StartDate: 2022-12-26 19:11:11+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 3169bf56b7b69a13599bda2029f1ce159e56e4d8 CommitTime: 2022-12-26 17:09:17 +0100 CommitAuthor: Matthias Krack CommitSubject: Sync arch files with toolchain Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=3169bf56b7b69a13599bda2029f1ce159e56e4d8 Sending build context to Docker daemon 366.3MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 6e3729cf69e0: Already exists Digest: sha256:27cb6e6ccef575a4698b66f5de06c7ecd61589132d5a91d098f7f3f9285415a9 Status: Downloaded newer image for ubuntu:22.04 ---> 6b7dfa7e8fdb Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> e98199835f6f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> ccd07bf8588a Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 0aa7ad9d2809 Step 5/42 : RUN mkdir scripts ---> Using cache ---> e9459f85bb88 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 ---> 47c0caf3dab5 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 19088ac45e1f Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 92805a05cd8b Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> d51b4a6b3b7e Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> a18c614ddaa6 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 903dd37eb616 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> edb2bb8e5397 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 983b8bd5f663 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> b11ff944488d Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 2eee06160ddd Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 29b956f4a893 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 4b0375880c86 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 7747b12e843c Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 69369a62bc3e Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 109ed49835ab Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> a66a98b073fa Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 8aa98cc26e67 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 903c6ab45084 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> d7b7f3bd5079 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 6d0e2976a856 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> b1bcffa148c3 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> c6363caf72af Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 75d9416d8ec9 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 71ee22c39b1f Step 30/42 : COPY ./Makefile . ---> Using cache ---> 0cb1f5208e76 Step 31/42 : COPY ./src ./src ---> Using cache ---> 80fac2b01bfb Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 05c1b9fd7dac Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 715560a17171 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 6cdfb0f12ca0 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 6cdfb0f12ca0 ---> a906e1d5d9dc Step 35/42 : COPY ./data ./data ---> ba1a6a01bfb1 Step 36/42 : COPY ./tests ./tests ---> e024c8da463d Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> b1cd51363438 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 7c3ad7631409 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 30870f820722 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 427c0f3e5118 ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 69 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 0.029 0.029 84.998 84.998 qs_mol_dyn_low 1 2.0 0.003 0.003 84.393 84.393 qs_forces 11 3.9 0.001 0.001 84.354 84.354 qs_energies 11 4.9 0.001 0.001 78.370 78.370 scf_env_do_scf 11 5.9 0.001 0.001 67.703 67.703 velocity_verlet 10 3.0 0.002 0.002 55.214 55.214 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 51.764 51.764 rebuild_ks_matrix 119 8.3 0.001 0.001 19.747 19.747 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 19.746 19.746 qs_rho_update_rho_low 119 7.7 0.001 0.001 18.815 18.815 calculate_rho_elec 119 8.7 0.948 0.948 18.814 18.814 dbcsr_multiply_generic 2286 12.5 0.159 0.159 18.749 18.749 qs_scf_new_mos 108 7.5 0.001 0.001 18.586 18.586 qs_scf_loop_do_ot 108 8.5 0.001 0.001 18.586 18.586 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.079 18.079 ot_scf_mini 108 9.5 0.002 0.002 17.284 17.284 init_scf_loop 11 6.9 0.000 0.000 15.809 15.809 grid_collocate_task_list 119 9.7 14.507 14.507 14.507 14.507 prepare_preconditioner 11 7.9 0.000 0.000 13.388 13.388 make_preconditioner 11 8.9 0.000 0.000 13.388 13.388 sum_up_and_integrate 119 10.3 0.494 0.494 12.774 12.774 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.289 12.289 integrate_v_rspace 119 11.3 0.093 0.093 12.279 12.279 ot_mini 108 10.5 0.001 0.001 11.161 11.161 make_m2s 4572 13.5 0.044 0.044 10.404 10.404 grid_integrate_task_list 119 12.3 10.342 10.342 10.342 10.342 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.252 6.252 pw_transfer 1439 11.6 0.062 0.062 5.920 5.920 qs_ot_get_derivative 108 11.5 0.001 0.001 5.877 5.877 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.723 5.723 dbcsr_make_dense_low 5837 15.5 0.066 0.066 5.587 5.587 make_dense_data 5837 16.5 4.958 4.958 5.507 5.507 ot_diis_step 108 11.5 0.004 0.004 5.281 5.281 make_images 4572 14.5 2.072 2.072 5.230 5.230 fft_wrap_pw1pw2_140 487 13.2 0.483 0.483 4.931 4.931 dbcsr_make_images_dense 3978 14.8 0.017 0.017 4.869 4.869 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 4.751 4.751 apply_single 119 13.6 0.000 0.000 4.751 4.751 multiply_cannon 2286 13.5 0.183 0.183 4.713 4.713 cp_fm_cholesky_decompose 22 10.9 4.255 4.255 4.255 4.255 multiply_cannon_loop 2286 14.5 0.041 0.041 4.253 4.253 multiply_cannon_multrec 2286 15.5 4.164 4.164 4.211 4.211 cp_fm_cholesky_invert 11 10.9 3.980 3.980 3.980 3.980 init_scf_run 11 5.9 0.002 0.002 3.831 3.831 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.829 3.829 dbcsr_complete_redistribute 329 12.2 1.875 1.875 3.646 3.646 dbcsr_copy 2102 12.0 0.225 0.225 3.581 3.581 wfi_extrapolate 11 7.9 0.001 0.001 3.377 3.377 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.368 3.368 density_rs2pw 119 9.7 0.004 0.004 3.359 3.359 dbcsr_copy_into_existing 22 7.9 3.325 3.325 3.325 3.325 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.298 3.298 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.888 2.888 qs_create_task_list 11 7.9 0.000 0.000 2.869 2.869 generate_qs_task_list 11 8.9 1.963 1.963 2.869 2.869 fft3d_s 1202 14.6 2.851 2.851 2.856 2.856 qs_ot_get_p 119 10.4 0.001 0.001 2.837 2.837 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.614 2.614 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.545 2.545 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.223 2.223 pw_poisson_solve 119 10.3 0.328 0.328 1.985 1.985 dbcsr_data_release 279534 16.0 1.904 1.904 1.904 1.904 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.862 1.862 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.855 1.855 potential_pw2rs 119 12.3 0.045 0.045 1.845 1.845 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.818 1.818 cp_fm_upper_to_full 72 14.2 1.772 1.772 1.772 1.772 ------------------------------------------------------------------------------- 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 42.369 42.379 qs_mol_dyn_low 1 2.0 0.003 0.004 42.256 42.260 qs_forces 11 3.9 0.001 0.001 42.216 42.216 qs_energies 11 4.9 0.001 0.001 39.268 39.270 scf_env_do_scf 11 5.9 0.000 0.002 35.988 35.989 scf_env_do_scf_inner_loop 108 6.5 0.003 0.017 33.193 33.194 velocity_verlet 10 3.0 0.001 0.003 25.219 25.220 rebuild_ks_matrix 119 8.3 0.000 0.001 15.363 15.475 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.017 15.362 15.475 qs_ks_update_qs_env 119 7.6 0.001 0.001 13.581 13.685 dbcsr_multiply_generic 2286 12.5 0.070 0.076 12.380 12.613 qs_rho_update_rho_low 119 7.7 0.001 0.001 12.419 12.427 calculate_rho_elec 119 8.7 0.030 0.031 12.418 12.426 sum_up_and_integrate 119 10.3 0.029 0.033 11.437 11.454 integrate_v_rspace 119 11.3 0.004 0.005 11.407 11.425 qs_scf_new_mos 108 7.5 0.001 0.001 9.727 9.844 qs_scf_loop_do_ot 108 8.5 0.001 0.001 9.727 9.843 multiply_cannon 2286 13.5 0.145 0.156 9.190 9.673 ot_scf_mini 108 9.5 0.002 0.002 9.130 9.240 multiply_cannon_loop 2286 14.5 0.092 0.104 8.695 9.176 grid_collocate_task_list 119 9.7 8.841 9.167 8.841 9.167 grid_integrate_task_list 119 12.3 7.945 8.082 7.945 8.082 mp_waitall_1 158411 16.6 7.007 7.677 7.007 7.677 multiply_cannon_metrocomm3 18288 15.5 0.036 0.040 5.021 5.811 ot_mini 108 10.5 0.001 0.001 5.292 5.414 rs_pw_transfer 974 11.9 0.010 0.012 3.892 4.292 density_rs2pw 119 9.7 0.005 0.006 3.246 3.646 pw_transfer 1439 11.6 0.097 0.109 3.190 3.234 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.027 3.067 multiply_cannon_multrec 18288 15.5 2.895 3.040 2.904 3.048 potential_pw2rs 119 12.3 0.006 0.007 2.981 2.995 qs_ot_get_derivative 108 11.5 0.001 0.001 2.694 2.802 init_scf_loop 11 6.9 0.000 0.000 2.782 2.782 fft_wrap_pw1pw2_140 487 13.2 0.259 0.288 2.599 2.677 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.509 2.639 apply_single 119 13.6 0.000 0.000 2.509 2.639 ot_diis_step 108 11.5 0.003 0.003 2.577 2.578 init_scf_run 11 5.9 0.000 0.004 2.315 2.315 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.315 2.315 fft3d_ps 1201 14.6 1.179 1.259 2.163 2.220 make_m2s 4572 13.5 0.044 0.048 2.139 2.202 wfi_extrapolate 11 7.9 0.001 0.001 2.095 2.095 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.918 1.929 make_images 4572 14.5 0.113 0.116 1.826 1.895 mp_waitany 9880 13.7 1.167 1.530 1.167 1.530 qs_ot_get_p 119 10.4 0.001 0.001 1.151 1.291 rs_pw_transfer_RS2PW_140 130 11.5 0.184 0.234 0.867 1.271 rs_pw_transfer_PW2RS_140 130 13.9 0.356 0.409 1.145 1.188 make_images_data 4572 15.5 0.034 0.040 1.009 1.131 prepare_preconditioner 11 7.9 0.000 0.000 1.095 1.108 make_preconditioner 11 8.9 0.000 0.000 1.095 1.108 multiply_cannon_metrocomm1 18288 15.5 0.018 0.020 0.484 1.045 mp_sum_l 11218 13.2 0.631 1.025 0.631 1.025 make_full_inverse_cholesky 11 9.9 0.000 0.000 0.990 1.011 hybrid_alltoall_any 4725 16.4 0.061 0.188 0.891 1.010 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.856 0.952 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.881 0.937 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.840 0.894 mp_alltoall_d11v 2130 13.8 0.670 0.883 0.670 0.883 mp_alltoall_z22v 1201 16.6 0.735 0.874 0.735 0.874 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.869 0.871 ------------------------------------------------------------------------------- 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=46.772, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.507, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.342, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.958, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.255, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.164, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=14.502000000000002, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.841, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=7.945, 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=2.895, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=1.179, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.007, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.032 0.032 109.267 109.267 qs_mol_dyn_low 1 2.0 0.003 0.003 108.614 108.614 qs_forces 11 3.9 0.001 0.001 108.576 108.576 qs_energies 11 4.9 0.001 0.001 101.091 101.091 scf_env_do_scf 11 5.9 0.001 0.001 88.598 88.598 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 70.513 70.513 velocity_verlet 10 3.0 0.002 0.002 70.079 70.079 rebuild_ks_matrix 107 8.3 0.001 0.001 32.969 32.969 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 32.969 32.969 qs_rho_update_rho_low 107 7.7 0.000 0.000 31.088 31.088 calculate_rho_elec 107 8.7 0.851 0.851 31.087 31.087 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.584 29.584 grid_collocate_task_list 107 9.7 26.974 26.974 26.974 26.974 sum_up_and_integrate 107 10.3 0.446 0.446 26.523 26.523 integrate_v_rspace 107 11.3 0.085 0.085 26.077 26.077 grid_integrate_task_list 107 12.3 24.286 24.286 24.286 24.286 init_scf_loop 11 6.9 0.000 0.000 17.892 17.892 dbcsr_multiply_generic 1966 12.4 0.138 0.138 16.959 16.959 qs_scf_new_mos 96 7.5 0.001 0.001 16.534 16.534 qs_scf_loop_do_ot 96 8.5 0.001 0.001 16.534 16.534 ot_scf_mini 96 9.5 0.002 0.002 15.394 15.394 prepare_preconditioner 11 7.9 0.000 0.000 13.868 13.868 make_preconditioner 11 8.9 0.000 0.000 13.868 13.868 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.727 12.727 ot_mini 96 10.5 0.001 0.001 9.952 9.952 make_m2s 3932 13.4 0.039 0.039 9.496 9.496 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.502 6.502 pw_transfer 1295 11.6 0.055 0.055 5.650 5.650 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.479 5.479 init_scf_run 11 5.9 0.002 0.002 5.362 5.362 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.360 5.360 qs_ot_get_derivative 96 11.5 0.001 0.001 5.164 5.164 dbcsr_make_dense_low 4961 15.5 0.056 0.056 5.023 5.023 make_dense_data 4961 16.5 4.454 4.454 4.955 4.955 make_images 3932 14.4 1.901 1.901 4.807 4.807 ot_diis_step 96 11.5 0.003 0.003 4.785 4.785 fft_wrap_pw1pw2_140 439 13.2 0.529 0.529 4.753 4.753 wfi_extrapolate 11 7.9 0.001 0.001 4.664 4.664 cp_fm_cholesky_decompose 22 10.9 4.628 4.628 4.628 4.628 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.459 4.459 apply_single 107 13.6 0.000 0.000 4.459 4.459 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.413 4.413 multiply_cannon 1966 13.4 0.149 0.149 4.251 4.251 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.228 4.228 cp_fm_cholesky_invert 11 10.9 3.929 3.929 3.929 3.929 multiply_cannon_loop 1966 14.4 0.034 0.034 3.861 3.861 dbcsr_complete_redistribute 317 12.2 1.871 1.871 3.844 3.844 multiply_cannon_multrec 1966 15.4 3.781 3.781 3.826 3.826 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.689 3.689 dbcsr_copy 1855 11.9 0.195 0.195 3.404 3.404 qs_create_task_list 11 7.9 0.000 0.000 3.329 3.329 generate_qs_task_list 11 8.9 2.408 2.408 3.329 3.329 density_rs2pw 107 9.7 0.004 0.004 3.262 3.262 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.255 3.255 dbcsr_copy_into_existing 