StartDate: 2022-10-17 11:11:04+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 8d96446bea90f37d3e25c2492dcc34fe4f653cd4 CommitTime: 2022-10-17 09:59:57 +0200 CommitAuthor: Matthias Krack CommitSubject: Update arch file Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=8d96446bea90f37d3e25c2492dcc34fe4f653cd4 Sending build context to Docker daemon 365.3MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu cf92e523b49e: Already exists Digest: sha256:35fb073f9e56eb84041b0745cb714eff0f7b225ea9e024f703cab56aaa5c7720 Status: Downloaded newer image for ubuntu:22.04 ---> 216c552ea5ba Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 20d076db758f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 4b417da6a397 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 5f46925292ae Step 5/42 : RUN mkdir scripts ---> Using cache ---> 1d1e6363a04f 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 ---> 1bac43e64090 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 7d17f6081efc Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --mpi-mode=mpich --target-cpu=native --with-gcc=system --dry-run ---> Using cache ---> f50c614e95d1 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> ddd6bdad2541 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 682c93918026 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 0805ee19df5e Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> d61920fb0b41 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> fee9ef523de6 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 015f01497548 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> e565ae84072c Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> afcad32b5a2c Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> d391ad26ab56 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 97ab2d52179f Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 7573c04cf23e Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> a12eac7f9ad5 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> dcd23b0a2e59 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> eebfb6b4d8f0 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 1583721b664c Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 36134a312c8a Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> c7144857ca64 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> ab2dc3df04bf Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 9977e99f1824 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 05ca027b8c41 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> ee097b06524b Step 30/42 : COPY ./Makefile . ---> Using cache ---> b9418e091c7f Step 31/42 : COPY ./src ./src ---> Using cache ---> 9abfeb10e574 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> aa2e461c796d Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 954b1e245422 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 )" ---> Using cache ---> 64394ca43606 Step 35/42 : COPY ./data ./data ---> Using cache ---> f605dd08bcd3 Step 36/42 : COPY ./tests ./tests ---> Using cache ---> e3433efde42a Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> Using cache ---> 64699ea383a6 Step 38/42 : COPY ./benchmarks ./benchmarks ---> Using cache ---> e682d0f2f572 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> Using cache ---> 33e83bccc769 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Using cache ---> 6615acf74415 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Using cache ---> fb85db86202c Step 42/42 : ENTRYPOINT [] ---> Using cache ---> 2251e7ff17df [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 2251e7ff17df Successfully tagged gcr.io/cp2k-org-project/img_cp2k-perf-openmp-arch-be5:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### ========== 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 0.033 0.033 87.112 87.112 qs_mol_dyn_low 1 2.0 0.003 0.003 86.489 86.489 qs_forces 11 3.9 0.001 0.001 86.450 86.450 qs_energies 11 4.9 0.001 0.001 80.429 80.429 scf_env_do_scf 11 5.9 0.001 0.001 69.941 69.941 velocity_verlet 10 3.0 0.002 0.002 56.135 56.135 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 53.846 53.846 rebuild_ks_matrix 119 8.3 0.001 0.001 20.351 20.351 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.350 20.350 dbcsr_multiply_generic 2286 12.5 0.151 0.151 19.636 19.636 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.541 19.541 calculate_rho_elec 119 8.7 0.958 0.958 19.540 19.540 qs_scf_new_mos 108 7.5 0.001 0.001 19.335 19.335 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.334 19.334 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.693 18.693 ot_scf_mini 108 9.5 0.002 0.002 17.936 17.936 init_scf_loop 11 6.9 0.000 0.000 15.988 15.988 grid_collocate_task_list 119 9.7 15.171 15.171 15.171 15.171 prepare_preconditioner 11 7.9 0.000 0.000 13.653 13.653 make_preconditioner 11 8.9 0.000 0.000 13.653 13.653 sum_up_and_integrate 119 10.3 0.520 0.520 12.912 12.912 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.515 12.515 integrate_v_rspace 119 11.3 0.097 0.097 12.391 12.391 ot_mini 108 10.5 0.001 0.001 11.658 11.658 make_m2s 4572 13.5 0.046 0.046 10.796 10.796 grid_integrate_task_list 119 12.3 10.425 10.425 10.425 10.425 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.167 6.167 pw_transfer 1439 11.6 0.065 0.065 6.150 6.150 qs_ot_get_derivative 108 11.5 0.001 0.001 6.034 6.034 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.912 5.912 dbcsr_make_dense_low 5837 15.5 0.071 0.071 5.761 5.761 make_dense_data 5837 16.5 5.119 5.119 5.677 5.677 ot_diis_step 108 11.5 0.004 0.004 5.620 5.620 make_images 4572 14.5 2.111 2.111 5.432 5.432 fft_wrap_pw1pw2_140 487 13.2 0.484 0.484 5.103 5.103 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.071 5.071 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.028 5.028 apply_single 119 13.6 0.000 0.000 5.027 5.027 multiply_cannon 2286 13.5 0.174 0.174 4.904 4.904 multiply_cannon_loop 2286 14.5 0.064 0.064 4.447 4.447 cp_fm_cholesky_decompose 22 10.9 4.397 4.397 4.397 4.397 multiply_cannon_multrec 2286 15.5 4.330 4.330 4.382 4.382 cp_fm_cholesky_invert 11 10.9 4.043 4.043 4.043 4.043 init_scf_run 11 5.9 0.002 0.002 3.747 3.747 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.745 3.745 dbcsr_complete_redistribute 329 12.2 1.934 1.934 3.632 3.632 dbcsr_copy 2102 12.0 0.202 0.202 3.533 3.533 density_rs2pw 119 9.7 0.004 0.004 3.411 3.411 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.396 3.396 dbcsr_copy_into_existing 22 7.9 3.299 3.299 3.299 3.299 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.290 3.290 wfi_extrapolate 11 7.9 0.001 0.001 3.237 3.237 fft3d_s 1202 14.6 2.928 2.928 2.932 2.932 qs_create_task_list 11 7.9 0.000 0.000 2.926 2.926 generate_qs_task_list 11 8.9 1.978 1.978 2.926 2.926 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.917 2.917 qs_ot_get_p 119 10.4 0.001 0.001 2.791 2.791 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.623 2.623 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.460 2.460 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.273 2.273 dbcsr_data_release 