d88508063 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 196acfd778fb Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 1c5721a94525 Step 5/42 : RUN mkdir scripts ---> Using cache ---> aa1c7bdf0e90 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 ---> 8641bd388b4f Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 13fd585790c3 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> cac01e5ed808 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 4d68dfb96b0f Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> d498842004b1 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 653a132d5aa7 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 932f838464d3 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 1801374ed881 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> a8995b19ba48 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> e525eee1ff8e Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> f4f361a003dd Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 8b63f00f04f8 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 4a094f4a2f76 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 3b3f84e762a7 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 6ec03878598d Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> e19cd3bb6f22 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 5c3d211ed962 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 765ecf06ceba Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 85d65dea1e16 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 6e219fcd9e8c Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 3e6ff79bc60b Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 564abc7b20f4 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> ea8d38dfdbea Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> adce1f11e400 Step 30/42 : COPY ./Makefile . ---> Using cache ---> b337c5ad22d0 Step 31/42 : COPY ./src ./src ---> Using cache ---> 20abe044a46d Step 32/42 : COPY ./exts ./exts ---> Using cache ---> c3cfc79e57e7 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> a873e6316ba3 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 ) && ( [ ! -f ./exe/local/cp2k.psmp ] || ldd ./exe/local/cp2k.psmp | grep -q libmpi )" ---> Running in 6b3bc07fea97 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 6b3bc07fea97 ---> 9b2556f2e868 Step 35/42 : COPY ./data ./data ---> 10c55eb2fdfd Step 36/42 : COPY ./tests ./tests ---> 6b03aa6ce06e Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> e2abd1f1434e Step 38/42 : COPY ./benchmarks ./benchmarks ---> 91a6af5a026b Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 7aa7e0f88a11 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 5fbf070fed6d ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 60 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 0.028 0.028 86.478 86.478 qs_mol_dyn_low 1 2.0 0.003 0.003 85.864 85.864 qs_forces 11 3.9 0.001 0.001 85.825 85.825 qs_energies 11 4.9 0.001 0.001 79.818 79.818 scf_env_do_scf 11 5.9 0.001 0.001 69.231 69.231 velocity_verlet 10 3.0 0.002 0.002 56.174 56.174 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 52.878 52.878 rebuild_ks_matrix 119 8.3 0.001 0.001 20.036 20.036 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.036 20.036 dbcsr_multiply_generic 2286 12.5 0.164 0.164 19.655 19.655 qs_scf_new_mos 108 7.5 0.001 0.001 19.300 19.300 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.299 19.299 qs_rho_update_rho_low 119 7.7 0.000 0.000 19.008 19.008 calculate_rho_elec 119 8.7 0.949 0.949 19.007 19.007 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.325 18.325 ot_scf_mini 108 9.5 0.002 0.002 17.967 17.967 init_scf_loop 11 6.9 0.000 0.000 16.206 16.206 grid_collocate_task_list 119 9.7 14.745 14.745 14.745 14.745 prepare_preconditioner 11 7.9 0.000 0.000 13.741 13.741 make_preconditioner 11 8.9 0.000 0.000 13.741 13.741 sum_up_and_integrate 119 10.3 0.500 0.500 12.827 12.827 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.585 12.585 integrate_v_rspace 119 11.3 0.086 0.086 12.326 12.326 ot_mini 108 10.5 0.001 0.001 11.686 11.686 make_m2s 4572 13.5 0.045 0.045 10.901 10.901 grid_integrate_task_list 119 12.3 10.440 10.440 10.440 10.440 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.127 6.127 qs_ot_get_derivative 108 11.5 0.001 0.001 6.089 6.089 dbcsr_make_dense_low 5837 15.5 0.067 0.067 5.829 5.829 pw_transfer 1439 11.6 0.063 0.063 5.805 5.805 make_dense_data 5837 16.5 5.129 5.129 5.749 5.749 ot_diis_step 108 11.5 0.004 0.004 5.594 5.594 fft_wrap_pw1pw2 1201 12.6 0.007 0.007 5.588 5.588 make_images 4572 14.5 2.127 2.127 5.465 5.465 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.149 5.149 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.102 5.102 apply_single 119 13.6 0.000 0.000 5.102 5.102 fft_wrap_pw1pw2_140 487 13.2 0.435 0.435 4.781 4.781 multiply_cannon 2286 13.5 0.174 0.174 4.659 4.659 cp_fm_cholesky_decompose 22 10.9 4.339 4.339 4.339 4.339 multiply_cannon_loop 2286 14.5 0.050 0.050 4.202 4.202 multiply_cannon_multrec 2286 15.5 4.102 4.102 4.151 4.151 cp_fm_cholesky_invert 11 10.9 4.080 4.080 4.080 4.080 init_scf_run 11 5.9 0.002 0.002 3.840 3.840 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.838 3.838 dbcsr_copy 2102 12.0 0.252 0.252 3.639 3.639 dbcsr_complete_redistribute 329 12.2 1.885 1.885 3.627 3.627 wfi_extrapolate 11 7.9 0.001 0.001 3.360 3.360 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.351 3.351 density_rs2pw 119 9.7 0.004 0.004 3.313 3.313 dbcsr_copy_into_existing 22 7.9 3.312 3.312 3.312 3.312 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.249 3.249 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.960 2.960 qs_create_task_list 11 7.9 0.000 0.000 2.878 2.878 generate_qs_task_list 11 8.9 1.970 1.970 2.878 2.878 qs_ot_get_p 119 10.4 0.001 0.001 2.847 2.847 fft3d_s 1202 14.6 2.764 2.764 2.768 2.768 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.655 2.655 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.473 2.473 dbcsr_data_release 279534 16.0 2.375 2.375 2.375 2.375 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.309 2.309 pw_poisson_solve 119 10.3 0.328 0.328 1.991 1.991 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.912 1.912 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.912 1.912 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.894 1.894 potential_pw2rs 119 12.3 0.044 0.044 1.800 1.800 cp_fm_upper_to_full 72 14.2 1.769 1.769 1.769 1.769 dbcsr_finalize 5186 13.8 0.104 0.104 1.761 1.761 ------------------------------------------------------------------------------- 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 0.007 0.022 42.723 42.733 qs_mol_dyn_low 1 2.0 0.003 0.004 42.616 42.620 qs_forces 11 3.9 0.001 0.001 42.573 42.574 qs_energies 11 4.9 0.001 0.001 39.789 39.791 scf_env_do_scf 11 5.9 0.000 0.002 36.493 36.494 scf_env_do_scf_inner_loop 108 6.5 0.003 0.018 33.573 33.574 velocity_verlet 10 3.0 0.002 0.003 25.252 25.253 rebuild_ks_matrix 119 8.3 0.000 0.001 15.525 