22 7.9 3.161 3.161 3.161 3.161 copy_dbcsr_to_fm 147 11.2 0.002 0.002 2.999 2.999 fft3d_s 1082 14.6 2.726 2.726 2.730 2.730 qs_ot_get_p 107 10.4 0.001 0.001 2.524 2.524 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.406 2.406 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.313 2.313 ------------------------------------------------------------------------------- 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 0.020 69.776 69.786 qs_mol_dyn_low 1 2.0 0.003 0.003 69.677 69.681 qs_forces 11 3.9 0.001 0.001 69.627 69.627 qs_energies 11 4.9 0.001 0.001 64.843 64.845 scf_env_do_scf 11 5.9 0.000 0.002 59.897 59.897 scf_env_do_scf_inner_loop 96 6.5 0.002 0.018 55.308 55.309 velocity_verlet 10 3.0 0.002 0.003 41.700 41.701 rebuild_ks_matrix 107 8.3 0.000 0.001 30.100 30.155 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.015 30.099 30.155 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.414 26.460 sum_up_and_integrate 107 10.3 0.032 0.036 26.345 26.364 integrate_v_rspace 107 11.3 0.004 0.004 26.313 26.335 qs_rho_update_rho_low 107 7.7 0.000 0.001 25.270 25.274 calculate_rho_elec 107 8.7 0.026 0.028 25.269 25.273 grid_integrate_task_list 107 12.3 22.636 23.055 22.636 23.055 grid_collocate_task_list 107 9.7 21.701 22.011 21.701 22.011 dbcsr_multiply_generic 1966 12.4 0.064 0.067 12.119 12.299 multiply_cannon 1966 13.4 0.130 0.147 9.179 9.467 qs_scf_new_mos 96 7.5 0.000 0.001 9.298 9.395 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.298 9.394 multiply_cannon_loop 1966 14.4 0.088 0.102 8.710 9.013 ot_scf_mini 96 9.5 0.002 0.002 8.742 8.840 mp_waitall_1 136719 16.5 7.194 7.759 7.194 7.759 multiply_cannon_metrocomm3 15728 15.4 0.034 0.038 5.239 5.922 ot_mini 96 10.5 0.001 0.003 5.151 5.258 rs_pw_transfer 878 11.9 0.009 0.011 4.023 4.632 init_scf_loop 11 6.9 0.000 0.000 4.576 4.577 init_scf_run 11 5.9 0.000 0.005 3.915 3.915 scf_env_initial_rho_setup 11 6.9 0.000 0.004 3.914 3.915 density_rs2pw 107 9.7 0.005 0.010 3.233 3.829 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.807 3.820 wfi_extrapolate 11 7.9 0.001 0.001 3.558 3.559 multiply_cannon_multrec 15728 15.4 2.719 2.967 2.728 2.977 pw_transfer 1295 11.6 0.088 0.104 2.893 2.967 potential_pw2rs 107 12.3 0.006 0.007 2.865 2.878 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 2.746 2.817 qs_ot_get_derivative 96 11.5 0.001 0.001 2.595 2.689 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.505 2.611 apply_single 107 13.6 0.000 0.000 2.505 2.611 ot_diis_step 96 11.5 0.003 0.003 2.533 2.533 fft_wrap_pw1pw2_140 439 13.2 0.232 0.257 2.362 2.451 make_m2s 3932 13.4 0.040 0.047 2.014 2.068 fft3d_ps 1081 14.6 1.065 1.156 1.954 2.025 mp_waitany 8968 13.7 1.337 2.001 1.337 2.001 make_images 3932 14.4 0.102 0.106 1.728 1.786 mp_alltoall_d11v 1998 13.7 0.997 1.663 0.997 1.663 rs_pw_transfer_RS2PW_140 118 11.5 0.164 0.207 1.004 1.623 rs_gather_matrices 107 12.3 0.067 0.073 0.776 1.414 ------------------------------------------------------------------------------- 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=41.21499999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=26.974, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.286, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.628, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.454, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=3.929, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.781, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", 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=14.188999999999986, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.701, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.636, 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="make_dense_data", label="make_dense_data", 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=2.719, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.337, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.194, 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 0.191 0.191 104.742 104.742 qs_energies 1 2.0 0.000 0.000 103.925 103.925 scf_env_do_scf 1 3.0 0.000 0.000 102.821 102.821 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.265 97.265 rebuild_ks_matrix 7 6.0 0.000 0.000 97.211 97.211 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.211 97.211 hfx_ks_matrix 7 8.0 0.000 0.000 88.168 88.168 integrate_four_center 7 9.0 1.514 1.514 88.109 88.109 integrate_four_center_main 7 10.0 0.645 0.645 80.658 80.658 integrate_four_center_bin 448 11.0 80.012 80.012 80.012 80.012 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.407 56.407 init_scf_loop 1 4.0 0.000 0.000 46.401 46.401 integrate_four_center_load 7 10.0 0.000 0.000 5.674 5.674 hfx_load_balance 1 11.0 0.013 0.013 5.674 5.674 qs_vxc_create 14 8.0 0.000 0.000 3.157 3.157 xc_vxc_pw_create 14 9.0 0.130 0.130 3.157 3.157 prepare_preconditioner 1 5.0 0.000 0.000 2.837 2.837 make_preconditioner 1 6.0 0.000 0.000 2.837 2.837 hfx_load_balance_bin 1 12.0 2.825 2.825 2.825 2.825 hfx_load_balance_count 1 12.0 2.820 2.820 2.820 2.820 xc_rho_set_and_dset_create 14 10.0 0.098 0.098 2.390 2.390 calculate_rho_elec 15 7.4 0.117 0.117 2.377 2.377 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.315 2.315 ------------------------------------------------------------------------------- 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 0.212 0.239 94.069 94.081 qs_energies 1 2.0 0.000 0.000 93.713 93.720 scf_env_do_scf 1 3.0 0.000 0.000 93.376 93.376 qs_ks_update_qs_env 8 5.0 0.000 0.000 91.454 91.454 rebuild_ks_matrix 7 6.0 0.000 0.000 91.445 91.446 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 91.445 91.446 hfx_ks_matrix 7 8.0 0.000 0.000 86.243 86.244 integrate_four_center 7 9.0 0.053 0.329 86.235 86.236 integrate_four_center_main 7 10.0 0.003 0.003 78.398 79.553 integrate_four_center_bin 448 11.0 78.395 79.550 78.395 79.550 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 52.078 52.079 init_scf_loop 1 4.0 0.000 0.000 41.296 41.296 integrate_four_center_load 7 10.0 0.000 0.000 5.798 5.799 hfx_load_balance 1 11.0 0.001 0.001 5.798 5.799 hfx_load_balance_bin 1 12.0 2.768 2.897 2.768 2.897 hfx_load_balance_count 1 12.0 2.769 2.897 2.769 2.897 mp_sync 70 11.3 1.385 2.628 1.385 2.628 qs_vxc_create 14 8.0 0.000 0.000 2.386 2.386 xc_vxc_pw_create 14 9.0 0.007 0.008 2.385 2.385 xc_rho_set_and_dset_create 14 10.0 0.009 0.011 1.895 2.004 ------------------------------------------------------------------------------- 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=16.735000000000014, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.012, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.825, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.82, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.514, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.645, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.191, 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=8.483999999999995, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.395, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.768, 