279534 16.0 2.042 2.042 2.042 2.042 pw_poisson_solve 119 10.3 0.344 0.344 2.037 2.037 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.916 1.916 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.913 1.913 potential_pw2rs 119 12.3 0.046 0.046 1.869 1.869 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.823 1.823 ------------------------------------------------------------------------------- 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 43.893 43.903 qs_mol_dyn_low 1 2.0 0.003 0.004 43.793 43.797 qs_forces 11 3.9 0.001 0.001 43.751 43.751 qs_energies 11 4.9 0.001 0.001 40.860 40.862 scf_env_do_scf 11 5.9 0.001 0.002 37.418 37.419 scf_env_do_scf_inner_loop 108 6.5 0.003 0.020 34.486 34.486 velocity_verlet 10 3.0 0.002 0.003 26.443 26.444 rebuild_ks_matrix 119 8.3 0.001 0.001 15.946 16.030 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.016 15.945 16.029 qs_ks_update_qs_env 119 7.6 0.001 0.001 14.156 14.235 dbcsr_multiply_generic 2286 12.5 0.070 0.072 13.074 13.251 qs_rho_update_rho_low 119 7.7 0.001 0.001 12.802 12.810 calculate_rho_elec 119 8.7 0.030 0.033 12.802 12.809 sum_up_and_integrate 119 10.3 0.030 0.034 11.740 11.754 integrate_v_rspace 119 11.3 0.004 0.005 11.710 11.729 qs_scf_new_mos 108 7.5 0.001 0.001 10.204 10.274 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.204 10.274 multiply_cannon 2286 13.5 0.154 0.162 9.681 10.044 ot_scf_mini 108 9.5 0.002 0.002 9.574 9.641 multiply_cannon_loop 2286 14.5 0.089 0.096 9.137 9.560 grid_collocate_task_list 119 9.7 8.976 9.276 8.976 9.276 mp_waitall_1 169478 16.3 8.083 8.632 8.083 8.632 grid_integrate_task_list 119 12.3 8.049 8.271 8.049 8.271 multiply_cannon_metrocomm3 18288 15.5 0.036 0.038 5.327 5.914 ot_mini 108 10.5 0.001 0.001 5.582 5.664 rs_pw_transfer 974 11.9 0.011 0.012 4.187 4.605 density_rs2pw 119 9.7 0.005 0.006 3.485 3.897 pw_transfer 1439 11.6 0.106 0.116 3.301 3.348 multiply_cannon_multrec 18288 15.5 2.993 3.186 3.003 3.196 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.125 3.178 potential_pw2rs 119 12.3 0.007 0.007 3.124 3.141 init_scf_loop 11 6.9 0.000 0.000 2.919 2.919 qs_ot_get_derivative 108 11.5 0.001 0.001 2.847 2.918 fft_wrap_pw1pw2_140 487 13.2 0.269 0.291 2.670 2.741 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.614 2.737 apply_single 119 13.6 0.000 0.000 2.614 2.737 ot_diis_step 108 11.5 0.003 0.003 2.710 2.710 init_scf_run 11 5.9 0.000 0.004 2.428 2.429 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.428 2.429 make_m2s 4572 13.5 0.045 0.049 2.302 2.363 fft3d_ps 1201 14.6 1.210 1.275 2.241 2.298 wfi_extrapolate 11 7.9 0.001 0.001 2.211 2.211 make_images 4572 14.5 0.115 0.121 1.986 2.050 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.928 1.935 mp_waitany 9880 13.7 1.322 1.794 1.322 1.794 rs_pw_transfer_RS2PW_140 130 11.5 0.214 0.248 1.012 1.433 qs_ot_get_p 119 10.4 0.001 0.001 1.220 1.349 rs_pw_transfer_PW2RS_140 130 13.9 0.363 0.386 1.209 1.234 make_images_data 4572 15.5 0.035 0.040 1.118 1.229 prepare_preconditioner 11 7.9 0.000 0.000 1.119 1.142 make_preconditioner 11 8.9 0.000 0.000 1.119 1.142 hybrid_alltoall_any 4725 16.4 0.064 0.183 0.982 1.071 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.010 1.023 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.935 0.977 mp_alltoall_d11v 2130 13.8 0.722 0.975 0.722 0.975 mp_sum_l 11218 13.2 0.659 0.974 0.659 0.974 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.859 0.939 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.909 0.911 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.875 0.906 ------------------------------------------------------------------------------- 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=47.669999999999995, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.171, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.425, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.119, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.397, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.33, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=14.470000000000006, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.976, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.049, 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=2.993, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.322, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.083, 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 0.028 0.028 110.420 110.420 qs_mol_dyn_low 1 2.0 0.003 0.003 109.753 109.753 qs_forces 11 3.9 0.001 0.001 109.714 109.714 qs_energies 11 4.9 0.001 0.001 102.310 102.310 scf_env_do_scf 11 5.9 0.001 0.001 89.731 89.731 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 71.743 71.743 velocity_verlet 10 3.0 0.002 0.002 70.941 70.941 rebuild_ks_matrix 107 8.3 0.001 0.001 33.134 33.134 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.133 33.133 qs_rho_update_rho_low 107 7.7 0.000 0.000 31.578 31.578 calculate_rho_elec 107 8.7 0.871 0.871 31.577 31.577 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.855 29.855 grid_collocate_task_list 107 9.7 27.611 27.611 27.611 27.611 sum_up_and_integrate 107 10.3 0.471 0.471 26.670 26.670 integrate_v_rspace 107 11.3 0.088 0.088 26.199 26.199 grid_integrate_task_list 107 12.3 24.427 24.427 24.427 24.427 init_scf_loop 11 6.9 0.000 0.000 17.783 17.783 dbcsr_multiply_generic 1966 12.4 0.137 0.137 17.478 17.478 qs_scf_new_mos 96 7.5 0.001 0.001 17.015 17.015 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.014 17.014 ot_scf_mini 96 9.5 0.002 0.002 15.798 15.798 prepare_preconditioner 11 7.9 0.000 0.000 13.863 13.863 make_preconditioner 11 8.9 0.000 0.000 13.863 13.863 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.681 12.681 ot_mini 96 10.5 0.001 0.001 10.373 10.373 make_m2s 3932 13.4 0.040 0.040 9.777 9.777 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.685 6.685 pw_transfer 1295 11.6 0.058 0.058 5.398 5.398 qs_ot_get_derivative 96 11.5 0.001 0.001 5.314 5.314 dbcsr_make_dense_low 4961 15.5 0.056 0.056 5.251 5.251 init_scf_run 11 5.9 0.002 0.002 5.204 5.204 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.202 5.202 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.185 5.185 make_dense_data 4961 16.5 4.621 4.621 5.183 5.183 ot_diis_step 96 11.5 0.003 0.003 5.057 5.057 make_images 3932 14.4 1.899 1.899 4.894 4.894 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.709 4.709 apply_single 107 13.6 0.000 0.000 4.709 4.709 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.632 4.632 wfi_extrapolate 11 7.9 0.001 0.001 4.610 4.610 multiply_cannon 1966 13.4 0.151 0.151 4.437 4.437 fft_wrap_pw1pw2_140 439 13.2 0.362 0.362 4.433 4.433 cp_fm_cholesky_decompose 22 10.9 4.426 4.426 4.426 4.426 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.133 4.133 cp_fm_cholesky_invert 11 10.9 4.048 4.048 4.048 4.048 multiply_cannon_loop 1966 14.4 0.049 0.049 4.033 4.033 multiply_cannon_multrec 1966 15.4 3.935 3.935 3.984 3.984 dbcsr_complete_redistribute 317 12.2 1.923 1.923 3.785 3.785 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.732 