15.616 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.018 15.524 15.616 qs_ks_update_qs_env 119 7.6 0.001 0.001 13.829 13.914 dbcsr_multiply_generic 2286 12.5 0.072 0.075 12.536 12.749 qs_rho_update_rho_low 119 7.7 0.001 0.001 12.456 12.462 calculate_rho_elec 119 8.7 0.030 0.031 12.456 12.462 sum_up_and_integrate 119 10.3 0.031 0.033 11.573 11.588 integrate_v_rspace 119 11.3 0.004 0.006 11.543 11.556 qs_scf_new_mos 108 7.5 0.001 0.001 9.904 9.990 qs_scf_loop_do_ot 108 8.5 0.001 0.001 9.903 9.989 multiply_cannon 2286 13.5 0.143 0.151 9.181 9.595 ot_scf_mini 108 9.5 0.002 0.002 9.290 9.375 grid_collocate_task_list 119 9.7 8.861 9.167 8.861 9.167 multiply_cannon_loop 2286 14.5 0.093 0.097 8.693 9.149 grid_integrate_task_list 119 12.3 7.961 8.165 7.961 8.165 mp_waitall_1 169478 16.3 7.602 8.109 7.602 8.109 multiply_cannon_metrocomm3 18288 15.5 0.036 0.037 4.980 5.628 ot_mini 108 10.5 0.001 0.001 5.352 5.442 rs_pw_transfer 974 11.9 0.010 0.015 3.947 4.323 density_rs2pw 119 9.7 0.005 0.006 3.271 3.669 pw_transfer 1439 11.6 0.098 0.109 3.274 3.309 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.109 3.147 potential_pw2rs 119 12.3 0.006 0.007 3.084 3.092 multiply_cannon_multrec 18288 15.5 2.908 2.992 2.918 3.002 init_scf_loop 11 6.9 0.000 0.000 2.907 2.907 qs_ot_get_derivative 108 11.5 0.001 0.001 2.760 2.844 fft_wrap_pw1pw2_140 487 13.2 0.269 0.290 2.659 2.710 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.502 2.621 apply_single 119 13.6 0.000 0.000 2.502 2.621 ot_diis_step 108 11.5 0.003 0.003 2.571 2.571 init_scf_run 11 5.9 0.000 0.004 2.321 2.322 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.321 2.321 make_m2s 4572 13.5 0.045 0.051 2.230 2.288 fft3d_ps 1201 14.6 1.210 1.281 2.226 2.281 wfi_extrapolate 11 7.9 0.001 0.001 2.100 2.100 make_images 4572 14.5 0.115 0.119 1.913 1.969 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.831 1.843 mp_waitany 9880 13.7 1.219 1.618 1.219 1.618 qs_ot_get_p 119 10.4 0.001 0.001 1.234 1.326 rs_pw_transfer_RS2PW_140 130 11.5 0.191 0.222 0.903 1.292 rs_pw_transfer_PW2RS_140 130 13.9 0.368 0.400 1.188 1.213 make_images_data 4572 15.5 0.035 0.042 1.067 1.176 prepare_preconditioner 11 7.9 0.000 0.000 1.132 1.153 make_preconditioner 11 8.9 0.000 0.000 1.132 1.153 hybrid_alltoall_any 4725 16.4 0.062 0.171 0.949 1.044 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.026 1.042 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.931 0.992 mp_sum_l 11218 13.2 0.694 0.966 0.694 0.966 mp_alltoall_d11v 2130 13.8 0.687 0.962 0.687 0.962 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.853 0.928 multiply_cannon_metrocomm1 18288 15.5 0.018 0.021 0.507 0.920 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.879 0.882 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.841 0.870 ------------------------------------------------------------------------------- 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=47.723, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.745, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.44, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.129, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.339, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.102, 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=14.171999999999993, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.861, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=7.961, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.908, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.602, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.219, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.031 0.031 109.000 109.000 qs_mol_dyn_low 1 2.0 0.003 0.003 108.367 108.367 qs_forces 11 3.9 0.001 0.001 108.328 108.328 qs_energies 11 4.9 0.001 0.001 100.791 100.791 scf_env_do_scf 11 5.9 0.001 0.001 88.365 88.365 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 70.440 70.440 velocity_verlet 10 3.0 0.002 0.002 69.893 69.893 rebuild_ks_matrix 107 8.3 0.001 0.001 32.788 32.788 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 32.787 32.787 qs_rho_update_rho_low 107 7.7 0.001 0.001 31.308 31.308 calculate_rho_elec 107 8.7 0.853 0.853 31.307 31.307 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.453 29.453 grid_collocate_task_list 107 9.7 27.115 27.115 27.115 27.115 sum_up_and_integrate 107 10.3 0.451 0.451 26.501 26.501 integrate_v_rspace 107 11.3 0.081 0.081 26.049 26.049 grid_integrate_task_list 107 12.3 24.295 24.295 24.295 24.295 init_scf_loop 11 6.9 0.000 0.000 17.760 17.760 dbcsr_multiply_generic 1966 12.4 0.134 0.134 16.520 16.520 qs_scf_new_mos 96 7.5 0.000 0.000 16.344 16.344 qs_scf_loop_do_ot 96 8.5 0.001 0.001 16.344 16.344 ot_scf_mini 96 9.5 0.002 0.002 15.195 15.195 prepare_preconditioner 11 7.9 0.000 0.000 13.758 13.758 make_preconditioner 11 8.9 0.000 0.000 13.758 13.758 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.586 12.586 ot_mini 96 10.5 0.001 0.001 9.740 9.740 make_m2s 3932 13.4 0.039 0.039 9.114 9.114 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.489 6.489 pw_transfer 1295 11.6 0.056 0.056 5.636 5.636 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.457 5.457 init_scf_run 11 5.9 0.002 0.002 5.304 5.304 scf_env_initial_rho_setup 11 6.9 0.000 0.000 5.302 5.302 qs_ot_get_derivative 96 11.5 0.001 0.001 5.221 5.221 dbcsr_make_dense_low 4961 15.5 0.056 0.056 4.956 4.956 make_dense_data 4961 16.5 4.348 4.348 4.888 4.888 wfi_extrapolate 11 7.9 0.001 0.001 4.704 4.704 fft_wrap_pw1pw2_140 439 13.2 0.474 0.474 4.640 4.640 make_images 3932 14.4 1.852 1.852 4.543 4.543 ot_diis_step 96 11.5 0.003 0.003 4.516 4.516 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.314 4.314 cp_fm_cholesky_decompose 22 10.9 4.275 4.275 4.275 4.275 multiply_cannon 1966 13.4 0.150 0.150 4.231 4.231 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.192 4.192 apply_single 107 13.6 0.000 0.000 4.192 4.192 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.184 4.184 cp_fm_cholesky_invert 11 10.9 4.106 4.106 4.106 4.106 multiply_cannon_loop 1966 14.4 0.029 0.029 3.840 3.840 multiply_cannon_multrec 1966 15.4 3.764 3.764 3.810 3.810 dbcsr_complete_redistribute 317 12.2 1.879 1.879 3.768 3.768 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.709 3.709 dbcsr_copy 1855 11.9 0.216 0.216 3.473 3.473 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.351 3.351 density_rs2pw 107 9.7 0.004 0.004 3.339 3.339 qs_create_task_list 11 7.9 0.000 0.000 3.336 3.336 generate_qs_task_list 11 8.9 2.399 2.399 3.336 3.336 dbcsr_copy_into_existing 22 7.9 3.229 3.229 3.229 3.229 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.040 3.040 fft3d_s 1082 14.6 2.689 2.689 2.693 2.693 qs_ot_get_p 107 10.4 0.001 0.001 2.613 2.613 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.377 2.377 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.330 2.330 ------------------------------------------------------------------------------- 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 