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="integrate_four_center", label="integrate_four_center", y=0.053, 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=0.212, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=1.385, 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 82.061 82.061 qs_energies 1 2.0 0.000 0.000 81.678 81.678 mp2_main 1 3.0 0.000 0.000 79.030 79.030 mp2_gpw_main 1 4.0 0.000 0.000 78.932 78.932 rpa_ri_compute_en 1 5.0 0.000 0.000 75.273 75.273 rpa_num_int 1 6.0 0.001 0.001 75.267 75.267 compute_mat_P_omega 1 7.0 0.003 0.003 65.721 65.721 compute_mat_P_omega_contract 10 8.0 8.733 8.733 65.526 65.526 dbt_total 2336 9.6 0.011 0.011 52.065 52.065 dbt_contract 787 11.0 0.033 0.033 45.326 45.326 dbt_tas_total 1149 12.2 0.211 0.211 44.491 44.491 dbt_tas_multiply 807 12.1 0.003 0.003 43.129 43.129 dbt_tas_dbm 807 14.1 0.003 0.003 36.689 36.689 dbm_multiply 807 16.1 36.681 36.681 36.681 36.681 dbt_tas_mm_1N 524 15.1 0.002 0.002 29.626 29.626 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 28.221 28.221 compute_mat_P_omega_calc_M_occ 250 9.0 8.729 8.729 16.634 16.634 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.586 6.586 dbt_tas_mm_2 251 15.0 0.001 0.001 5.620 5.620 dbt_copy 1103 10.7 0.055 0.055 5.361 5.361 compute_QP_energies 1 7.0 0.000 0.000 4.942 4.942 compute_self_energy_cubic_gw 1 8.0 0.054 0.054 4.941 4.941 contract_cubic_gw 21 9.0 0.000 0.000 3.949 3.949 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.652 3.652 dbt_tas_reserve_blocks_index 3261 14.3 0.143 0.143 3.316 3.316 dbm_reserve_blocks 3628 15.3 3.235 3.235 3.235 3.235 scf_env_do_scf 1 3.0 0.000 0.000 2.547 2.547 scf_env_do_scf_inner_loop 17 4.0 0.001 0.001 2.547 2.547 dbt_reserve_blocks_index 2280 13.1 0.049 0.049 2.497 2.497 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.450 2.450 convert_to_new_pgrid 2421 14.1 0.101 0.101 2.281 2.281 dbt_tas_copy 574 11.4 1.328 1.328 2.211 2.211 dbm_copy 1614 15.1 2.179 2.179 2.179 2.179 dbt_crop 1042 12.0 1.344 1.344 2.098 2.098 dbt_tas_reshape 367 15.0 0.007 0.007 2.089 2.089 compute_W_cubic_GW 10 7.0 0.010 0.010 1.918 1.918 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.844 1.844 get_2c_integrals 1 6.0 0.000 0.000 1.756 1.756 dbt_reshape 278 11.9 0.926 0.926 1.750 1.750 ------------------------------------------------------------------------------- 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 0.005 0.024 30.082 30.091 qs_energies 1 2.0 0.000 0.000 29.992 29.994 mp2_main 1 3.0 0.000 0.001 29.108 29.110 mp2_gpw_main 1 4.0 0.000 0.000 29.075 29.077 rpa_ri_compute_en 1 5.0 0.000 0.000 27.782 27.784 rpa_num_int 1 6.0 0.000 0.002 27.781 27.783 dbt_total 2336 9.6 0.011 0.011 24.705 24.712 compute_mat_P_omega 1 7.0 0.001 0.005 23.650 23.674 compute_mat_P_omega_contract 10 8.0 0.403 0.420 23.540 23.543 dbt_contract 787 11.0 0.024 0.025 18.549 18.551 dbt_tas_total 1149 12.2 0.049 0.055 16.608 16.610 dbt_tas_multiply 807 12.1 0.002 0.002 16.560 16.562 dbt_tas_dbm 807 14.1 0.003 0.003 12.443 12.446 dbm_multiply 807 16.1 9.681 10.452 9.681 10.452 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.005 7.005 compute_mat_P_omega_calc_M_occ 250 9.0 0.384 0.396 6.907 6.907 dbt_tas_mm_2 251 15.0 0.001 0.001 5.881 5.881 dbt_copy 1111 10.7 0.011 0.012 5.412 5.621 dbt_reshape 1098 11.7 2.072 2.213 5.163 5.360 mp_sync 8706 11.6 4.371 5.330 4.371 5.330 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.001 5.002 dbt_tas_mm_1N 524 15.1 0.001 0.001 4.448 4.837 compute_QP_energies 1 7.0 0.000 0.000 2.664 2.665 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 2.662 2.663 mp_waitall_2 3776 15.3 2.424 2.659 2.424 2.659 dbt_communicate_buffer 1098 12.7 0.053 0.058 2.466 2.579 contract_cubic_gw 21 9.0 0.000 0.000 2.128 2.128 dbt_reserve_blocks_index 2849 13.1 0.061 0.066 1.517 1.724 dbt_reserve_blocks_index_array 2791 12.2 0.010 0.011 1.509 1.714 dbt_tas_reserve_blocks_index 3300 14.5 0.115 0.122 1.488 1.692 dbm_reserve_blocks 3696 15.4 1.460 1.666 1.460 1.666 dbt_crop 1042 12.0 0.885 0.981 1.355 1.506 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.291 1.292 dbt_tas_replicate 396 14.1 0.523 0.685 1.068 1.128 convert_to_new_pgrid 2421 14.1 0.023 0.026 0.780 0.974 dbm_copy 1608 15.1 0.751 0.951 0.751 0.951 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.945 0.947 parallel_gemm_fm 105 8.4 0.000 0.000 0.874 0.882 parallel_gemm_fm_cosma 105 9.4 0.874 0.882 0.874 0.882 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.871 0.873 scf_env_do_scf 1 3.0 0.000 0.000 0.847 0.847 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.847 0.847 mp_max_i 1994 9.8 0.520 0.704 0.520 0.704 compute_W_cubic_GW 10 7.0 0.001 0.001 0.658 0.661 ------------------------------------------------------------------------------- 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=21.578000000000003, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=36.681, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.733, 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=8.729, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.235, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.179, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.926, 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=8.536000000000001, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.681, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.403, 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=0.384, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.46, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.751, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.072, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.371, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.424, 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 0.017 0.017 296.102 296.102 qs_forces 1 2.0 0.000 0.000 295.556 295.556 rebuild_ks_matrix 7 6.6 0.000 0.000 294.058 294.058 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 294.058 294.058 hfx_ks_matrix 7 8.6 0.000 0.000 292.224 292.224 hfx_ri_update_ks 7 9.6 0.000 0.000 253.029 253.029 hfx_ri_update_ks_Pmat 7 10.6 30.921 30.921 253.025 253.025 dbt_total 841 11.0 0.005 0.005 238.538 238.538 qs_energies 1 3.0 0.000 0.000 220.559 220.559 scf_env_do_scf 1 4.0 0.000 0.000 220.202 220.202 dbt_contract 207 12.4 0.027 0.027 219.955 219.955 dbt_tas_total 375 13.4 1.386 1.386 219.502 219.502 qs_ks_update_qs_env 8 6.0 0.000 0.000 219.110 219.110 dbt_tas_multiply 216 13.5 0.001 0.001 215.218 215.218 dbt_tas_dbm 216 15.5 0.001 0.001 203.695 203.695 dbm_multiply 216 17.5 203.692 203.692 203.692 203.692 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.000 198.626 198.626 dbt_tas_mm_2 91 16.5 0.001 0.001 190.423 190.423 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 138.093 138.093 init_scf_loop 2 5.0 0.000 0.000 82.107 82.107 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 74.952 74.952 hfx_ri_update_forces 1 7.0 1.571 1.571 39.191 39.191 hfx_ri_forces_Pmat_3c 1 8.0 4.720 4.720 22.538 22.538 dbt_copy 409 11.7 