3.732 dbcsr_copy 1855 11.9 0.189 0.189 3.427 3.427 qs_create_task_list 11 7.9 0.000 0.000 3.348 3.348 generate_qs_task_list 11 8.9 2.410 2.410 3.348 3.348 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.265 3.265 dbcsr_copy_into_existing 22 7.9 3.210 3.210 3.210 3.210 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.105 3.105 density_rs2pw 107 9.7 0.003 0.003 3.096 3.096 fft3d_s 1082 14.6 2.585 2.585 2.589 2.589 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.539 2.539 qs_ot_get_p 107 10.4 0.001 0.001 2.433 2.433 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.319 2.319 ------------------------------------------------------------------------------- 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 70.620 70.630 qs_mol_dyn_low 1 2.0 0.003 0.004 70.516 70.521 qs_forces 11 3.9 0.001 0.001 70.476 70.477 qs_energies 11 4.9 0.001 0.001 65.758 65.761 scf_env_do_scf 11 5.9 0.000 0.002 60.886 60.887 scf_env_do_scf_inner_loop 96 6.5 0.002 0.016 56.124 56.125 velocity_verlet 10 3.0 0.002 0.003 42.047 42.048 rebuild_ks_matrix 107 8.3 0.001 0.001 30.500 30.571 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.015 30.499 30.570 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.867 26.938 sum_up_and_integrate 107 10.3 0.034 0.040 26.638 26.659 integrate_v_rspace 107 11.3 0.004 0.005 26.604 26.633 qs_rho_update_rho_low 107 7.7 0.001 0.001 25.535 25.544 calculate_rho_elec 107 8.7 0.027 0.028 25.534 25.543 grid_integrate_task_list 107 12.3 22.756 23.092 22.756 23.092 grid_collocate_task_list 107 9.7 21.844 22.140 21.844 22.140 dbcsr_multiply_generic 1966 12.4 0.064 0.066 12.193 12.357 qs_scf_new_mos 96 7.5 0.001 0.001 9.447 9.516 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.446 9.516 multiply_cannon 1966 13.4 0.137 0.144 9.058 9.437 ot_scf_mini 96 9.5 0.002 0.002 8.864 8.934 multiply_cannon_loop 1966 14.4 0.087 0.093 8.567 8.877 mp_waitall_1 146670 16.2 7.572 7.934 7.572 7.934 multiply_cannon_metrocomm3 15728 15.4 0.034 0.036 5.023 5.404 ot_mini 96 10.5 0.001 0.001 5.196 5.272 rs_pw_transfer 878 11.9 0.010 0.011 4.118 4.751 init_scf_loop 11 6.9 0.000 0.001 4.747 4.747 density_rs2pw 107 9.7 0.005 0.005 3.356 3.985 init_scf_run 11 5.9 0.000 0.004 3.834 3.835 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.833 3.835 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.760 3.767 wfi_extrapolate 11 7.9 0.001 0.001 3.484 3.484 pw_transfer 1295 11.6 0.098 0.106 3.075 3.145 potential_pw2rs 107 12.3 0.006 0.007 2.983 2.995 fft_wrap_pw1pw2 1081 12.6 0.009 0.011 2.910 2.985 multiply_cannon_multrec 15728 15.4 2.791 2.917 2.800 2.926 qs_ot_get_derivative 96 11.5 0.001 0.001 2.636 2.704 fft_wrap_pw1pw2_140 439 13.2 0.259 0.275 2.503 2.616 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.502 2.582 apply_single 107 13.6 0.000 0.000 2.501 2.582 ot_diis_step 96 11.5 0.003 0.003 2.537 2.537 make_m2s 3932 13.4 0.041 0.045 2.153 2.191 fft3d_ps 1081 14.6 1.133 1.228 2.068 2.136 mp_waitany 8968 13.7 1.408 2.041 1.408 2.041 make_images 3932 14.4 0.104 0.107 1.863 1.906 rs_pw_transfer_RS2PW_140 118 11.5 0.190 0.221 1.072 1.712 mp_alltoall_d11v 1998 13.7 1.051 1.708 1.051 1.708 rs_gather_matrices 107 12.3 0.081 0.090 0.825 1.442 ------------------------------------------------------------------------------- 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=41.352000000000004, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.611, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.427, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.621, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.426, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.048, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.935, 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=14.249000000000002, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.844, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.756, 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=2.791, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.572, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.408, 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 0.191 104.533 104.533 qs_energies 1 2.0 0.000 0.000 103.691 103.691 scf_env_do_scf 1 3.0 0.000 0.000 102.547 102.547 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.566 97.566 rebuild_ks_matrix 7 6.0 0.000 0.000 97.509 97.509 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.509 97.509 hfx_ks_matrix 7 8.0 0.000 0.000 88.493 88.493 integrate_four_center 7 9.0 1.590 1.590 88.455 88.455 integrate_four_center_main 7 10.0 0.681 0.681 80.974 80.974 integrate_four_center_bin 448 11.0 80.293 80.293 80.293 80.293 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.307 56.307 init_scf_loop 1 4.0 0.000 0.000 46.229 46.229 integrate_four_center_load 7 10.0 0.000 0.000 5.640 5.640 hfx_load_balance 1 11.0 0.001 0.001 5.640 5.640 qs_vxc_create 14 8.0 0.000 0.000 3.088 3.088 xc_vxc_pw_create 14 9.0 0.117 0.117 3.088 3.088 hfx_load_balance_bin 1 12.0 2.812 2.812 2.812 2.812 hfx_load_balance_count 1 12.0 2.811 2.811 2.811 2.811 calculate_rho_elec 15 7.4 0.118 0.118 2.473 2.473 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.440 2.440 prepare_preconditioner 1 5.0 0.000 0.000 2.422 2.422 make_preconditioner 1 6.0 0.000 0.000 2.422 2.422 xc_rho_set_and_dset_create 14 10.0 0.092 0.092 2.355 2.355 ------------------------------------------------------------------------------- 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 0.227 0.252 96.048 96.058 qs_energies 1 2.0 0.000 0.000 95.688 95.695 scf_env_do_scf 1 3.0 0.000 0.000 95.354 95.355 qs_ks_update_qs_env 8 5.0 0.000 0.000 93.422 93.423 rebuild_ks_matrix 7 6.0 0.000 0.000 93.413 93.414 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 93.413 93.414 hfx_ks_matrix 7 8.0 0.000 0.000 88.080 88.082 integrate_four_center 7 9.0 0.053 0.335 88.071 88.072 integrate_four_center_main 7 10.0 0.003 0.004 78.829 81.301 integrate_four_center_bin 448 11.0 78.825 81.297 78.825 81.297 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 53.554 53.554 init_scf_loop 1 4.0 0.000 0.000 41.800 41.800 integrate_four_center_load 7 10.0 0.000 0.000 5.740 5.741 hfx_load_balance 1 11.0 0.001 0.001 5.740 5.741 mp_sync 70 11.3 2.831 4.368 2.831 4.368 hfx_load_balance_bin 1 12.0 2.786 2.951 2.786 2.951 hfx_load_balance_count 1 12.0 2.776 2.850 2.776 2.850 qs_vxc_create 14 8.0 0.000 0.000 2.396 2.396 xc_vxc_pw_create 14 9.0 0.007 0.008 2.396 2.396 xc_rho_set_and_dset_create 14 10.0 0.011 0.012 1.921 2.033 ------------------------------------------------------------------------------- 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=16.155, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.293, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.812, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.811, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.59, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.681, 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=8.546999999999997, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.825, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.786, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.776, 