0.007 0.021 70.253 70.264 qs_mol_dyn_low 1 2.0 0.003 0.003 70.155 70.160 qs_forces 11 3.9 0.001 0.001 70.115 70.115 qs_energies 11 4.9 0.001 0.001 65.433 65.435 scf_env_do_scf 11 5.9 0.000 0.002 60.538 60.539 scf_env_do_scf_inner_loop 96 6.5 0.002 0.017 55.865 55.866 velocity_verlet 10 3.0 0.002 0.003 41.534 41.535 rebuild_ks_matrix 107 8.3 0.000 0.001 30.256 30.330 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.016 30.256 30.330 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.646 26.715 sum_up_and_integrate 107 10.3 0.033 0.036 26.507 26.538 integrate_v_rspace 107 11.3 0.004 0.005 26.474 26.511 qs_rho_update_rho_low 107 7.7 0.000 0.001 25.843 25.850 calculate_rho_elec 107 8.7 0.027 0.030 25.843 25.849 grid_integrate_task_list 107 12.3 22.670 23.189 22.670 23.189 grid_collocate_task_list 107 9.7 21.778 22.622 21.778 22.622 dbcsr_multiply_generic 1966 12.4 0.065 0.069 11.931 12.182 qs_scf_new_mos 96 7.5 0.000 0.001 9.223 9.319 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.222 9.319 multiply_cannon 1966 13.4 0.129 0.143 8.953 9.262 multiply_cannon_loop 1966 14.4 0.090 0.098 8.512 8.847 ot_scf_mini 96 9.5 0.002 0.002 8.664 8.755 mp_waitall_1 146670 16.2 7.528 7.897 7.528 7.897 multiply_cannon_metrocomm3 15728 15.4 0.034 0.037 5.070 5.514 ot_mini 96 10.5 0.001 0.001 5.049 5.151 rs_pw_transfer 878 11.9 0.010 0.012 4.515 5.130 init_scf_loop 11 6.9 0.000 0.000 4.660 4.660 density_rs2pw 107 9.7 0.005 0.005 3.762 4.376 init_scf_run 11 5.9 0.000 0.004 3.893 3.894 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.893 3.893 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.728 3.737 wfi_extrapolate 11 7.9 0.001 0.001 3.537 3.537 pw_transfer 1295 11.6 0.092 0.109 2.974 3.029 potential_pw2rs 107 12.3 0.006 0.006 2.896 2.907 fft_wrap_pw1pw2 1081 12.6 0.008 0.010 2.823 2.876 multiply_cannon_multrec 15728 15.4 2.703 2.836 2.712 2.846 qs_ot_get_derivative 96 11.5 0.001 0.001 2.596 2.687 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.438 2.527 apply_single 107 13.6 0.000 0.000 2.438 2.527 fft_wrap_pw1pw2_140 439 13.2 0.246 0.259 2.442 2.505 mp_waitany 8968 13.7 1.875 2.480 1.875 2.480 ot_diis_step 96 11.5 0.003 0.003 2.434 2.434 rs_pw_transfer_RS2PW_140 118 11.5 0.160 0.184 1.565 2.189 fft3d_ps 1081 14.6 1.107 1.188 2.009 2.066 make_m2s 3932 13.4 0.040 0.045 2.030 2.065 make_images 3932 14.4 0.103 0.106 1.745 1.785 mp_alltoall_d11v 1998 13.7 1.081 1.782 1.081 1.782 rs_gather_matrices 107 12.3 0.070 0.079 0.870 1.531 ------------------------------------------------------------------------------- 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=41.09700000000001, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.115, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.295, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.348, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.275, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.106, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.764, 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=13.698999999999998, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.778, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.67, 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="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.703, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.528, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.875, 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 0.175 0.175 104.486 104.486 qs_energies 1 2.0 0.000 0.000 103.667 103.667 scf_env_do_scf 1 3.0 0.000 0.000 102.520 102.520 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.767 97.767 rebuild_ks_matrix 7 6.0 0.000 0.000 97.711 97.711 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.711 97.711 hfx_ks_matrix 7 8.0 0.000 0.000 88.998 88.998 integrate_four_center 7 9.0 1.681 1.681 88.933 88.933 integrate_four_center_main 7 10.0 0.518 0.518 81.378 81.378 integrate_four_center_bin 450 11.0 80.860 80.860 80.860 80.860 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.211 56.211 init_scf_loop 1 4.0 0.000 0.000 46.300 46.300 integrate_four_center_load 7 10.0 0.010 0.010 5.651 5.651 hfx_load_balance 1 11.0 0.001 0.001 5.641 5.641 qs_vxc_create 14 8.0 0.000 0.000 3.046 3.046 xc_vxc_pw_create 14 9.0 0.148 0.148 3.046 3.046 hfx_load_balance_count 1 12.0 2.815 2.815 2.815 2.815 hfx_load_balance_bin 1 12.0 2.808 2.808 2.808 2.808 calculate_rho_elec 15 7.4 0.118 0.118 2.430 2.430 xc_rho_set_and_dset_create 14 10.0 0.086 0.086 2.299 2.299 prepare_preconditioner 1 5.0 0.000 0.000 2.246 2.246 make_preconditioner 1 6.0 0.000 0.000 2.246 2.246 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.122 2.122 ------------------------------------------------------------------------------- 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 0.255 0.280 95.299 95.310 qs_energies 1 2.0 0.000 0.000 94.918 94.919 scf_env_do_scf 1 3.0 0.000 0.000 94.586 94.586 qs_ks_update_qs_env 8 5.0 0.000 0.000 92.721 92.722 rebuild_ks_matrix 7 6.0 0.000 0.000 92.712 92.713 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 92.712 92.713 hfx_ks_matrix 7 8.0 0.000 0.000 87.475 87.477 integrate_four_center 7 9.0 0.055 0.340 87.467 87.468 integrate_four_center_main 7 10.0 0.003 0.003 78.761 80.705 integrate_four_center_bin 448 11.0 78.758 80.702 78.758 80.702 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 52.710 52.710 init_scf_loop 1 4.0 0.000 0.000 41.875 41.875 integrate_four_center_load 7 10.0 0.000 0.000 5.612 5.613 hfx_load_balance 1 11.0 0.001 0.001 5.612 5.613 mp_sync 70 11.3 2.431 3.884 2.431 3.884 hfx_load_balance_count 1 12.0 2.769 2.806 2.769 2.806 hfx_load_balance_bin 1 12.0 2.766 2.804 2.766 2.804 qs_vxc_create 14 8.0 0.000 0.000 2.365 2.366 xc_vxc_pw_create 14 9.0 0.007 0.008 2.365 2.365 xc_rho_set_and_dset_create 14 10.0 0.010 0.011 1.908 2.014 ------------------------------------------------------------------------------- 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=15.629000000000005, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.86, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.815, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.808, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.681, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.518, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.175, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="H2O-hyb_timings_32mpi", title="Timings of H2O-hyb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32mpi", name="rest", label="rest", y=8.262, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.758, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.769, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.766, 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=0.255, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=2.431, 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 85.260 85.260 qs_energies 1 2.0 0.000 0.000 84.874 84.874 mp2_main 1 3.0 0.000 0.000 82.062 82.062 