0.047 0.047 14.292 14.292 precalc_derivatives 1 8.0 2.216 2.216 12.730 12.730 dbt_reshape 132 13.2 6.307 6.307 10.128 10.128 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.398 9.398 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.097 9.097 build_3c_derivatives 3 9.0 2.444 2.444 6.925 6.925 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.693 6.693 dbt_tas_reserve_blocks_index 1287 15.4 0.274 0.274 6.627 6.627 dbm_reserve_blocks 1461 16.2 6.523 6.523 6.523 6.523 ------------------------------------------------------------------------------- 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 0.006 0.020 43.194 43.204 qs_forces 1 2.0 0.000 0.000 43.058 43.058 rebuild_ks_matrix 7 6.6 0.000 0.000 42.410 42.410 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 42.410 42.410 hfx_ks_matrix 7 8.6 0.000 0.000 41.490 41.499 dbt_total 841 11.0 0.005 0.005 36.874 36.878 dbt_contract 207 12.4 0.020 0.021 29.092 29.103 dbt_tas_total 375 13.4 0.063 0.194 27.105 27.105 dbt_tas_multiply 216 13.5 0.001 0.001 26.140 26.141 hfx_ri_update_ks 7 9.6 0.000 0.000 24.055 24.055 hfx_ri_update_ks_Pmat 7 10.6 1.196 1.268 24.050 24.054 qs_energies 1 3.0 0.000 0.000 22.648 22.648 scf_env_do_scf 1 4.0 0.000 0.001 22.513 22.513 qs_ks_update_qs_env 8 6.0 0.000 0.000 22.010 22.010 dbt_tas_dbm 216 15.5 0.001 0.001 20.905 20.912 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 20.401 20.401 dbm_multiply 216 17.5 18.473 19.574 18.473 19.574 hfx_ri_update_forces 1 7.0 0.055 0.059 17.434 17.443 hfx_ri_forces_Pmat_3c 1 8.0 0.165 0.176 13.087 13.100 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 12.600 12.600 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 11.408 11.409 init_scf_loop 2 5.0 0.000 0.000 9.912 9.913 dbt_tas_mm_2 91 16.5 0.001 0.001 9.647 9.655 mp_sync 2909 12.8 4.438 6.784 4.438 6.784 dbt_copy 421 11.8 0.010 0.016 6.416 6.628 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.743 6.100 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.812 4.812 dbt_reshape 252 12.8 2.221 2.289 4.380 4.500 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.866 4.197 precalc_derivatives 1 8.0 0.079 0.084 3.319 3.319 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.063 3.063 dbm_reserve_blocks 1477 16.3 2.472 2.733 2.472 2.733 dbt_tas_reserve_blocks_index 1302 15.5 0.221 0.237 2.463 2.724 dbt_crop 372 13.7 1.678 1.763 2.284 2.407 mp_waitall_2 1204 16.3 2.133 2.237 2.133 2.237 dbt_reserve_blocks_index 938 14.4 0.088 0.095 1.937 2.153 dbt_reserve_blocks_index_array 915 13.4 0.005 0.006 1.915 2.134 build_3c_derivatives 3 9.0 0.222 0.243 1.879 1.887 dbt_tas_replicate 175 15.2 0.676 0.707 1.650 1.702 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.600 1.604 convert_to_new_pgrid 648 15.5 0.033 0.061 1.296 1.550 dbt_communicate_buffer 252 13.8 0.012 0.013 1.432 1.500 dbt_tas_copy 169 12.8 0.807 0.861 1.401 1.499 dbm_copy 452 16.3 1.134 1.391 1.134 1.391 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.329 1.330 dbt_tas_communicate_buffer 352 16.4 0.013 0.013 0.926 0.979 ------------------------------------------------------------------------------- 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=43.93899999999999, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=203.692, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=30.921, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=6.523, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.307, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.72, 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=12.096000000000004, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=18.473, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.196, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.472, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.221, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.165, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.438, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.133, 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 0.014 184.903 184.903 qs_energies 1 2.0 0.000 0.000 184.721 184.721 mp2_main 1 3.0 0.000 0.000 180.009 180.009 mp2_gpw_main 1 4.0 0.001 0.001 179.569 179.569 mp2_ri_gpw_compute_in 1 5.0 0.383 0.383 130.244 130.244 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 119.085 119.085 mp2_eri_3c_integrate_gpw 2656 7.0 0.012 0.012 88.609 88.609 integrate_v_rspace 2666 8.0 0.588 0.588 75.830 75.830 grid_integrate_task_list 2666 9.0 73.274 73.274 73.274 73.274 mp2_ri_gpw_compute_en 1 5.0 0.087 0.087 49.300 49.300 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.915 9.915 47.520 47.520 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.090 2.090 30.107 30.107 local_gemm 2080 8.0 28.016 28.016 28.016 28.016 dbcsr_multiply_generic 5322 8.0 0.178 0.178 20.903 20.903 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.863 20.863 pw_transfer 63872 10.6 1.036 1.036 11.490 11.490 calculate_wavefunction 2656 8.0 8.082 8.082 11.474 11.474 get_2c_integrals 1 6.0 0.000 0.000 10.775 10.775 multiply_cannon 5322 9.0 0.501 0.501 10.558 10.558 fft_wrap_pw1pw2 53228 11.4 0.109 0.109 10.257 10.257 compute_2c_integrals 1 7.0 0.006 0.006 9.951 9.951 compute_2c_integrals_loop_lm 1 8.0 0.011 0.011 9.931 9.931 mp2_eri_2c_integrate_gpw 1 9.0 3.332 3.332 9.920 9.920 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.195 2.195 9.500 9.500 multiply_cannon_loop 5322 10.0 0.131 0.131 9.036 9.036 make_m2s 10644 9.0 0.061 0.061 8.299 8.299 make_images 10644 10.0 3.271 3.271 7.924 7.924 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 7.906 7.906 multiply_cannon_multrec 5322 11.0 7.508 7.508 7.547 7.547 fft_wrap_pw1pw2_20 21271 12.4 0.456 0.456 7.329 7.329 dbcsr_complete_redistribute 2689 9.0 1.116 1.116 6.387 6.387 fft3d_s 53229 13.4 6.275 6.275 6.310 6.310 dbcsr_finalize 10708 9.5 0.200 0.200 5.876 5.876 mp2_ri_gpw_compute_en_ener 2080 7.0 5.633 5.633 5.633 5.633 dbcsr_merge_all 8011 10.3 4.117 4.117 5.221 5.221 scf_env_do_scf 1 3.0 0.000 0.000 4.318 4.318 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.318 4.318 potential_pw2rs 5322 10.0 0.144 0.144 3.863 3.863 ------------------------------------------------------------------------------- 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 0.005 0.020 33.821 33.831 qs_energies 1 2.0 0.000 0.000 33.734 33.735 mp2_main 1 3.0 0.000 0.001 31.831 31.831 mp2_gpw_main 1 4.0 0.001 0.002 31.727 31.727 mp2_ri_gpw_compute_in 1 5.0 0.051 0.054 16.820 17.233 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.650 16.046 mp2_ri_gpw_compute_en 1 5.0 0.161 0.180 14.823 15.020 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.686 13.915 integrate_v_rspace 93 8.1 0.097 0.107 13.548 13.778 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.780 0.869 13.759 13.771 grid_integrate_task_list 93 9.1 13.267 13.498 13.267 13.498 mp2_ri_gpw_compute_en_expansio 65 7.0 0.096 0.112 10.374 10.526 local_gemm 65 8.0 10.278 10.431 10.278 10.431 mp2_ri_gpw_compute_en_comm 17 7.0 0.063 0.075 2.260 2.635 mp_sendrecv_dm3 1054 8.0 1.754 2.184 1.754 