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=0.227, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=2.831, 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 85.192 85.192 qs_energies 1 2.0 0.000 0.000 84.815 84.815 mp2_main 1 3.0 0.000 0.000 81.990 81.990 mp2_gpw_main 1 4.0 0.000 0.000 81.880 81.880 rpa_ri_compute_en 1 5.0 0.000 0.000 78.589 78.589 rpa_num_int 1 6.0 0.001 0.001 78.583 78.583 compute_mat_P_omega 1 7.0 0.003 0.003 68.336 68.336 compute_mat_P_omega_contract 10 8.0 8.942 8.942 68.128 68.128 dbt_total 2336 9.6 0.011 0.011 54.301 54.301 dbt_contract 787 11.0 0.033 0.033 47.362 47.362 dbt_tas_total 1149 12.2 0.208 0.208 46.407 46.407 dbt_tas_multiply 807 12.1 0.002 0.002 45.004 45.004 dbt_tas_dbm 807 14.1 0.003 0.003 38.318 38.318 dbm_multiply 807 16.1 38.310 38.310 38.310 38.310 dbt_tas_mm_1N 524 15.1 0.002 0.002 30.087 30.087 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 28.743 28.743 compute_mat_P_omega_calc_M_occ 250 9.0 8.971 8.971 17.161 17.161 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.637 7.637 dbt_tas_mm_2 251 15.0 0.001 0.001 6.674 6.674 dbt_copy 1103 10.7 0.075 0.075 5.519 5.519 compute_QP_energies 1 7.0 0.000 0.000 5.172 5.172 compute_self_energy_cubic_gw 1 8.0 0.055 0.055 5.171 5.171 contract_cubic_gw 21 9.0 0.000 0.000 4.165 4.165 dbt_tas_reserve_blocks_index 3261 14.3 0.150 0.150 3.391 3.391 dbm_reserve_blocks 3628 15.3 3.320 3.320 3.320 3.320 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 3.283 3.283 scf_env_do_scf 1 3.0 0.000 0.000 2.720 2.720 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.720 2.720 dbt_reserve_blocks_index 2280 13.1 0.052 0.052 2.530 2.530 dbt_reserve_blocks_index_array 2222 12.2 0.011 0.011 2.522 2.522 convert_to_new_pgrid 2421 14.1 0.124 0.124 2.390 2.390 dbt_tas_copy 574 11.4 1.394 1.394 2.310 2.310 dbm_copy 1614 15.1 2.266 2.266 2.266 2.266 dbt_crop 1042 12.0 1.411 1.411 2.257 2.257 dbt_tas_reshape 367 15.0 0.007 0.007 2.131 2.131 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.124 2.124 compute_W_cubic_GW 10 7.0 0.004 0.004 2.062 2.062 dbt_reshape 278 11.9 0.955 0.955 1.809 1.809 get_2c_integrals 1 6.0 0.000 0.000 1.761 1.761 ------------------------------------------------------------------------------- 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 0.029 32.724 32.737 qs_energies 1 2.0 0.000 0.000 32.628 32.629 mp2_main 1 3.0 0.000 0.000 31.681 31.682 mp2_gpw_main 1 4.0 0.000 0.000 31.646 31.647 rpa_ri_compute_en 1 5.0 0.000 0.000 30.411 30.412 rpa_num_int 1 6.0 0.000 0.002 30.410 30.411 dbt_total 2336 9.6 0.011 0.012 26.932 26.935 compute_mat_P_omega 1 7.0 0.001 0.005 25.752 25.774 compute_mat_P_omega_contract 10 8.0 0.422 0.438 25.586 25.589 dbt_contract 787 11.0 0.026 0.030 20.196 20.207 dbt_tas_total 1149 12.2 0.053 0.066 18.140 18.141 dbt_tas_multiply 807 12.1 0.002 0.002 18.095 18.097 dbt_tas_dbm 807 14.1 0.003 0.003 13.503 13.508 dbm_multiply 807 16.1 10.335 11.176 10.335 11.176 compute_mat_P_omega_calc_M_occ 250 9.0 0.400 0.414 7.608 7.610 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.539 7.542 dbt_tas_mm_2 251 15.0 0.001 0.001 6.185 6.195 mp_sync 8706 11.6 5.047 6.189 5.047 6.189 dbt_copy 1111 10.7 0.012 0.013 5.864 6.027 dbt_reshape 1098 11.7 2.210 2.347 5.595 5.761 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.436 5.437 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.831 5.374 compute_QP_energies 1 7.0 0.000 0.000 2.941 2.942 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 2.937 2.940 dbt_communicate_buffer 1098 12.7 0.053 0.058 2.670 2.772 mp_waitall_2 3776 15.3 2.600 2.754 2.600 2.754 contract_cubic_gw 21 9.0 0.000 0.000 2.368 2.368 dbt_reserve_blocks_index 2849 13.1 0.065 0.070 1.676 1.836 dbt_reserve_blocks_index_array 2791 12.2 0.009 0.010 1.676 1.836 dbt_tas_reserve_blocks_index 3300 14.5 0.115 0.131 1.647 1.806 dbm_reserve_blocks 3696 15.4 1.627 1.780 1.627 1.780 dbt_crop 1042 12.0 0.893 0.999 1.411 1.559 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 1.231 1.234 dbt_tas_replicate 396 14.1 0.536 0.694 1.086 1.151 parallel_gemm_fm 105 8.4 0.000 0.000 1.035 1.042 parallel_gemm_fm_cosma 105 9.4 1.035 1.041 1.035 1.041 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.002 1.005 convert_to_new_pgrid 2421 14.1 0.024 0.029 0.852 0.950 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.937 0.939 dbm_copy 1608 15.1 0.822 0.924 0.822 0.924 scf_env_do_scf 1 3.0 0.000 0.000 0.908 0.908 scf_env_do_scf_inner_loop 17 4.0 0.000 0.003 0.908 0.908 compute_W_cubic_GW 10 7.0 0.001 0.001 0.800 0.805 mp_max_i 1994 9.8 0.565 0.730 0.565 0.730 dbm_add 807 14.1 0.677 0.727 0.677 0.727 ------------------------------------------------------------------------------- Plot: name="GW_PBE_4benzene_timings_32omp", title="Timings of GW_PBE_4benzene with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="rest", label="rest", y=22.42799999999999, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=38.31, 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=8.971, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.942, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.32, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.266, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.955, 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=9.260999999999992, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.335, 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=0.4, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.422, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.627, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.822, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.21, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.047, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.6, 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 0.018 289.357 289.357 qs_forces 1 2.0 0.000 0.000 288.787 288.787 rebuild_ks_matrix 7 6.6 0.000 0.000 287.309 287.309 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 287.309 287.309 hfx_ks_matrix 7 8.6 0.000 0.000 285.263 285.263 hfx_ri_update_ks 7 9.6 0.000 0.000 247.087 247.087 hfx_ri_update_ks_Pmat 7 10.6 31.692 31.692 247.083 247.083 dbt_total 841 11.0 0.005 0.005 230.788 230.788 qs_energies 1 3.0 0.000 0.000 216.356 216.356 scf_env_do_scf 1 4.0 0.000 0.000 216.058 216.058 qs_ks_update_qs_env 8 6.0 0.000 0.000 214.927 214.927 dbt_contract 207 12.4 0.028 0.028 212.776 212.776 dbt_tas_total 375 13.4 1.454 1.454 212.413 212.413 dbt_tas_multiply 216 13.5 0.001 0.001 208.035 208.035 dbt_tas_dbm 216 15.5 0.001 0.001 197.029 197.029 dbm_multiply 216 17.5 197.026 197.026 197.026 197.026 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.000 191.582 191.582 dbt_tas_mm_2 91 16.5 0.001 0.001 183.383 183.383 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 134.132 134.132 init_scf_loop 2 5.0 0.000 0.000 81.924 81.924 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 72.386 72.386 hfx_ri_update_forces 