mp2_gpw_main 1 4.0 0.000 0.000 81.956 81.956 rpa_ri_compute_en 1 5.0 0.000 0.000 78.356 78.356 rpa_num_int 1 6.0 0.001 0.001 78.350 78.350 compute_mat_P_omega 1 7.0 0.003 0.003 68.446 68.446 compute_mat_P_omega_contract 10 8.0 8.857 8.857 68.254 68.254 dbt_total 2336 9.6 0.011 0.011 54.507 54.507 dbt_contract 787 11.0 0.033 0.033 47.659 47.659 dbt_tas_total 1149 12.2 0.183 0.183 46.850 46.850 dbt_tas_multiply 807 12.1 0.002 0.002 45.449 45.449 dbt_tas_dbm 807 14.1 0.003 0.003 38.927 38.927 dbm_multiply 807 16.1 38.919 38.919 38.919 38.919 dbt_tas_mm_1N 524 15.1 0.001 0.001 31.875 31.875 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 30.460 30.460 compute_mat_P_omega_calc_M_occ 250 9.0 8.867 8.867 16.788 16.788 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.634 6.634 dbt_tas_mm_2 251 15.0 0.001 0.001 5.632 5.632 dbt_copy 1103 10.7 0.081 0.081 5.431 5.431 compute_QP_energies 1 7.0 0.000 0.000 4.940 4.940 compute_self_energy_cubic_gw 1 8.0 0.053 0.053 4.939 4.939 contract_cubic_gw 21 9.0 0.000 0.000 3.995 3.995 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.593 3.593 dbt_tas_reserve_blocks_index 3261 14.3 0.142 0.142 3.260 3.260 dbm_reserve_blocks 3628 15.3 3.180 3.180 3.180 3.180 scf_env_do_scf 1 3.0 0.000 0.000 2.707 2.707 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.706 2.706 dbt_reserve_blocks_index 2280 13.1 0.050 0.050 2.443 2.443 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.406 2.406 convert_to_new_pgrid 2421 14.1 0.077 0.077 2.299 2.299 dbt_tas_copy 574 11.4 1.388 1.388 2.251 2.251 dbm_copy 1614 15.1 2.223 2.223 2.223 2.223 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.181 2.181 dbt_tas_reshape 367 15.0 0.006 0.006 2.148 2.148 dbt_crop 1042 12.0 1.357 1.357 2.111 2.111 compute_W_cubic_GW 10 7.0 0.004 0.004 1.953 1.953 get_2c_integrals 1 6.0 0.000 0.000 1.760 1.760 dbt_reshape 278 11.9 0.919 0.919 1.739 1.739 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.025 31.076 31.089 qs_energies 1 2.0 0.000 0.001 30.993 30.995 mp2_main 1 3.0 0.000 0.000 30.066 30.068 mp2_gpw_main 1 4.0 0.000 0.000 30.031 30.033 rpa_ri_compute_en 1 5.0 0.000 0.000 28.773 28.775 rpa_num_int 1 6.0 0.000 0.002 28.773 28.775 dbt_total 2336 9.6 0.011 0.012 25.494 25.497 compute_mat_P_omega 1 7.0 0.001 0.005 24.335 24.336 compute_mat_P_omega_contract 10 8.0 0.416 0.428 24.232 24.234 dbt_contract 787 11.0 0.025 0.026 19.163 19.166 dbt_tas_total 1149 12.2 0.051 0.057 17.160 17.162 dbt_tas_multiply 807 12.1 0.002 0.002 17.132 17.134 dbt_tas_dbm 807 14.1 0.003 0.003 12.777 12.781 dbm_multiply 807 16.1 9.968 10.838 9.968 10.838 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.214 7.214 compute_mat_P_omega_calc_M_occ 250 9.0 0.392 0.405 7.093 7.094 dbt_tas_mm_2 251 15.0 0.001 0.001 5.995 5.996 dbt_copy 1111 10.7 0.011 0.012 5.614 5.776 dbt_reshape 1098 11.7 2.152 2.265 5.346 5.499 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.223 5.223 mp_sync 8706 11.6 4.401 5.106 4.401 5.106 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.637 4.979 compute_QP_energies 1 7.0 0.000 0.000 2.779 2.780 compute_self_energy_cubic_gw 1 8.0 0.003 0.004 2.779 2.779 mp_waitall_2 3776 15.3 2.451 2.616 2.451 2.616 dbt_communicate_buffer 1098 12.7 0.053 0.057 2.512 2.608 contract_cubic_gw 21 9.0 0.000 0.000 2.203 2.203 dbt_reserve_blocks_index 2849 13.1 0.065 0.069 1.600 1.723 dbt_reserve_blocks_index_array 2791 12.2 0.010 0.011 1.591 1.712 dbt_tas_reserve_blocks_index 3300 14.5 0.110 0.118 1.569 1.692 dbm_reserve_blocks 3696 15.4 1.550 1.669 1.550 1.669 dbt_crop 1042 12.0 0.903 0.999 1.392 1.520 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.256 1.257 dbt_tas_replicate 396 14.1 0.526 0.686 1.073 1.133 parallel_gemm_fm 105 8.4 0.000 0.000 0.995 1.003 parallel_gemm_fm_cosma 105 9.4 0.994 1.003 0.994 1.003 convert_to_new_pgrid 2421 14.1 0.024 0.027 0.809 0.963 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.951 0.953 dbm_copy 1608 15.1 0.778 0.934 0.778 0.934 scf_env_do_scf 1 3.0 0.000 0.000 0.890 0.890 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.890 0.890 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.877 0.879 compute_W_cubic_GW 10 7.0 0.001 0.001 0.762 0.768 dbm_add 807 14.1 0.639 0.690 0.639 0.690 mp_max_i 1994 9.8 0.522 0.637 0.522 0.637 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 0.634 0.634 ------------------------------------------------------------------------------- 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=22.29500000000001, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=38.919, 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=8.867, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.857, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.18, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.223, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.919, 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=8.968, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.968, 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=0.392, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.416, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.55, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.778, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.152, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.401, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.451, 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 0.018 0.018 321.458 321.458 qs_forces 1 2.0 0.000 0.000 320.902 320.902 rebuild_ks_matrix 7 6.6 0.000 0.000 319.491 319.491 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 319.491 319.491 hfx_ks_matrix 7 8.6 0.000 0.000 317.424 317.424 hfx_ri_update_ks 7 9.6 0.000 0.000 280.499 280.499 hfx_ri_update_ks_Pmat 7 10.6 31.148 31.148 280.489 280.489 dbt_total 841 11.0 0.005 0.005 264.097 264.097 qs_energies 1 3.0 0.000 0.000 247.295 247.295 scf_env_do_scf 1 4.0 0.000 0.000 247.010 247.010 dbt_contract 207 12.4 0.060 0.060 246.457 246.457 dbt_tas_total 375 13.4 1.468 1.468 246.077 246.077 qs_ks_update_qs_env 8 6.0 0.000 0.000 245.933 245.933 dbt_tas_multiply 216 13.5 0.001 0.001 241.747 241.747 dbt_tas_dbm 216 15.5 0.001 0.001 230.442 230.442 dbm_multiply 216 17.5 230.438 230.438 230.438 230.438 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.000 225.837 225.837 dbt_tas_mm_2 91 16.5 0.001 0.001 217.233 217.233 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 156.359 156.359 init_scf_loop 2 5.0 0.000 0.000 90.650 90.650 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 73.561 73.561 hfx_ri_update_forces 1 7.0 1.637 1.637 36.922 36.922 hfx_ri_forces_Pmat_3c 1 8.0 4.673 4.673 21.085 21.085 dbt_copy 409 11.7 0.059 0.059 13.302 13.302 precalc_derivatives 1 8.0 2.108 2.108 12.188 12.188 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.241 9.241 dbt_reshape 132 13.2 5.627 5.627 9.132 9.132 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.127 9.127 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.009 7.009 build_3c_derivatives 3 9.0 2.346 