2.184 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.687 1.913 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.670 1.896 scf_env_do_scf 1 3.0 0.000 0.000 1.790 1.790 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.790 1.790 get_2c_integrals 1 6.0 0.000 0.000 1.101 1.127 multiply_cannon 176 9.0 0.015 0.016 1.010 1.093 multiply_cannon_loop 176 10.0 0.002 0.002 0.954 1.035 qs_scf_new_mos 10 5.0 0.000 0.000 0.881 0.885 multiply_cannon_multrec 246 11.0 0.825 0.870 0.830 0.876 eigensolver 11 5.8 0.001 0.001 0.857 0.859 compute_2c_integrals 1 7.0 0.003 0.003 0.808 0.826 make_m2s 352 9.0 0.003 0.003 0.643 0.782 pw_transfer 2120 10.5 0.043 0.044 0.733 0.771 make_images 352 10.0 0.050 0.052 0.631 0.770 compute_2c_integrals_loop_lm 1 8.0 0.002 0.003 0.722 0.743 mp2_eri_2c_integrate_gpw 1 9.0 0.196 0.198 0.721 0.742 fft_wrap_pw1pw2 1768 11.4 0.004 0.004 0.677 0.714 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.706 0.706 cp_fm_redistribute_end 11 7.8 0.263 0.695 0.277 0.700 ------------------------------------------------------------------------------- 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=58.10800000000002, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=73.274, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=28.016, 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=9.915, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.082, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.508, 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=6.9169999999999945, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.267, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.278, 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=0.78, 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=0.825, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.754, 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 0.086 0.086 122.970 122.970 qs_energies 1 2.0 0.000 0.000 121.608 121.608 scf_env_do_scf 1 3.0 0.000 0.000 115.091 115.091 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 115.091 115.091 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.437 48.437 rebuild_ks_matrix 15 6.0 0.000 0.000 48.231 48.231 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.231 48.231 qs_scf_new_mos 15 5.0 0.000 0.000 42.065 42.065 eigensolver 15 6.0 0.001 0.001 34.165 34.165 qs_vxc_create 15 8.0 0.017 0.017 33.011 33.011 calculate_dispersion_nonloc 15 9.0 6.617 6.617 28.783 28.783 pw_transfer 1191 10.0 0.058 0.058 22.725 22.725 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 22.561 22.561 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.716 21.716 calculate_rho_elec 16 6.0 0.217 0.217 21.715 21.715 cp_fm_diag_elpa 15 7.0 0.000 0.000 21.383 21.383 cp_fm_diag_elpa_base 15 8.0 18.831 18.831 21.383 21.383 grid_collocate_task_list 16 7.0 20.361 20.361 20.361 20.361 fft_wrap_pw1pw2_150 765 12.0 3.536 3.536 16.383 16.383 sum_up_and_integrate 15 8.0 0.104 0.104 14.036 14.036 integrate_v_rspace 15 9.0 0.039 0.039 13.932 13.932 grid_integrate_task_list 15 10.0 13.388 13.388 13.388 13.388 cp_fm_cholesky_restore 45 7.0 10.544 10.544 10.544 10.544 fft3d_s 1087 13.0 9.964 9.964 9.971 9.971 pw_scatter_s 585 13.1 7.209 7.209 7.209 7.209 fft_wrap_pw1pw2_200 197 12.3 0.739 0.739 5.992 5.992 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.608 5.608 dbcsr_complete_redistribute 46 8.3 2.188 2.188 5.586 5.586 cp_fm_upper_to_full 30 8.0 4.788 4.788 4.788 4.788 vdW_energy 15 10.0 4.292 4.292 4.292 4.292 xc_vxc_pw_create 15 9.0 0.210 0.210 4.212 4.212 gspace_mixing 14 5.0 0.170 0.170 4.087 4.087 broyden_mixing 14 6.0 3.463 3.463 3.463 3.463 init_scf_run 1 3.0 0.000 0.000 3.047 3.047 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.977 2.977 xc_pw_derive 90 11.0 0.001 0.001 2.776 2.776 calculate_dm_sparse 15 6.0 0.017 0.017 2.639 2.639 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 2.562 2.562 ------------------------------------------------------------------------------- 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 0.029 59.683 59.695 qs_energies 1 2.0 0.000 0.000 59.433 59.438 scf_env_do_scf 1 3.0 0.000 0.001 55.362 55.363 scf_env_do_scf_inner_loop 15 4.0 0.001 0.012 55.362 55.363 qs_ks_update_qs_env 15 5.0 0.000 0.000 22.633 22.639 rebuild_ks_matrix 15 6.0 0.000 0.000 22.601 22.606 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 22.601 22.606 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.590 20.595 calculate_rho_elec 16 6.0 0.007 0.007 20.590 20.595 grid_collocate_task_list 16 7.0 19.137 19.328 19.137 19.328 sum_up_and_integrate 15 8.0 0.011 0.018 13.566 13.608 integrate_v_rspace 15 9.0 0.000 0.001 13.555 13.603 grid_integrate_task_list 15 10.0 12.835 12.958 12.835 12.958 qs_scf_new_mos 15 5.0 0.000 0.000 12.747 12.781 eigensolver 15 6.0 0.001 0.002 11.807 11.828 qs_vxc_create 15 8.0 0.001 0.002 8.762 8.773 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.423 8.429 cp_fm_diag_elpa_base 15 8.0 8.275 8.306 8.420 8.422 calculate_dispersion_nonloc 15 9.0 0.902 0.918 7.064 7.082 pw_transfer 1191 10.0 0.086 0.097 6.468 6.512 fft_wrap_pw1pw2 1086 11.0 0.011 0.013 6.300 6.361 fft3d_ps 1086 13.0 2.372 2.532 4.698 4.873 fft_wrap_pw1pw2_150 765 12.0 0.261 0.290 4.052 4.085 cp_fm_cholesky_restore 45 7.0 3.236 3.271 3.236 3.271 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.449 2.449 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.138 2.353 fft_wrap_pw1pw2_200 197 12.3 0.169 0.197 2.145 2.209 mp_alltoall_z22v 1086 15.0 1.770 2.197 1.770 2.197 xc_vxc_pw_create 15 9.0 0.015 0.018 1.697 1.724 rs_pw_transfer 158 9.4 0.001 0.002 1.378 1.651 density_rs2pw 16 7.0 0.001 0.001 1.339 1.494 x_to_yz 585 14.1 0.326 0.347 1.223 1.426 build_core_ppnl 1 5.0 1.249 1.393 1.249 1.393 init_scf_run 1 3.0 0.000 0.000 1.380 1.381 vdW_energy 15 10.0 1.260 1.314 1.260 1.314 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.291 1.291 yz_to_x 501 13.9 0.206 0.238 1.078 1.280 mp_waitany 520 11.3 0.965 1.204 0.965 1.204 ------------------------------------------------------------------------------- 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=49.882000000000005, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.361, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=18.831, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.388, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.544, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=9.964, 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=13.828000000000003, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.137, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.275, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.835, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.236, 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=2.372, 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 0.081 0.081 325.281 325.281 qs_energies 1 2.0 0.000 0.000 325.139 325.139 ls_scf 1 3.0 0.000 0.000 323.925 323.925 ls_scf_main 1 4.0 0.002 0.002 314.869 314.869 density_matrix_trs4 11 5.0 0.013 0.013 223.603 