1 7.0 1.666 1.666 38.173 38.173 hfx_ri_forces_Pmat_3c 1 8.0 4.857 4.857 22.261 22.261 dbt_copy 409 11.7 0.029 0.029 13.627 13.627 precalc_derivatives 1 8.0 2.132 2.132 12.276 12.276 dbt_reshape 132 13.2 5.869 5.869 9.426 9.426 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.423 9.423 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.387 9.387 build_3c_derivatives 3 9.0 2.405 2.405 6.946 6.946 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.756 6.756 dbt_tas_reserve_blocks_index 1287 15.4 0.272 0.272 6.260 6.260 dbm_reserve_blocks 1461 16.2 6.176 6.176 6.176 6.176 ------------------------------------------------------------------------------- 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 0.026 45.422 45.432 qs_forces 1 2.0 0.000 0.000 45.298 45.299 rebuild_ks_matrix 7 6.6 0.000 0.000 44.619 44.619 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 44.618 44.619 hfx_ks_matrix 7 8.6 0.000 0.000 43.657 43.662 dbt_total 841 11.0 0.005 0.005 38.840 38.846 dbt_contract 207 12.4 0.021 0.024 30.741 30.754 dbt_tas_total 375 13.4 0.044 0.113 28.522 28.523 dbt_tas_multiply 216 13.5 0.001 0.001 27.604 27.605 hfx_ri_update_ks 7 9.6 0.000 0.000 25.265 25.265 hfx_ri_update_ks_Pmat 7 10.6 1.244 1.331 25.262 25.264 qs_energies 1 3.0 0.000 0.000 23.792 23.792 scf_env_do_scf 1 4.0 0.000 0.001 23.645 23.645 qs_ks_update_qs_env 8 6.0 0.000 0.000 23.124 23.124 dbt_tas_dbm 216 15.5 0.001 0.001 22.002 22.008 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 21.496 21.496 dbm_multiply 216 17.5 19.446 20.590 19.446 20.590 hfx_ri_update_forces 1 7.0 0.059 0.063 18.392 18.396 hfx_ri_forces_Pmat_3c 1 8.0 0.178 0.188 13.880 13.890 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 13.175 13.175 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 11.840 11.840 init_scf_loop 2 5.0 0.000 0.000 10.470 10.470 dbt_tas_mm_2 91 16.5 0.001 0.001 9.966 9.973 mp_sync 2909 12.8 4.593 7.313 4.593 7.313 dbt_copy 421 11.8 0.010 0.012 6.809 7.008 dbt_tas_mm_3T 77 17.1 0.000 0.000 6.017 6.411 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.014 5.014 dbt_reshape 252 12.8 2.357 2.440 4.666 4.748 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.294 4.478 precalc_derivatives 1 8.0 0.079 0.083 3.405 3.405 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.295 3.295 dbm_reserve_blocks 1477 16.3 2.673 2.935 2.673 2.935 dbt_tas_reserve_blocks_index 1302 15.5 0.214 0.222 2.642 2.888 dbt_crop 372 13.7 1.758 1.843 2.412 2.566 mp_waitall_2 1204 16.3 2.291 2.396 2.291 2.396 dbt_reserve_blocks_index 938 14.4 0.094 0.100 2.064 2.224 dbt_reserve_blocks_index_array 915 13.4 0.005 0.005 2.039 2.202 build_3c_derivatives 3 9.0 0.219 0.236 1.880 1.896 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.798 1.802 dbt_tas_replicate 175 15.2 0.706 0.737 1.708 1.745 convert_to_new_pgrid 648 15.5 0.034 0.064 1.363 1.674 dbt_communicate_buffer 252 13.8 0.011 0.012 1.570 1.624 dbt_tas_copy 169 12.8 0.822 0.865 1.473 1.592 dbm_copy 452 16.3 1.174 1.482 1.174 1.482 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.445 1.446 dbt_tas_communicate_buffer 352 16.4 0.013 0.014 0.959 1.019 dbm_add 216 15.5 0.839 0.909 0.839 0.909 ------------------------------------------------------------------------------- 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=43.73700000000002, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=197.026, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.692, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=6.176, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=5.869, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.857, 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=12.64, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=19.446, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.244, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.673, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.357, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.178, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.593, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.291, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.015 0.015 175.832 175.832 qs_energies 1 2.0 0.000 0.000 175.645 175.645 mp2_main 1 3.0 0.000 0.000 170.959 170.959 mp2_gpw_main 1 4.0 0.001 0.001 170.571 170.571 mp2_ri_gpw_compute_in 1 5.0 0.391 0.391 122.427 122.427 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 110.724 110.724 mp2_eri_3c_integrate_gpw 2656 7.0 0.014 0.014 80.918 80.918 integrate_v_rspace 2666 8.0 0.637 0.637 67.908 67.908 grid_integrate_task_list 2666 9.0 65.289 65.289 65.289 65.289 mp2_ri_gpw_compute_en 1 5.0 0.092 0.092 48.118 48.118 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.650 9.650 46.224 46.224 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.035 2.035 28.852 28.852 local_gemm 2080 8.0 26.818 26.818 26.818 26.818 dbcsr_multiply_generic 5322 8.0 0.188 0.188 21.134 21.134 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 21.114 21.114 pw_transfer 63872 10.6 1.038 1.038 11.942 11.942 calculate_wavefunction 2656 8.0 8.164 8.164 11.653 11.653 get_2c_integrals 1 6.0 0.000 0.000 11.311 11.311 multiply_cannon 5322 9.0 0.457 0.457 10.781 10.781 fft_wrap_pw1pw2 53228 11.4 0.120 0.120 10.684 10.684 compute_2c_integrals 1 7.0 0.006 0.006 10.483 10.483 compute_2c_integrals_loop_lm 1 8.0 0.007 0.007 10.457 10.457 mp2_eri_2c_integrate_gpw 1 9.0 3.477 3.477 10.450 10.450 multiply_cannon_loop 5322 10.0 0.093 0.093 9.376 9.376 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.467 2.467 8.583 8.583 make_m2s 10644 9.0 0.062 0.062 8.175 8.175 multiply_cannon_multrec 5322 11.0 7.852 7.852 7.890 7.890 make_images 10644 10.0 3.225 3.225 7.880 7.880 fft_wrap_pw1pw2_20 21271 12.4 0.496 0.496 7.652 7.652 copy_dbcsr_to_fm 2679 8.0 0.028 0.028 6.659 6.659 fft3d_s 53229 13.4 6.571 6.571 6.606 6.606 mp2_ri_gpw_compute_en_ener 2080 7.0 5.811 5.811 5.811 5.811 dbcsr_complete_redistribute 2689 9.0 1.106 1.106 5.048 5.048 dbcsr_finalize 10708 9.5 0.134 0.134 4.499 4.499 scf_env_do_scf 1 3.0 0.000 0.000 4.298 4.298 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.298 4.298 potential_pw2rs 5322 10.0 0.144 0.144 3.939 3.939 dbcsr_merge_all 8011 10.3 3.027 3.027 3.902 3.902 ------------------------------------------------------------------------------- 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 0.023 35.412 35.423 qs_energies 1 2.0 0.000 0.000 35.338 35.339 mp2_main 1 3.0 0.000 0.001 33.266 33.267 mp2_gpw_main 1 4.0 0.001 0.002 33.139 33.140 mp2_ri_gpw_compute_in 1 5.0 0.052 0.060 17.335 17.960 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 16.129 16.758 mp2_ri_gpw_compute_en 1 5.0 0.152 0.160 15.717 15.928 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 14.036 14.636 integrate_v_rspace 93 8.1 0.104 0.116 13.893 14.500 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.871 0.981 14.433 14.441 grid_integrate_task_list 93 9.1 13.597 14.210 13.597 14.210 mp2_ri_gpw_compute_en_expansio 65 7.0 0.106 0.119 10.799 10.918 local_gemm 65 8.0 10.693 10.811 10.693 10.811 