2.346 6.842 6.842 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-HFX_H2O-32_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.024 43.693 43.702 qs_forces 1 2.0 0.000 0.000 43.558 43.558 rebuild_ks_matrix 7 6.6 0.000 0.000 42.890 42.890 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 42.890 42.890 hfx_ks_matrix 7 8.6 0.000 0.000 41.950 41.956 dbt_total 841 11.0 0.005 0.005 37.235 37.244 dbt_contract 207 12.4 0.020 0.024 29.446 29.458 dbt_tas_total 375 13.4 0.043 0.117 27.298 27.299 dbt_tas_multiply 216 13.5 0.001 0.001 26.406 26.407 hfx_ri_update_ks 7 9.6 0.000 0.000 24.674 24.674 hfx_ri_update_ks_Pmat 7 10.6 1.204 1.272 24.670 24.671 qs_energies 1 3.0 0.000 0.000 23.248 23.248 scf_env_do_scf 1 4.0 0.000 0.001 23.107 23.108 qs_ks_update_qs_env 8 6.0 0.000 0.000 22.599 22.600 dbt_tas_dbm 216 15.5 0.001 0.001 21.153 21.157 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 20.300 20.301 dbm_multiply 216 17.5 18.681 19.474 18.681 19.474 hfx_ri_update_forces 1 7.0 0.057 0.059 17.275 17.281 hfx_ri_forces_Pmat_3c 1 8.0 0.166 0.175 12.901 12.915 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 12.790 12.790 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 11.616 11.616 init_scf_loop 2 5.0 0.000 0.001 10.317 10.317 dbt_tas_mm_2 91 16.5 0.001 0.001 9.767 9.768 mp_sync 2909 12.8 4.395 6.821 4.395 6.821 dbt_copy 421 11.8 0.009 0.011 6.496 6.722 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.777 6.124 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.954 4.954 dbt_reshape 252 12.8 2.252 2.340 4.447 4.571 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.963 4.109 precalc_derivatives 1 8.0 0.078 0.083 3.339 3.339 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.179 3.179 dbm_reserve_blocks 1477 16.3 2.520 2.837 2.520 2.837 dbt_tas_reserve_blocks_index 1302 15.5 0.216 0.227 2.505 2.793 dbt_crop 372 13.7 1.707 1.815 2.324 2.490 mp_waitall_2 1204 16.3 2.168 2.281 2.168 2.281 dbt_reserve_blocks_index 938 14.4 0.092 0.098 1.970 2.183 dbt_reserve_blocks_index_array 915 13.4 0.005 0.005 1.947 2.158 build_3c_derivatives 3 9.0 0.221 0.239 1.863 1.875 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.710 1.713 dbt_tas_replicate 175 15.2 0.681 0.709 1.658 1.708 dbt_communicate_buffer 252 13.8 0.011 0.012 1.465 1.539 dbt_tas_copy 169 12.8 0.807 0.846 1.414 1.526 convert_to_new_pgrid 648 15.5 0.032 0.063 1.273 1.459 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.385 1.386 dbm_copy 452 16.3 1.094 1.283 1.094 1.283 dbt_tas_communicate_buffer 352 16.4 0.013 0.014 0.930 0.985 ------------------------------------------------------------------------------- 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=47.226, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=230.438, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.148, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=5.627, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.673, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="build_3c_derivatives", label="build_3c_derivatives", y=2.346, 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 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=12.085999999999999, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=18.681, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.204, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.252, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.166, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="build_3c_derivatives", label="build_3c_derivatives", y=0.221, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.395, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.168, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.52, 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 0.014 0.014 218.722 218.722 qs_energies 1 2.0 0.000 0.000 218.541 218.541 mp2_main 1 3.0 0.000 0.000 213.837 213.837 mp2_gpw_main 1 4.0 0.001 0.001 213.415 213.415 mp2_ri_gpw_compute_in 1 5.0 0.381 0.381 167.164 167.164 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 155.759 155.759 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 125.774 125.774 integrate_v_rspace 2666 8.0 0.598 0.598 112.643 112.643 grid_integrate_task_list 2666 9.0 110.074 110.074 110.074 110.074 mp2_ri_gpw_compute_en 1 5.0 0.090 0.090 46.229 46.229 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.871 9.871 44.372 44.372 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.089 2.089 27.445 27.445 local_gemm 2080 8.0 25.356 25.356 25.356 25.356 dbcsr_multiply_generic 5322 8.0 0.174 0.174 20.300 20.300 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.279 20.279 pw_transfer 63872 10.6 1.016 1.016 11.953 11.953 calculate_wavefunction 2656 8.0 8.117 8.117 11.775 11.775 get_2c_integrals 1 6.0 0.000 0.000 11.023 11.023 fft_wrap_pw1pw2 53228 11.4 0.107 0.107 10.728 10.728 multiply_cannon 5322 9.0 0.430 0.430 10.334 10.334 compute_2c_integrals 1 7.0 0.006 0.006 10.052 10.052 compute_2c_integrals_loop_lm 1 8.0 0.008 0.008 10.027 10.027 mp2_eri_2c_integrate_gpw 1 9.0 3.235 3.235 10.019 10.019 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.262 2.262 9.600 9.600 multiply_cannon_loop 5322 10.0 0.102 0.102 9.009 9.009 make_m2s 10644 9.0 0.061 0.061 7.873 7.873 copy_dbcsr_to_fm 2679 8.0 0.028 0.028 7.827 7.827 fft_wrap_pw1pw2_20 21271 12.4 0.451 0.451 7.663 7.663 make_images 10644 10.0 3.101 3.101 7.585 7.585 multiply_cannon_multrec 5322 11.0 7.466 7.466 7.507 7.507 fft3d_s 53229 13.4 6.677 6.677 6.712 6.712 dbcsr_complete_redistribute 2689 9.0 1.280 1.280 5.945 5.945 dbcsr_finalize 10708 9.5 0.204 0.204 5.206 5.206 mp2_ri_gpw_compute_en_ener 2080 7.0 5.195 5.195 5.195 5.195 dbcsr_merge_all 8011 10.3 3.480 3.480 4.529 4.529 ------------------------------------------------------------------------------- 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 0.006 0.020 33.979 33.989 qs_energies 1 2.0 0.000 0.000 33.910 33.910 mp2_main 1 3.0 0.000 0.001 31.876 31.877 mp2_gpw_main 1 4.0 0.001 0.002 31.762 31.762 mp2_ri_gpw_compute_in 1 5.0 0.051 0.052 16.847 17.035 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.685 15.877 mp2_ri_gpw_compute_en 1 5.0 0.155 0.166 14.824 15.062 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.794 0.883 13.943 13.947 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.674 13.923 integrate_v_rspace 93 8.1 0.099 0.107 13.537 13.795 grid_integrate_task_list 93 9.1 13.253 13.517 13.253 13.517 mp2_ri_gpw_compute_en_expansio 65 7.0 0.102 0.117 10.520 10.668 local_gemm 65 8.0 10.418 10.551 10.418 10.551 mp2_ri_gpw_compute_en_comm 17 7.0 0.065 0.078 2.272 2.499 mp_sendrecv_dm3 1054 8.0 1.753 2.019 1.753 2.019 scf_env_do_scf 1 3.0 0.000 0.000 1.919 1.919 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.919 1.919 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.726 1.888 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.708 1.868 get_2c_integrals 1 6.0 0.000 0.000 1.089 1.124 multiply_cannon 176 9.0 0.015 0.016 1.016 1.068 multiply_cannon_loop 176 10.0 