223.603 arnoldi_extremal 12 6.1 0.000 0.000 139.740 139.740 arnoldi_normal_ev 12 7.1 0.015 0.015 139.739 139.739 dbcsr_matrix_vector_mult 652 9.0 0.184 0.184 137.363 137.363 build_subspace 23 8.1 0.079 0.079 137.042 137.042 dbcsr_matrix_vector_mult_local 652 10.0 135.806 135.806 135.815 135.815 ls_scf_dm_to_ks 11 5.0 0.000 0.000 85.986 85.986 matrix_ls_to_qs 11 6.0 0.000 0.000 82.725 82.725 dbcsr_multiply_generic 185 6.1 0.837 0.837 72.956 72.956 dbcsr_copy_into_existing 11 7.0 44.629 44.629 44.630 44.630 multiply_cannon 185 7.1 0.418 0.418 43.569 43.569 dbcsr_complete_redistribute 23 7.5 30.693 30.693 41.836 41.836 matrix_decluster 11 7.0 0.000 0.000 38.094 38.094 multiply_cannon_loop 185 8.1 0.257 0.257 31.167 31.167 make_m2s 370 7.1 0.037 0.037 24.988 24.988 make_images 370 8.1 10.554 10.554 23.344 23.344 multiply_cannon_multrec 185 9.1 22.136 22.136 22.244 22.244 dbcsr_finalize 646 7.5 0.155 0.155 14.696 14.696 dbcsr_merge_all 597 8.5 2.303 2.303 13.544 13.544 setup_rec_index_2d 370 8.1 11.805 11.805 11.805 11.805 dbcsr_sort_indices 1103 9.9 10.728 10.728 10.728 10.728 tree_to_linear_d 110 9.4 9.988 9.988 9.988 9.988 quick_finalize 395 10.0 0.404 0.404 9.292 9.292 calculate_norms 370 9.1 8.667 8.667 8.667 8.667 dbcsr_special_finalize 370 9.1 0.002 0.002 8.598 8.598 ls_scf_init_scf 1 4.0 0.000 0.000 8.369 8.369 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.039 8.039 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.383 7.383 ------------------------------------------------------------------------------- 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 0.024 63.605 63.615 qs_energies 1 2.0 0.000 0.000 63.509 63.509 ls_scf 1 3.0 0.000 0.000 63.460 63.460 ls_scf_main 1 4.0 0.001 0.009 60.965 60.966 density_matrix_trs4 11 5.0 0.006 0.017 58.580 58.653 dbcsr_multiply_generic 185 6.1 0.056 0.061 55.473 55.782 multiply_cannon 185 7.1 0.034 0.037 46.281 46.631 multiply_cannon_loop 185 8.1 0.113 0.136 43.952 44.536 multiply_cannon_multrec 1480 9.1 27.155 29.743 27.420 30.032 mp_waitall_1 11936 10.3 14.161 17.655 14.161 17.655 multiply_cannon_metrocomm3 1480 9.1 0.013 0.017 8.329 13.651 make_m2s 370 7.1 0.034 0.036 6.397 6.466 make_images 370 8.1 0.624 0.680 6.273 6.343 calculate_norms 2960 9.1 4.729 5.931 4.729 5.931 multiply_cannon_metrocomm1 1480 9.1 0.007 0.009 3.305 5.149 make_images_data 370 9.1 0.009 0.011 2.753 2.948 hybrid_alltoall_any 393 9.9 0.174 0.885 2.398 2.621 mp_sum_l 1119 5.6 1.718 2.376 1.718 2.376 arnoldi_extremal 12 6.1 0.000 0.000 2.292 2.302 arnoldi_normal_ev 12 7.1 0.001 0.004 2.291 2.302 build_subspace 23 8.1 0.019 0.025 2.202 2.204 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.061 2.125 dbcsr_complete_redistribute 23 7.5 1.173 1.213 1.868 1.963 dbcsr_matrix_vector_mult 652 9.0 0.009 0.044 1.887 1.939 ls_scf_init_scf 1 4.0 0.000 0.000 1.922 1.922 matrix_ls_to_qs 11 6.0 0.000 0.000 1.822 1.922 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.897 1.903 matrix_decluster 11 7.0 0.000 0.000 1.684 1.778 make_images_pack 370 9.1 1.597 1.767 1.601 1.771 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.731 1.734 dbcsr_matrix_vector_mult_local 652 10.0 1.572 1.647 1.574 1.649 dbcsr_finalize 646 7.5 0.007 0.008 1.403 1.599 buffer_matrices_ensure_size 370 8.1 1.266 1.421 1.266 1.421 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 0.903 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=71.54499999999999, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=135.806, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=44.629, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.693, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.136, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.805, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.667, 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 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", 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=11.499999999999986, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.572, 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=1.173, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=27.155, 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=4.729, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.718, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.161, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.597, 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 70.363 70.363 lib_test 1 2.0 0.000 0.000 70.355 70.355 dbcsr_run_tests 3 3.0 0.002 0.002 70.355 70.355 test_multiplies_multiproc 3 4.0 0.001 0.001 54.530 54.530 dbcsr_redistribute 9 5.0 35.322 35.322 37.419 37.419 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.800 15.800 dbcsr_make_random_matrix 9 4.0 12.789 12.789 15.719 15.719 multiply_cannon 9 6.0 0.001 0.001 11.188 11.188 multiply_cannon_loop 9 7.0 0.015 0.015 10.831 10.831 multiply_cannon_multrec 9 8.0 10.815 10.815 10.816 10.816 dbcsr_finalize 27 5.7 0.008 0.008 5.407 5.407 dbcsr_merge_all 18 6.5 1.924 1.924 4.685 4.685 dbcsr_data_release 975 7.6 2.762 2.762 2.762 2.762 tree_to_linear_d 9 7.0 1.838 1.838 1.838 1.838 mp_alltoall_d11v 27 6.0 1.751 1.751 1.751 1.751 make_m2s 18 6.0 0.001 0.001 1.567 1.567 make_images 18 7.0 0.543 0.543 1.521 1.521 ------------------------------------------------------------------------------- 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 0.014 17.182 17.186 lib_test 1 2.0 0.000 0.000 17.156 17.173 dbcsr_run_tests 3 3.0 0.000 0.001 17.152 17.168 test_multiplies_multiproc 3 4.0 0.000 0.002 16.327 16.361 dbcsr_multiply_generic 9 5.0 0.001 0.001 14.971 15.077 multiply_cannon 9 6.0 0.001 0.002 13.244 13.517 multiply_cannon_loop 9 7.0 0.002 0.002 12.964 13.286 multiply_cannon_multrec 72 8.0 10.842 11.253 10.843 11.253 mp_waitall_1 576 9.2 2.425 3.029 2.425 3.029 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.873 2.562 dbcsr_data_release 444 7.6 0.783 0.914 0.783 0.914 mp_sum_l 390 2.5 0.415 0.905 0.415 0.905 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.411 0.901 dbcsr_make_random_matrix 9 4.0 0.661 0.668 0.795 0.826 dbcsr_finalize 27 5.7 0.000 0.000 0.674 0.826 dbcsr_destroy 111 5.9 0.000 0.000 0.633 0.763 make_m2s 18 6.0 0.001 0.001 0.645 0.690 make_images 18 7.0 0.021 0.021 0.642 0.687 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.242 0.663 dbcsr_merge_all 18 6.5 0.096 0.117 0.522 0.653 make_images_data 18 8.0 0.000 0.001 0.340 0.431 dbcsr_redistribute 9 5.0 0.229 0.265 0.390 0.416 dbcsr_data_copy_aa2 18 7.5 0.315 0.415 0.315 0.415 hybrid_alltoall_any 18 9.0 0.026 0.115 0.300 0.363 ------------------------------------------------------------------------------- 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=6.750999999999998, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.322, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.789, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.815, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.762, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.924, 