mp2_ri_gpw_compute_en_comm 17 7.0 0.066 0.080 2.408 2.760 mp_sendrecv_dm3 1054 8.0 1.873 2.290 1.873 2.290 dbcsr_multiply_generic 176 8.0 0.008 0.009 1.788 2.056 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.771 2.037 scf_env_do_scf 1 3.0 0.000 0.000 1.954 1.954 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.953 1.954 get_2c_integrals 1 6.0 0.000 0.000 1.136 1.163 multiply_cannon 176 9.0 0.016 0.017 1.054 1.157 multiply_cannon_loop 176 10.0 0.002 0.002 0.997 1.098 qs_scf_new_mos 10 5.0 0.000 0.000 1.012 1.016 eigensolver 11 5.8 0.001 0.003 1.005 1.007 multiply_cannon_multrec 246 11.0 0.857 0.922 0.862 0.928 mp_min_d 2 7.0 0.655 0.918 0.655 0.918 make_m2s 352 9.0 0.003 0.003 0.696 0.859 compute_2c_integrals 1 7.0 0.002 0.004 0.841 0.856 make_images 352 10.0 0.051 0.053 0.684 0.846 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.844 0.845 mp2_ri_get_integ_group_size 1 6.0 0.000 0.000 0.628 0.840 cp_fm_redistribute_end 11 7.8 0.316 0.834 0.329 0.837 cp_fm_diag_elpa_base 11 7.8 0.493 0.795 0.503 0.808 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 0.739 0.774 mp2_eri_2c_integrate_gpw 1 9.0 0.199 0.206 0.737 0.771 pw_transfer 2120 10.5 0.045 0.046 0.745 0.760 ------------------------------------------------------------------------------- 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=58.05899999999998, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=65.289, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=26.818, 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=9.65, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.164, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.852, 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=7.521000000000001, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.597, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.693, 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=0.871, 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=0.857, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.873, 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 0.084 0.084 126.643 126.643 qs_energies 1 2.0 0.000 0.000 125.244 125.244 scf_env_do_scf 1 3.0 0.000 0.000 118.606 118.606 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 118.606 118.606 qs_ks_update_qs_env 15 5.0 0.000 0.000 49.425 49.425 rebuild_ks_matrix 15 6.0 0.000 0.000 49.213 49.213 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 49.213 49.213 qs_scf_new_mos 15 5.0 0.000 0.000 43.958 43.958 eigensolver 15 6.0 0.001 0.001 35.947 35.947 qs_vxc_create 15 8.0 0.040 0.040 33.863 33.863 calculate_dispersion_nonloc 15 9.0 6.712 6.712 29.306 29.306 pw_transfer 1191 10.0 0.062 0.062 23.476 23.476 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 23.296 23.296 cp_fm_diag_elpa 15 7.0 0.000 0.000 23.221 23.221 cp_fm_diag_elpa_base 15 8.0 20.584 20.584 23.220 23.220 qs_rho_update_rho_low 16 5.0 0.000 0.000 22.176 22.176 calculate_rho_elec 16 6.0 0.230 0.230 22.176 22.176 grid_collocate_task_list 16 7.0 20.767 20.767 20.767 20.767 fft_wrap_pw1pw2_150 765 12.0 3.621 3.621 16.838 16.838 sum_up_and_integrate 15 8.0 0.116 0.116 14.150 14.150 integrate_v_rspace 15 9.0 0.020 0.020 14.034 14.034 grid_integrate_task_list 15 10.0 13.496 13.496 13.496 13.496 cp_fm_cholesky_restore 45 7.0 10.419 10.419 10.419 10.419 fft3d_s 1087 13.0 10.382 10.382 10.389 10.389 pw_scatter_s 585 13.1 7.217 7.217 7.217 7.217 fft_wrap_pw1pw2_200 197 12.3 0.804 0.804 6.278 6.278 dbcsr_complete_redistribute 46 8.3 2.317 2.317 5.766 5.766 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.706 5.706 cp_fm_upper_to_full 30 8.0 4.942 4.942 4.942 4.942 xc_vxc_pw_create 15 9.0 0.234 0.234 4.517 4.517 vdW_energy 15 10.0 4.400 4.400 4.400 4.400 gspace_mixing 14 5.0 0.171 0.171 4.245 4.245 broyden_mixing 14 6.0 3.610 3.610 3.610 3.610 init_scf_run 1 3.0 0.000 0.000 3.163 3.163 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.010 3.010 xc_pw_derive 90 11.0 0.000 0.000 2.994 2.994 calculate_dm_sparse 15 6.0 0.019 0.019 2.666 2.666 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 2.585 2.585 ------------------------------------------------------------------------------- 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 0.030 63.291 63.302 qs_energies 1 2.0 0.000 0.000 63.017 63.023 scf_env_do_scf 1 3.0 0.000 0.001 58.948 58.949 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 58.948 58.949 qs_ks_update_qs_env 15 5.0 0.000 0.000 23.676 23.691 rebuild_ks_matrix 15 6.0 0.000 0.000 23.640 23.655 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 23.640 23.655 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.806 21.810 calculate_rho_elec 16 6.0 0.007 0.007 21.806 21.810 grid_collocate_task_list 16 7.0 19.541 19.953 19.541 19.953 sum_up_and_integrate 15 8.0 0.012 0.017 14.166 14.213 integrate_v_rspace 15 9.0 0.001 0.001 14.153 14.207 qs_scf_new_mos 15 5.0 0.000 0.000 14.070 14.153 grid_integrate_task_list 15 10.0 13.069 13.198 13.069 13.198 eigensolver 15 6.0 0.001 0.002 13.074 13.092 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.565 9.572 cp_fm_diag_elpa_base 15 8.0 9.419 9.446 9.560 9.564 qs_vxc_create 15 8.0 0.001 0.001 9.184 9.195 calculate_dispersion_nonloc 15 9.0 0.912 0.923 7.384 7.404 pw_transfer 1191 10.0 0.086 0.095 6.795 6.855 fft_wrap_pw1pw2 1086 11.0 0.012 0.013 6.619 6.686 fft3d_ps 1086 13.0 2.440 2.648 4.933 5.123 fft_wrap_pw1pw2_150 765 12.0 0.278 0.309 4.226 4.257 cp_fm_cholesky_restore 45 7.0 3.361 3.404 3.361 3.404 rs_pw_transfer 158 9.4 0.001 0.002 2.153 2.499 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.449 2.449 density_rs2pw 16 7.0 0.001 0.001 2.139 2.397 mp_alltoall_z22v 1086 15.0 1.899 2.361 1.899 2.361 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.149 2.349 fft_wrap_pw1pw2_200 197 12.3 0.187 0.210 2.274 2.340 mp_waitany 520 11.3 1.474 1.991 1.474 1.991 xc_vxc_pw_create 15 9.0 0.015 0.018 1.799 1.826 rs_pw_transfer_RS2PW_200 18 8.8 0.030 0.033 1.036 1.621 x_to_yz 585 14.1 0.340 0.355 1.318 1.496 vdW_energy 15 10.0 1.350 1.414 1.350 1.414 yz_to_x 501 13.9 0.231 0.280 1.151 1.395 init_scf_run 1 3.0 0.000 0.001 1.393 1.395 build_core_ppnl 1 5.0 1.260 1.386 1.260 1.386 scf_env_initial_rho_setup 1 4.0 0.000 0.001 1.302 1.303 xc_pw_derive 90 11.0 0.001 0.001 1.193 1.268 ------------------------------------------------------------------------------- Plot: name="diag_cu144_broy_timings_32omp", title="Timings of diag_cu144_broy with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32omp", name="rest", label="rest", y=50.99499999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.767, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.584, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.496, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.419, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.382, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=15.460999999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.541, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=9.419, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.069, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.361, 