0.002 0.002 0.961 1.014 qs_scf_new_mos 10 5.0 0.000 0.000 1.005 1.010 eigensolver 11 5.8 0.001 0.001 0.991 0.993 multiply_cannon_multrec 246 11.0 0.828 0.870 0.833 0.876 compute_2c_integrals 1 7.0 0.003 0.003 0.808 0.827 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.818 0.822 cp_fm_redistribute_end 11 7.8 0.307 0.814 0.318 0.815 make_m2s 352 9.0 0.003 0.003 0.675 0.796 cp_fm_diag_elpa_base 11 7.8 0.480 0.772 0.490 0.787 make_images 352 10.0 0.050 0.051 0.663 0.784 pw_transfer 2120 10.5 0.043 0.044 0.730 0.748 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 0.729 0.746 mp2_eri_2c_integrate_gpw 1 9.0 0.197 0.199 0.727 0.745 fft_wrap_pw1pw2 1768 11.4 0.004 0.004 0.674 0.695 ------------------------------------------------------------------------------- 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=57.837999999999994, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=110.074, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=25.356, 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=9.871, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.117, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.466, 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=6.933, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.253, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.418, 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=0.794, 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=0.828, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.753, 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 0.080 0.080 125.519 125.519 qs_energies 1 2.0 0.000 0.000 124.139 124.139 scf_env_do_scf 1 3.0 0.000 0.000 117.607 117.607 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 117.607 117.607 qs_ks_update_qs_env 15 5.0 0.000 0.000 49.955 49.955 rebuild_ks_matrix 15 6.0 0.000 0.000 49.747 49.747 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 49.747 49.747 qs_scf_new_mos 15 5.0 0.000 0.000 42.919 42.919 eigensolver 15 6.0 0.001 0.001 35.050 35.050 qs_vxc_create 15 8.0 0.036 0.036 34.511 34.511 calculate_dispersion_nonloc 15 9.0 7.178 7.178 30.139 30.139 pw_transfer 1191 10.0 0.057 0.057 22.934 22.934 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.800 22.800 cp_fm_diag_elpa_base 15 8.0 20.285 20.285 22.800 22.800 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 22.767 22.767 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.825 21.825 calculate_rho_elec 16 6.0 0.214 0.214 21.825 21.825 grid_collocate_task_list 16 7.0 20.453 20.453 20.453 20.453 fft_wrap_pw1pw2_150 765 12.0 3.538 3.538 16.410 16.410 sum_up_and_integrate 15 8.0 0.105 0.105 14.014 14.014 integrate_v_rspace 15 9.0 0.021 0.021 13.910 13.910 grid_integrate_task_list 15 10.0 13.390 13.390 13.390 13.390 cp_fm_cholesky_restore 45 7.0 10.040 10.040 10.040 10.040 fft3d_s 1087 13.0 9.970 9.970 9.978 9.978 pw_scatter_s 585 13.1 7.295 7.295 7.295 7.295 fft_wrap_pw1pw2_200 197 12.3 0.804 0.804 6.173 6.173 dbcsr_complete_redistribute 46 8.3 2.190 2.190 5.643 5.643 copy_dbcsr_to_fm 16 5.9 0.000 0.000 5.546 5.546 cp_fm_upper_to_full 30 8.0 4.724 4.724 4.724 4.724 xc_vxc_pw_create 15 9.0 0.211 0.211 4.336 4.336 vdW_energy 15 10.0 4.269 4.269 4.269 4.269 gspace_mixing 14 5.0 0.170 0.170 4.127 4.127 broyden_mixing 14 6.0 3.472 3.472 3.472 3.472 init_scf_run 1 3.0 0.000 0.000 3.037 3.037 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.034 3.034 xc_pw_derive 90 11.0 0.001 0.001 2.873 2.873 calculate_dm_sparse 15 6.0 0.018 0.018 2.674 2.674 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 2.596 2.596 ------------------------------------------------------------------------------- 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 0.014 0.027 59.469 59.480 qs_energies 1 2.0 0.000 0.000 59.213 59.218 scf_env_do_scf 1 3.0 0.000 0.001 55.048 55.048 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 55.048 55.048 qs_ks_update_qs_env 15 5.0 0.000 0.000 22.947 22.956 rebuild_ks_matrix 15 6.0 0.000 0.000 22.915 22.924 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 22.915 22.924 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.376 20.379 calculate_rho_elec 16 6.0 0.007 0.007 20.376 20.379 grid_collocate_task_list 16 7.0 19.147 19.354 19.147 19.354 sum_up_and_integrate 15 8.0 0.011 0.016 13.535 13.580 integrate_v_rspace 15 9.0 0.000 0.001 13.524 13.573 grid_integrate_task_list 15 10.0 12.866 12.965 12.866 12.965 qs_scf_new_mos 15 5.0 0.000 0.000 12.396 12.431 eigensolver 15 6.0 0.001 0.002 11.455 11.472 qs_vxc_create 15 8.0 0.001 0.001 9.090 9.099 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.307 8.309 cp_fm_diag_elpa_base 15 8.0 8.158 8.195 8.302 8.302 calculate_dispersion_nonloc 15 9.0 0.906 0.940 7.298 7.314 pw_transfer 1191 10.0 0.095 0.104 6.821 6.890 fft_wrap_pw1pw2 1086 11.0 0.013 0.015 6.638 6.727 fft3d_ps 1086 13.0 2.514 2.682 4.950 5.119 fft_wrap_pw1pw2_150 765 12.0 0.305 0.327 4.279 4.315 cp_fm_cholesky_restore 45 7.0 3.001 3.044 3.001 3.044 qs_energies_init_hamiltonians 1 3.0 0.000 0.001 2.451 2.451 mp_alltoall_z22v 1086 15.0 1.842 2.389 1.842 2.389 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.144 2.354 fft_wrap_pw1pw2_200 197 12.3 0.183 0.201 2.249 2.307 xc_vxc_pw_create 15 9.0 0.015 0.018 1.791 1.817 init_scf_run 1 3.0 0.000 0.001 1.493 1.493 x_to_yz 585 14.1 0.344 0.360 1.239 1.457 yz_to_x 501 13.9 0.224 0.273 1.171 1.449 build_core_ppnl 1 5.0 1.245 1.379 1.245 1.379 vdW_energy 15 10.0 1.296 1.356 1.296 1.356 rs_pw_transfer 158 9.4 0.001 0.002 1.109 1.347 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.293 1.294 density_rs2pw 16 7.0 0.001 0.001 1.107 1.283 xc_pw_derive 90 11.0 0.001 0.002 1.185 1.256 ------------------------------------------------------------------------------- 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=51.381, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.453, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.285, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.39, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.04, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=9.97, 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=13.783000000000001, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.147, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.158, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.866, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.001, 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=2.514, 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 0.075 0.075 315.228 315.228 qs_energies 1 2.0 0.000 0.000 315.093 315.093 ls_scf 1 3.0 0.000 0.000 313.848 313.848 ls_scf_main 1 4.0 0.002 0.002 304.877 304.877 density_matrix_trs4 11 5.0 0.012 0.012 213.646 213.646 arnoldi_extremal 12 6.1 0.000 0.000 130.353 130.353 arnoldi_normal_ev 12 7.1 0.014 0.014 130.353 130.353 build_subspace 23 8.1 0.081 0.081 128.113 128.113 dbcsr_matrix_vector_mult 652 9.0 0.168 0.168 127.911 127.911 dbcsr_matrix_vector_mult_local 652 10.0 126.568 