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=1.730999999999998, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.229, 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=10.842, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.783, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.096, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.425, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.415, 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 0.049 0.049 129.855 129.855 qs_mol_dyn_low 1 2.0 0.003 0.003 128.481 128.481 velocity_verlet 5 3.0 0.003 0.003 104.639 104.639 qmmm_el_coupling 6 3.8 0.000 0.000 86.090 86.090 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 86.087 86.087 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 85.461 85.461 qmmm_elec_gaussian_low_G 6 6.8 84.554 84.554 84.554 84.554 qs_forces 6 3.8 0.000 0.000 33.994 33.994 qs_energies 6 4.8 0.000 0.000 30.190 30.190 scf_env_do_scf 6 5.8 0.001 0.001 27.969 27.969 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.404 24.404 rebuild_ks_matrix 45 8.4 0.000 0.000 23.557 23.557 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.557 23.557 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.169 20.169 pw_transfer 966 12.3 0.051 0.051 16.821 16.821 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.633 16.633 fft_wrap_pw1pw2_150 507 15.2 2.182 2.182 16.229 16.229 qs_vxc_create 45 10.4 0.001 0.001 13.048 13.048 xc_vxc_pw_create 45 11.4 0.691 0.691 13.047 13.047 xc_pw_derive 270 13.4 0.002 0.002 9.180 9.180 fft3d_s 802 15.6 7.625 7.625 7.633 7.633 qs_rho_update_rho_low 45 7.9 0.000 0.000 6.953 6.953 calculate_rho_elec 45 8.9 0.563 0.563 6.953 6.953 xc_rho_set_and_dset_create 45 12.4 0.620 0.620 6.759 6.759 pw_scatter_s 429 15.8 5.591 5.591 5.591 5.591 xc_pw_divergence 45 12.4 0.001 0.001 5.550 5.550 qmmm_forces 6 3.8 0.002 0.002 5.192 5.192 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 4.856 4.856 pw_integral_ab 2539 7.4 4.476 4.476 4.476 4.476 qs_ks_ddapc 45 10.4 0.001 0.001 4.102 4.102 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.080 4.080 init_scf_loop 6 6.8 0.000 0.000 3.561 3.561 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.395 3.395 qmmm_forces_gaussian_low_G 6 6.8 3.394 3.394 3.394 3.394 sum_up_and_integrate 45 10.4 0.356 0.356 3.313 3.313 density_rs2pw 45 9.9 0.002 0.002 3.221 3.221 grid_collocate_task_list 45 9.9 3.169 3.169 3.169 3.169 integrate_v_rspace 45 11.4 0.006 0.006 2.957 2.957 fist_calc_energy_force 6 3.8 0.001 0.001 2.603 2.603 ------------------------------------------------------------------------------- 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 0.054 51.811 51.821 qs_mol_dyn_low 1 2.0 0.003 0.004 50.823 50.880 qs_forces 6 3.8 0.000 0.000 36.846 36.846 qs_energies 6 4.8 0.000 0.000 35.153 35.153 scf_env_do_scf 6 5.8 0.000 0.001 34.269 34.269 scf_env_do_scf_inner_loop 113 6.2 0.002 0.018 32.898 32.898 rebuild_ks_matrix 119 8.1 0.000 0.000 24.155 24.164 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.017 24.155 24.164 qs_ks_update_qs_env 119 7.3 0.001 0.001 22.744 22.752 velocity_verlet 5 3.0 0.002 0.004 21.471 21.474 pw_transfer 2446 12.3 0.193 0.211 16.019 16.488 fft_wrap_pw1pw2 2059 13.4 0.023 0.030 15.598 16.097 fft_wrap_pw1pw2_150 1321 14.9 1.193 1.433 15.055 15.535 qs_vxc_create 119 10.1 0.002 0.003 12.707 12.709 xc_vxc_pw_create 119 11.1 0.146 0.216 12.705 12.707 fft3d_ps 2059 15.4 6.609 7.384 11.662 12.279 qs_rho_update_rho_low 119 7.3 0.000 0.001 9.926 9.927 calculate_rho_elec 119 8.3 0.048 0.055 9.926 9.926 xc_pw_derive 714 13.1 0.010 0.012 9.527 9.782 sum_up_and_integrate 119 10.1 0.078 0.091 8.423 8.435 integrate_v_rspace 119 11.1 0.003 0.003 8.344 8.362 qmmm_forces 6 3.8 0.002 0.002 7.156 7.156 qmmm_forces_with_gaussian 6 4.8 0.007 0.010 6.836 7.007 xc_pw_divergence 119 12.1 0.005 0.006 6.196 6.421 xc_rho_set_and_dset_create 119 12.1 0.347 0.423 6.165 6.344 rs_pw_transfer 988 11.5 0.010 0.013 5.830 6.091 qmmm_el_coupling 6 3.8 0.000 0.000 5.972 6.083 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 5.970 6.080 density_rs2pw 119 9.3 0.005 0.007 5.497 5.709 potential_pw2rs 119 12.1 0.005 0.006 4.755 4.767 grid_collocate_task_list 119 9.3 4.282 4.518 4.282 4.518 mp_alltoall_z22v 2059 17.4 3.683 4.441 3.683 4.441 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.826 3.876 grid_integrate_task_list 119 12.1 3.358 3.550 3.358 3.550 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.293 3.344 qmmm_forces_gaussian_low_G 6 6.8 3.147 3.198 3.147 3.198 x_to_yz 1095 16.8 0.797 0.892 2.687 2.953 yz_to_x 964 16.0 0.513 0.689 2.306 2.752 qmmm_elec_gaussian_low_G 6 6.8 2.704 2.750 2.704 2.750 pw_restrict_s3 18 5.8 1.310 1.370 2.397 2.558 mp_waitany 4028 12.8 2.152 2.481 2.152 2.481 rs_pw_transfer_PW2RS_150 125 13.9 0.700 0.774 2.172 2.209 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.012 2.122 pw_prolongate_s3 18 6.8 1.110 1.142 2.012 2.122 rs_pw_transfer_RS2PW_150 125 11.2 0.548 0.691 1.725 1.970 qs_scf_new_mos 113 7.2 0.000 0.000 1.919 1.925 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.919 1.925 qs_ks_ddapc 119 10.1 0.002 0.002 1.787 1.852 ot_scf_mini 113 9.2 0.001 0.001 1.838 1.844 dbcsr_multiply_generic 2588 12.3 0.056 0.057 1.727 1.751 pw_scatter_p 1095 15.8 1.507 1.629 1.507 1.629 pw_integral_ab 2761 7.7 1.155 1.254 1.377 1.461 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.421 1.422 pw_gather_p 964 15.0 1.185 1.411 1.185 1.411 init_scf_loop 6 6.8 0.000 0.000 1.368 1.369 mp_sum_dm3 33 5.7 1.174 1.231 1.174 1.231 mp_waitall_1 177795 16.4 1.042 1.163 1.042 1.163 ot_mini 113 10.2 0.000 0.000 1.135 1.142 ------------------------------------------------------------------------------- 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=21.045999999999992, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=84.554, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.625, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.591, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.476, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.394, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.169, 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=26.872999999999998, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.704, 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=1.155, 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=4.282, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.683, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.358, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.609, yerr=0.0 Summary: Performance test took 33 minutes. Status: OK Removing intermediate container 427c0f3e5118 ---> c35f51e72ddf Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in c9eb3dcda84f Removing intermediate container c9eb3dcda84f ---> 074f1645a15c Step 42/42 : ENTRYPOINT [] ---> Running in 863275a7e9ab Removing intermediate container 863275a7e9ab ---> c143499f0330 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built c143499f0330 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: 2022-12-26 19:56:51+00:00