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=2.44, 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 0.078 0.078 283.676 283.676 qs_energies 1 2.0 0.000 0.000 283.537 283.537 ls_scf 1 3.0 0.000 0.000 282.314 282.314 ls_scf_main 1 4.0 0.002 0.002 273.218 273.218 density_matrix_trs4 11 5.0 0.012 0.012 179.251 179.251 arnoldi_extremal 12 6.1 0.000 0.000 91.733 91.733 arnoldi_normal_ev 12 7.1 0.014 0.014 91.733 91.733 build_subspace 23 8.1 0.080 0.080 89.678 89.678 dbcsr_matrix_vector_mult 652 9.0 0.177 0.177 89.633 89.633 ls_scf_dm_to_ks 11 5.0 0.000 0.000 88.657 88.657 dbcsr_matrix_vector_mult_local 652 10.0 88.171 88.171 88.181 88.181 matrix_ls_to_qs 11 6.0 0.000 0.000 85.269 85.269 dbcsr_multiply_generic 185 6.1 0.852 0.852 76.294 76.294 dbcsr_copy_into_existing 11 7.0 46.009 46.009 46.010 46.010 multiply_cannon 185 7.1 0.303 0.303 45.979 45.979 dbcsr_complete_redistribute 23 7.5 31.112 31.112 43.009 43.009 matrix_decluster 11 7.0 0.000 0.000 39.259 39.259 multiply_cannon_loop 185 8.1 0.243 0.243 33.677 33.677 make_m2s 370 7.1 0.038 0.038 25.701 25.701 make_images 370 8.1 10.749 10.749 24.024 24.024 multiply_cannon_multrec 185 9.1 23.767 23.767 23.898 23.898 dbcsr_finalize 646 7.5 0.146 0.146 15.674 15.674 dbcsr_merge_all 597 8.5 2.404 2.404 14.453 14.453 setup_rec_index_2d 370 8.1 11.895 11.895 11.895 11.895 dbcsr_sort_indices 1103 9.9 10.920 10.920 10.920 10.920 tree_to_linear_d 110 9.4 10.712 10.712 10.712 10.712 calculate_norms 370 9.1 9.535 9.535 9.535 9.535 quick_finalize 395 10.0 0.422 0.422 9.448 9.448 dbcsr_special_finalize 370 9.1 0.002 0.002 8.735 8.735 ls_scf_init_scf 1 4.0 0.000 0.000 8.380 8.380 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.033 8.033 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.380 7.380 ------------------------------------------------------------------------------- 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 0.007 0.020 67.913 67.923 qs_energies 1 2.0 0.000 0.000 67.827 67.827 ls_scf 1 3.0 0.000 0.000 67.778 67.779 ls_scf_main 1 4.0 0.001 0.009 65.154 65.155 density_matrix_trs4 11 5.0 0.006 0.018 62.656 62.739 dbcsr_multiply_generic 185 6.1 0.060 0.098 59.368 59.551 multiply_cannon 185 7.1 0.033 0.036 49.501 50.217 multiply_cannon_loop 185 8.1 0.116 0.129 47.060 48.109 multiply_cannon_multrec 1480 9.1 29.195 31.418 29.474 31.676 mp_waitall_1 11936 10.3 15.023 17.064 15.023 17.064 multiply_cannon_metrocomm3 1480 9.1 0.013 0.016 8.808 12.786 make_m2s 370 7.1 0.034 0.037 6.909 6.974 make_images 370 8.1 0.623 0.658 6.781 6.848 calculate_norms 2960 9.1 5.157 5.887 5.157 5.887 multiply_cannon_metrocomm1 1480 9.1 0.008 0.009 3.447 5.387 make_images_data 370 9.1 0.009 0.010 3.028 3.224 hybrid_alltoall_any 393 9.9 0.207 1.161 2.627 2.760 mp_sum_l 1119 5.6 1.882 2.417 1.882 2.417 arnoldi_extremal 12 6.1 0.000 0.000 2.386 2.401 arnoldi_normal_ev 12 7.1 0.001 0.004 2.385 2.401 build_subspace 23 8.1 0.020 0.025 2.276 2.278 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.165 2.220 dbcsr_complete_redistribute 23 7.5 1.183 1.272 1.924 2.007 dbcsr_matrix_vector_mult 652 9.0 0.009 0.043 1.960 2.002 ls_scf_init_scf 1 4.0 0.000 0.000 1.992 1.993 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.968 1.973 matrix_ls_to_qs 11 6.0 0.000 0.000 1.876 1.961 make_images_pack 370 9.1 1.734 1.878 1.737 1.882 matrix_decluster 11 7.0 0.000 0.000 1.735 1.820 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.802 1.803 dbcsr_matrix_vector_mult_local 652 10.0 1.602 1.649 1.603 1.651 dbcsr_finalize 646 7.5 0.008 0.008 1.393 1.568 buffer_matrices_ensure_size 370 8.1 1.369 1.489 1.369 1.489 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.033 1.414 ------------------------------------------------------------------------------- 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=73.18699999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=88.171, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=46.009, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=31.112, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.767, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.895, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.535, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 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=12.137, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.602, 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=1.183, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=29.195, 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=5.157, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=15.023, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.882, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.734, 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 71.525 71.525 lib_test 1 2.0 0.000 0.000 71.517 71.517 dbcsr_run_tests 3 3.0 0.002 0.002 71.517 71.517 test_multiplies_multiproc 3 4.0 0.001 0.001 55.375 55.375 dbcsr_redistribute 9 5.0 35.962 35.962 37.569 37.569 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.430 16.430 dbcsr_make_random_matrix 9 4.0 13.024 13.024 16.030 16.030 multiply_cannon 9 6.0 0.001 0.001 11.585 11.585 multiply_cannon_loop 9 7.0 0.017 0.017 11.230 11.230 multiply_cannon_multrec 9 8.0 11.212 11.212 11.213 11.213 dbcsr_finalize 27 5.7 0.018 0.018 5.632 5.632 dbcsr_merge_all 18 6.5 2.038 2.038 4.861 4.861 dbcsr_data_release 975 7.6 2.904 2.904 2.904 2.904 tree_to_linear_d 9 7.0 1.952 1.952 1.952 1.952 make_m2s 18 6.0 0.001 0.001 1.645 1.645 make_images 18 7.0 0.557 0.557 1.596 1.596 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.004 0.014 18.115 18.120 lib_test 1 2.0 0.000 0.000 18.086 18.104 dbcsr_run_tests 3 3.0 0.000 0.001 18.082 18.100 test_multiplies_multiproc 3 4.0 0.000 0.004 17.236 17.282 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.851 15.928 multiply_cannon 9 6.0 0.001 0.002 14.043 14.367 multiply_cannon_loop 9 7.0 0.002 0.002 13.740 14.076 multiply_cannon_multrec 72 8.0 11.486 11.946 11.487 11.947 mp_waitall_1 576 9.2 2.571 3.139 2.571 3.139 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.989 2.689 dbcsr_finalize 27 5.7 0.000 0.000 0.737 0.891 dbcsr_data_release 444 7.6 0.771 0.869 0.771 0.869 dbcsr_make_random_matrix 9 4.0 0.664 0.676 0.814 0.842 mp_sum_l 390 2.5 0.412 0.769 0.412 0.769 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.394 0.750 make_m2s 18 6.0 0.001 0.001 0.696 0.736 make_images 18 7.0 0.021 0.021 0.693 0.732 dbcsr_destroy 111 5.9 0.000 0.000 0.614 0.706 dbcsr_merge_all 18 6.5 0.104 0.121 0.578 0.691 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.257 0.648 dbcsr_data_copy_aa2 18 7.5 0.351 0.458 0.351 0.458 dbcsr_redistribute 9 5.0 0.244 0.285 0.421 0.455 make_images_data 18 8.0 0.000 0.001 0.361 0.422 hybrid_alltoall_any 18 9.0 0.031 0.127 0.322 0.386 ------------------------------------------------------------------------------- 