126.568 126.578 126.578 ls_scf_dm_to_ks 11 5.0 0.000 0.000 85.996 85.996 matrix_ls_to_qs 11 6.0 0.000 0.000 82.701 82.701 dbcsr_multiply_generic 185 6.1 0.810 0.810 72.291 72.291 dbcsr_copy_into_existing 11 7.0 44.914 44.914 44.915 44.915 multiply_cannon 185 7.1 0.286 0.286 43.793 43.793 dbcsr_complete_redistribute 23 7.5 30.449 30.449 41.474 41.474 matrix_decluster 11 7.0 0.000 0.000 37.782 37.782 multiply_cannon_loop 185 8.1 0.226 0.226 31.656 31.656 make_m2s 370 7.1 0.037 0.037 24.205 24.205 make_images 370 8.1 10.450 10.450 22.641 22.641 multiply_cannon_multrec 185 9.1 22.346 22.346 22.372 22.372 dbcsr_finalize 646 7.5 0.246 0.246 14.601 14.601 dbcsr_merge_all 597 8.5 2.204 2.204 13.469 13.469 setup_rec_index_2d 370 8.1 11.764 11.764 11.764 11.764 dbcsr_sort_indices 1103 9.9 10.119 10.119 10.119 10.119 tree_to_linear_d 110 9.4 10.004 10.004 10.004 10.004 calculate_norms 370 9.1 9.057 9.057 9.057 9.057 quick_finalize 395 10.0 0.358 0.358 8.763 8.763 ls_scf_init_scf 1 4.0 0.000 0.000 8.303 8.303 dbcsr_special_finalize 370 9.1 0.002 0.002 8.105 8.105 ls_scf_init_matrix_S 1 5.0 0.000 0.000 7.959 7.959 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.322 7.322 ------------------------------------------------------------------------------- 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 0.009 0.023 64.679 64.689 qs_energies 1 2.0 0.000 0.000 64.585 64.585 ls_scf 1 3.0 0.000 0.000 64.536 64.537 ls_scf_main 1 4.0 0.001 0.008 62.005 62.005 density_matrix_trs4 11 5.0 0.006 0.017 59.563 59.621 dbcsr_multiply_generic 185 6.1 0.059 0.079 56.499 56.695 multiply_cannon 185 7.1 0.034 0.036 47.266 47.799 multiply_cannon_loop 185 8.1 0.116 0.128 44.855 45.677 multiply_cannon_multrec 1480 9.1 27.748 29.840 28.022 30.113 mp_waitall_1 11936 10.3 14.438 15.964 14.438 15.964 multiply_cannon_metrocomm3 1480 9.1 0.014 0.018 8.704 11.794 make_m2s 370 7.1 0.035 0.039 6.416 6.472 make_images 370 8.1 0.622 0.663 6.289 6.347 calculate_norms 2960 9.1 4.757 5.586 4.757 5.586 multiply_cannon_metrocomm1 1480 9.1 0.008 0.010 3.199 5.232 make_images_data 370 9.1 0.009 0.011 2.783 2.941 hybrid_alltoall_any 393 9.9 0.192 1.130 2.440 2.592 mp_sum_l 1119 5.6 1.754 2.499 1.754 2.499 arnoldi_extremal 12 6.1 0.000 0.000 2.278 2.292 arnoldi_normal_ev 12 7.1 0.001 0.004 2.278 2.292 build_subspace 23 8.1 0.020 0.025 2.188 2.190 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.114 2.170 dbcsr_complete_redistribute 23 7.5 1.191 1.278 1.906 1.974 dbcsr_matrix_vector_mult 652 9.0 0.009 0.043 1.893 1.950 ls_scf_init_scf 1 4.0 0.000 0.000 1.948 1.949 matrix_ls_to_qs 11 6.0 0.000 0.000 1.860 1.931 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.922 1.928 matrix_decluster 11 7.0 0.000 0.000 1.721 1.793 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.754 1.756 make_images_pack 370 9.1 1.615 1.728 1.618 1.732 dbcsr_finalize 646 7.5 0.008 0.008 1.456 1.677 dbcsr_matrix_vector_mult_local 652 10.0 1.589 1.651 1.591 1.653 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 0.964 1.558 buffer_matrices_ensure_size 370 8.1 1.326 1.419 1.326 1.419 ------------------------------------------------------------------------------- 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=70.13, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=126.568, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=44.914, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.449, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.346, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.764, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.057, 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_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=11.586999999999996, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.589, 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=1.191, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=27.748, 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=4.757, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.615, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.754, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.438, 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 68.873 68.873 lib_test 1 2.0 0.000 0.000 68.865 68.865 dbcsr_run_tests 3 3.0 0.011 0.011 68.865 68.865 test_multiplies_multiproc 3 4.0 0.001 0.001 53.086 53.086 dbcsr_redistribute 9 5.0 34.311 34.311 35.909 35.909 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.854 15.854 dbcsr_make_random_matrix 9 4.0 12.670 12.670 15.662 15.662 multiply_cannon 9 6.0 0.001 0.001 11.220 11.220 multiply_cannon_loop 9 7.0 0.002 0.002 10.866 10.866 multiply_cannon_multrec 9 8.0 10.864 10.864 10.864 10.864 dbcsr_finalize 27 5.7 0.003 0.003 5.484 5.484 dbcsr_merge_all 18 6.5 1.940 1.940 4.751 4.751 dbcsr_data_release 975 7.6 2.805 2.805 2.805 2.805 tree_to_linear_d 9 7.0 1.901 1.901 1.901 1.901 make_m2s 18 6.0 0.001 0.001 1.583 1.583 make_images 18 7.0 0.545 0.545 1.538 1.538 ------------------------------------------------------------------------------- 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 0.003 0.011 17.498 17.502 lib_test 1 2.0 0.000 0.001 17.469 17.489 dbcsr_run_tests 3 3.0 0.000 0.001 17.468 17.488 test_multiplies_multiproc 3 4.0 0.000 0.002 16.630 16.672 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.297 15.354 multiply_cannon 9 6.0 0.002 0.002 13.611 13.902 multiply_cannon_loop 9 7.0 0.002 0.002 13.324 13.582 multiply_cannon_multrec 72 8.0 11.194 11.608 11.194 11.609 mp_waitall_1 576 9.2 2.422 2.934 2.422 2.934 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.898 2.383 dbcsr_data_release 444 7.6 0.768 0.864 0.768 0.864 mp_sum_l 390 2.5 0.375 0.852 0.375 0.852 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.372 0.849 dbcsr_make_random_matrix 9 4.0 0.661 0.671 0.805 0.835 dbcsr_finalize 27 5.7 0.000 0.000 0.694 0.795 dbcsr_destroy 111 5.9 0.000 0.000 0.618 0.753 make_m2s 18 6.0 0.001 0.001 0.644 0.694 make_images 18 7.0 0.021 0.021 0.640 0.691 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.224 0.641 dbcsr_merge_all 18 6.5 0.099 0.120 0.543 0.628 dbcsr_redistribute 9 5.0 0.234 0.268 0.396 0.418 make_images_data 18 8.0 0.000 0.001 0.331 0.414 dbcsr_data_copy_aa2 18 7.5 0.327 0.394 0.327 0.394 hybrid_alltoall_any 18 9.0 0.027 0.130 0.291 0.365 ------------------------------------------------------------------------------- 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=6.283000000000008, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=34.311, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.67, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.864, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.805, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.94, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=1.7449999999999992, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.234, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.661, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.194, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.768, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.099, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.422, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.375, 