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=6.385000000000005, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.962, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.024, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.212, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.904, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.038, 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=1.8629999999999995, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.244, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.664, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.486, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.771, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.104, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.571, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.412, 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 0.054 0.054 132.449 132.449 qs_mol_dyn_low 1 2.0 0.003 0.003 131.052 131.052 velocity_verlet 5 3.0 0.003 0.003 106.812 106.812 qmmm_el_coupling 6 3.8 0.000 0.000 87.658 87.658 qmmm_elec_with_gaussian 6 4.8 0.014 0.014 87.651 87.651 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.004 87.004 qmmm_elec_gaussian_low_G 6 6.8 86.121 86.121 86.121 86.121 qs_forces 6 3.8 0.000 0.000 35.038 35.038 qs_energies 6 4.8 0.000 0.000 31.104 31.104 scf_env_do_scf 6 5.8 0.001 0.001 28.807 28.807 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 25.184 25.184 rebuild_ks_matrix 45 8.4 0.000 0.000 24.138 24.138 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.137 24.137 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.631 20.631 pw_transfer 966 12.3 0.053 0.053 17.315 17.315 fft_wrap_pw1pw2 801 13.6 0.006 0.006 17.105 17.105 fft_wrap_pw1pw2_150 507 15.2 2.265 2.265 16.704 16.704 qs_vxc_create 45 10.4 0.001 0.001 13.393 13.393 xc_vxc_pw_create 45 11.4 0.707 0.707 13.393 13.393 xc_pw_derive 270 13.4 0.002 0.002 9.451 9.451 fft3d_s 802 15.6 7.982 7.982 7.990 7.990 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.337 7.337 calculate_rho_elec 45 8.9 0.564 0.564 7.337 7.337 xc_rho_set_and_dset_create 45 12.4 0.605 0.605 6.830 6.830 xc_pw_divergence 45 12.4 0.001 0.001 5.801 5.801 pw_scatter_s 429 15.8 5.543 5.543 5.543 5.543 qmmm_forces 6 3.8 0.002 0.002 5.222 5.222 qmmm_forces_with_gaussian 6 4.8 0.030 0.030 4.888 4.888 pw_integral_ab 2539 7.4 4.497 4.497 4.497 4.497 qs_ks_ddapc 45 10.4 0.001 0.001 4.188 4.188 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.145 4.145 init_scf_loop 6 6.8 0.000 0.000 3.618 3.618 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.514 3.514 qmmm_forces_gaussian_low_G 6 6.8 3.457 3.457 3.457 3.457 grid_collocate_task_list 45 9.9 3.411 3.411 3.411 3.411 sum_up_and_integrate 45 10.4 0.343 0.343 3.398 3.398 density_rs2pw 45 9.9 0.002 0.002 3.362 3.362 integrate_v_rspace 45 11.4 0.006 0.006 3.055 3.055 ------------------------------------------------------------------------------- From /workspace/artifacts/MQAE_single_node_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.033 0.055 52.852 52.866 qs_mol_dyn_low 1 2.0 0.003 0.004 51.869 51.927 qs_forces 6 3.8 0.000 0.001 37.782 37.782 qs_energies 6 4.8 0.001 0.001 36.026 36.026 scf_env_do_scf 6 5.8 0.000 0.001 35.041 35.041 scf_env_do_scf_inner_loop 113 6.2 0.002 0.017 33.644 33.645 rebuild_ks_matrix 119 8.1 0.000 0.000 24.748 24.758 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.016 24.747 24.757 qs_ks_update_qs_env 119 7.3 0.001 0.001 23.273 23.283 velocity_verlet 5 3.0 0.002 0.003 21.801 21.804 pw_transfer 2446 12.3 0.196 0.217 16.415 16.812 fft_wrap_pw1pw2 2059 13.4 0.022 0.024 16.002 16.407 fft_wrap_pw1pw2_150 1321 14.9 1.185 1.406 15.401 15.903 qs_vxc_create 119 10.1 0.002 0.003 12.967 12.970 xc_vxc_pw_create 119 11.1 0.141 0.195 12.965 12.968 fft3d_ps 2059 15.4 6.530 7.344 12.009 12.725 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.122 10.123 calculate_rho_elec 119 8.3 0.048 0.055 10.121 10.122 xc_pw_derive 714 13.1 0.009 0.010 9.738 9.987 sum_up_and_integrate 119 10.1 0.077 0.091 8.651 8.700 integrate_v_rspace 119 11.1 0.003 0.003 8.573 8.609 qmmm_forces 6 3.8 0.002 0.002 7.225 7.226 qmmm_forces_with_gaussian 6 4.8 0.010 0.012 6.912 7.050 xc_pw_divergence 119 12.1 0.004 0.005 6.314 6.535 xc_rho_set_and_dset_create 119 12.1 0.349 0.426 6.315 6.483 rs_pw_transfer 988 11.5 0.010 0.013 6.030 6.268 qmmm_el_coupling 6 3.8 0.000 0.000 5.954 6.079 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 5.952 6.077 density_rs2pw 119 9.3 0.005 0.006 5.640 5.853 mp_alltoall_z22v 2059 17.4 4.132 5.088 4.132 5.088 potential_pw2rs 119 12.1 0.006 0.006 4.947 4.965 grid_collocate_task_list 119 9.3 4.301 4.549 4.301 4.549 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.829 3.869 grid_integrate_task_list 119 12.1 3.385 3.555 3.385 3.555 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.299 3.352 x_to_yz 1095 16.8 0.774 0.882 2.909 3.255 qmmm_forces_gaussian_low_G 6 6.8 3.150 3.188 3.150 3.188 yz_to_x 964 16.0 0.518 0.658 2.514 3.120 qmmm_elec_gaussian_low_G 6 6.8 2.708 2.756 2.708 2.756 mp_waitany 4028 12.8 2.242 2.584 2.242 2.584 pw_restrict_s3 18 5.8 1.345 1.382 2.471 2.578 rs_pw_transfer_PW2RS_150 125 13.9 0.696 0.773 2.253 2.277 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 1.981 2.105 pw_prolongate_s3 18 6.8 1.108 1.150 1.981 2.105 rs_pw_transfer_RS2PW_150 125 11.2 0.551 0.659 1.743 1.995 qs_scf_new_mos 113 7.2 0.000 0.000 1.961 1.966 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.960 1.966 ot_scf_mini 113 9.2 0.001 0.001 1.878 1.884 qs_ks_ddapc 119 10.1 0.002 0.002 1.787 1.872 dbcsr_multiply_generic 2588 12.3 0.056 0.057 1.839 1.864 mp_waitall_1 188862 16.2 1.762 1.860 1.762 1.860 pw_gather_p 964 15.0 1.238 1.588 1.238 1.588 pw_scatter_p 1095 15.8 1.521 1.546 1.521 1.546 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.485 1.485 pw_integral_ab 2761 7.7 1.109 1.208 1.398 1.477 init_scf_loop 6 6.8 0.000 0.000 1.394 1.394 mp_sum_dm3 33 5.7 1.173 1.231 1.173 1.231 ot_mini 113 10.2 0.001 0.001 1.164 1.170 mp_sum_d 5820 12.2 0.785 1.101 0.785 1.101 ------------------------------------------------------------------------------- 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=21.438000000000017, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.121, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.982, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.543, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.497, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.457, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.411, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", 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=27.537, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.708, 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=1.109, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.15, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.301, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.53, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.385, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.132, yerr=0.0 Summary: Performance test took 33 minutes. (cached) Status: OK Uploading artifacts... done EndDate: 2022-10-17 11:13:06+00:00