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 0.055 0.055 136.741 136.741 qs_mol_dyn_low 1 2.0 0.003 0.003 135.397 135.397 velocity_verlet 5 3.0 0.003 0.003 111.123 111.123 qmmm_el_coupling 6 3.8 0.000 0.000 92.798 92.798 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 92.795 92.795 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 92.165 92.165 qmmm_elec_gaussian_low_G 6 6.8 91.267 91.267 91.267 91.267 qs_forces 6 3.8 0.000 0.000 34.238 34.238 qs_energies 6 4.8 0.000 0.000 30.379 30.379 scf_env_do_scf 6 5.8 0.001 0.001 28.113 28.113 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.478 24.478 rebuild_ks_matrix 45 8.4 0.000 0.000 23.520 23.520 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.520 23.520 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.112 20.112 pw_transfer 966 12.3 0.052 0.052 16.939 16.939 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.738 16.738 fft_wrap_pw1pw2_150 507 15.2 2.209 2.209 16.324 16.324 qs_vxc_create 45 10.4 0.001 0.001 13.002 13.002 xc_vxc_pw_create 45 11.4 0.664 0.664 13.001 13.001 xc_pw_derive 270 13.4 0.002 0.002 9.185 9.185 fft3d_s 802 15.6 7.683 7.683 7.697 7.697 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.042 7.042 calculate_rho_elec 45 8.9 0.563 0.563 7.042 7.042 xc_rho_set_and_dset_create 45 12.4 0.563 0.563 6.658 6.658 xc_pw_divergence 45 12.4 0.001 0.001 5.627 5.627 pw_scatter_s 429 15.8 5.597 5.597 5.597 5.597 qmmm_forces 6 3.8 0.001 0.001 5.150 5.150 qmmm_forces_with_gaussian 6 4.8 0.016 0.016 4.828 4.828 pw_integral_ab 2539 7.4 4.434 4.434 4.434 4.434 qs_ks_ddapc 45 10.4 0.001 0.001 4.159 4.159 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.117 4.117 init_scf_loop 6 6.8 0.000 0.000 3.611 3.611 qmmm_forces_gaussian_low_G 6 6.8 3.432 3.432 3.432 3.432 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.415 3.415 sum_up_and_integrate 45 10.4 0.321 0.321 3.302 3.302 grid_collocate_task_list 45 9.9 3.248 3.248 3.248 3.248 density_rs2pw 45 9.9 0.002 0.002 3.232 3.232 integrate_v_rspace 45 11.4 0.006 0.006 2.980 2.980 ------------------------------------------------------------------------------- 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 0.038 0.058 53.073 53.087 qs_mol_dyn_low 1 2.0 0.002 0.004 52.086 52.143 qs_forces 6 3.8 0.001 0.001 37.365 37.366 qs_energies 6 4.8 0.000 0.001 35.627 35.628 scf_env_do_scf 6 5.8 0.000 0.001 34.631 34.631 scf_env_do_scf_inner_loop 113 6.2 0.002 0.017 33.238 33.238 rebuild_ks_matrix 119 8.1 0.000 0.000 24.538 24.545 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.016 24.537 24.545 qs_ks_update_qs_env 119 7.3 0.001 0.001 23.078 23.086 velocity_verlet 5 3.0 0.002 0.004 22.189 22.192 pw_transfer 2446 12.3 0.194 0.219 16.272 16.771 fft_wrap_pw1pw2 2059 13.4 0.024 0.027 15.835 16.327 fft_wrap_pw1pw2_150 1321 14.9 1.254 1.410 15.298 15.796 qs_vxc_create 119 10.1 0.002 0.003 12.897 12.902 xc_vxc_pw_create 119 11.1 0.150 0.215 12.895 12.900 fft3d_ps 2059 15.4 6.807 7.535 11.764 12.332 xc_pw_derive 714 13.1 0.011 0.012 9.682 9.953 qs_rho_update_rho_low 119 7.3 0.000 0.001 9.943 9.943 calculate_rho_elec 119 8.3 0.049 0.054 9.942 9.943 sum_up_and_integrate 119 10.1 0.081 0.092 8.532 8.550 integrate_v_rspace 119 11.1 0.003 0.003 8.451 8.475 qmmm_forces 6 3.8 0.002 0.002 7.359 7.360 qmmm_forces_with_gaussian 6 4.8 0.008 0.010 6.982 7.191 qmmm_el_coupling 6 3.8 0.000 0.000 6.378 6.543 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 6.377 6.541 xc_pw_divergence 119 12.1 0.005 0.006 6.289 6.508 xc_rho_set_and_dset_create 119 12.1 0.355 0.428 6.266 6.437 rs_pw_transfer 988 11.5 0.010 0.012 5.847 6.094 density_rs2pw 119 9.3 0.005 0.007 5.496 5.716 potential_pw2rs 119 12.1 0.005 0.006 4.837 4.852 grid_collocate_task_list 119 9.3 4.311 4.537 4.311 4.537 mp_alltoall_z22v 2059 17.4 3.540 4.088 3.540 4.088 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.826 3.939 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.415 3.635 grid_integrate_task_list 119 12.1 3.379 3.568 3.379 3.568 qmmm_forces_gaussian_low_G 6 6.8 3.147 3.227 3.147 3.227 qmmm_elec_gaussian_low_G 6 6.8 2.819 2.977 2.819 2.977 x_to_yz 1095 16.8 0.812 0.918 2.654 2.900 pw_restrict_s3 18 5.8 1.364 1.419 2.573 2.659 yz_to_x 964 16.0 0.544 0.822 2.242 2.624 mp_waitany 4028 12.8 2.116 2.450 2.116 2.450 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.117 2.281 pw_prolongate_s3 18 6.8 1.140 1.203 2.117 2.281 rs_pw_transfer_PW2RS_150 125 13.9 0.733 0.778 2.199 2.227 rs_pw_transfer_RS2PW_150 125 11.2 0.577 0.661 1.712 1.968 qs_scf_new_mos 113 7.2 0.000 0.000 1.930 1.935 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.930 1.934 qs_ks_ddapc 119 10.1 0.002 0.002 1.826 1.892 ot_scf_mini 113 9.2 0.001 0.001 1.844 1.851 dbcsr_multiply_generic 2588 12.3 0.056 0.058 1.749 1.769 mp_waitall_1 188862 16.2 1.656 1.751 1.656 1.751 pw_gather_p 964 15.0 1.247 1.631 1.247 1.631 pw_integral_ab 2761 7.7 1.259 1.320 1.476 1.582 pw_scatter_p 1095 15.8 1.517 1.550 1.517 1.550 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.468 1.469 init_scf_loop 6 6.8 0.000 0.000 1.391 1.391 mp_sum_dm3 33 5.7 1.321 1.370 1.321 1.370 ot_mini 113 10.2 0.000 0.000 1.142 1.147 ------------------------------------------------------------------------------- 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=21.080000000000027, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=91.267, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.683, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.597, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.434, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.432, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.248, 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 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=27.811, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.819, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_scatter_s", label="pw_scatter_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=1.259, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.147, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.311, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.54, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.379, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.807, yerr=0.0 Summary: Performance test took 35 minutes. Status: OK Removing intermediate container 5fbf070fed6d ---> 5eb7635390ca Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in e6808ff61502 Removing intermediate container e6808ff61502 ---> d1778bf46097 Step 42/42 : ENTRYPOINT [] ---> Running in ce3fa3ad9ed9 Removing intermediate container ce3fa3ad9ed9 ---> b221dc20f842 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built b221dc20f842 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: 2022-11-19 19:51:40+00:00