StartDate: 2022-11-20 19:11:06+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 393dd794fe555d9c12ad5bce6d81de7f468dc7c7 CommitTime: 2022-11-20 18:30:41 +0100 CommitAuthor: Ole Schütt CommitSubject: DBM: Switch to realloc Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=393dd794fe555d9c12ad5bce6d81de7f468dc7c7 Sending build context to Docker daemon 365.4MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu e96e057aae67: Already exists Digest: sha256:4b1d0c4a2d2aaf63b37111f34eb9fa89fa1bf53dd6e4ca954d47caebca4005c2 Status: Downloaded newer image for ubuntu:22.04 ---> a8780b506fa4 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 456d88508063 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 196acfd778fb Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 1c5721a94525 Step 5/42 : RUN mkdir scripts ---> Using cache ---> aa1c7bdf0e90 Step 6/42 : COPY ./tools/toolchain/scripts/VERSION ./tools/toolchain/scripts/parse_if.py ./tools/toolchain/scripts/tool_kit.sh ./tools/toolchain/scripts/common_vars.sh ./tools/toolchain/scripts/signal_trap.sh ./tools/toolchain/scripts/get_openblas_arch.sh ./scripts/ ---> Using cache ---> 8641bd388b4f Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 13fd585790c3 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> cac01e5ed808 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 4d68dfb96b0f Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> d498842004b1 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 653a132d5aa7 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 932f838464d3 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 1801374ed881 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> a8995b19ba48 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> e525eee1ff8e Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> f4f361a003dd Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 8b63f00f04f8 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 4a094f4a2f76 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 3b3f84e762a7 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 6ec03878598d Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> e19cd3bb6f22 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 5c3d211ed962 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 765ecf06ceba Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 85d65dea1e16 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 6e219fcd9e8c Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 3e6ff79bc60b Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 564abc7b20f4 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> ea8d38dfdbea Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> adce1f11e400 Step 30/42 : COPY ./Makefile . ---> Using cache ---> b337c5ad22d0 Step 31/42 : COPY ./src ./src ---> Using cache ---> 8a42c3f64148 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 3a8007c36561 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 87f9f5920a85 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 37f839d366f6 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 37f839d366f6 ---> 10cfaf9e1ae6 Step 35/42 : COPY ./data ./data ---> fdb15edc9a66 Step 36/42 : COPY ./tests ./tests ---> 38822b63a9e5 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 86ef4949de7d Step 38/42 : COPY ./benchmarks ./benchmarks ---> 4bf878a28048 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 5014e8764e4e Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 7e65c1b9ee48 ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 60 input files and 0 errors. ========== Running Performance Test ========== Running H2O-64.inp with 1 threads and 32 ranks... done. Running H2O-64.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.028 0.028 87.796 87.796 qs_mol_dyn_low 1 2.0 0.003 0.003 87.178 87.178 qs_forces 11 3.9 0.001 0.001 87.139 87.139 qs_energies 11 4.9 0.001 0.001 81.138 81.138 scf_env_do_scf 11 5.9 0.001 0.001 70.362 70.362 velocity_verlet 10 3.0 0.002 0.002 57.098 57.098 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 53.651 53.651 rebuild_ks_matrix 119 8.3 0.001 0.001 19.974 19.974 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 19.973 19.973 dbcsr_multiply_generic 2286 12.5 0.153 0.153 19.948 19.948 qs_scf_new_mos 108 7.5 0.001 0.001 19.582 19.582 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.582 19.582 qs_rho_update_rho_low 119 7.7 0.000 0.000 19.539 19.539 calculate_rho_elec 119 8.7 0.955 0.955 19.539 19.539 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.298 18.298 ot_scf_mini 108 9.5 0.002 0.002 18.207 18.207 init_scf_loop 11 6.9 0.000 0.000 16.576 16.576 grid_collocate_task_list 119 9.7 15.116 15.116 15.116 15.116 prepare_preconditioner 11 7.9 0.000 0.000 14.062 14.062 make_preconditioner 11 8.9 0.000 0.000 14.062 14.062 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.894 12.894 sum_up_and_integrate 119 10.3 0.523 0.523 12.805 12.805 integrate_v_rspace 119 11.3 0.094 0.094 12.282 12.282 ot_mini 108 10.5 0.001 0.001 11.863 11.863 make_m2s 4572 13.5 0.045 0.045 11.005 11.005 grid_integrate_task_list 119 12.3 10.357 10.357 10.357 10.357 qs_ot_get_derivative 108 11.5 0.001 0.001 6.193 6.193 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.113 6.113 pw_transfer 1439 11.6 0.064 0.064 5.960 5.960 dbcsr_make_dense_low 5837 15.5 0.071 0.071 5.877 5.877 make_dense_data 5837 16.5 5.184 5.184 5.792 5.792 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.750 5.750 ot_diis_step 108 11.5 0.004 0.004 5.667 5.667 make_images 4572 14.5 2.172 2.172 5.541 5.541 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.218 5.218 apply_single 119 13.6 0.000 0.000 5.218 5.218 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.173 5.173 fft_wrap_pw1pw2_140 487 13.2 0.471 0.471 4.941 4.941 multiply_cannon 2286 13.5 0.174 0.174 4.919 4.919 cp_fm_cholesky_decompose 22 10.9 4.563 4.563 4.563 4.563 multiply_cannon_loop 2286 14.5 0.043 0.043 4.463 4.463 multiply_cannon_multrec 2286 15.5 4.369 4.369 4.420 4.420 cp_fm_cholesky_invert 11 10.9 4.100 4.100 4.100 4.100 init_scf_run 11 5.9 0.002 0.002 4.065 4.065 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.063 4.063 dbcsr_complete_redistribute 329 12.2 1.921 1.921 3.761 3.761 wfi_extrapolate 11 7.9 0.001 0.001 3.552 3.552 dbcsr_copy 2102 12.0 0.240 0.240 3.527 3.527 density_rs2pw 119 9.7 0.005 0.005 3.468 3.468 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.379 3.379 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.269 3.269 dbcsr_copy_into_existing 22 7.9 3.253 3.253 3.253 3.253 copy_dbcsr_to_fm 153 11.3 0.002 0.002 3.046 3.046 qs_create_task_list 11 7.9 0.000 0.000 2.908 2.908 generate_qs_task_list 11 8.9 1.977 1.977 2.908 2.908 qs_ot_get_p 119 10.4 0.001 0.001 2.872 2.872 fft3d_s 1202 14.6 2.823 2.823 2.828 2.828 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.621 2.621 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.426 2.426 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.355 2.355 dbcsr_data_release 279534 16.0 2.251 2.251 2.251 2.251 pw_poisson_solve 119 10.3 0.340 0.340 1.983 1.983 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.965 1.965 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.937 1.937 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.886 1.886 potential_pw2rs 119 12.3 0.046 0.046 1.831 1.831 cp_fm_upper_to_full 72 14.2 1.792 1.792 1.792 1.792 dbcsr_finalize 5186 13.8 0.091 0.091 1.767 1.767 ------------------------------------------------------------------------------- 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 0.025 48.209 48.219 qs_mol_dyn_low 1 2.0 0.004 0.013 48.105 48.109 qs_forces 11 3.9 0.001 0.001 48.046 48.046 qs_energies 11 4.9 0.001 0.001 44.716 44.719 scf_env_do_scf 11 5.9 0.000 0.002 40.876 40.877 scf_env_do_scf_inner_loop 108 6.5 0.003 0.019 37.561 37.563 velocity_verlet 10 3.0 0.002 0.009 29.078 29.079 rebuild_ks_matrix 119 8.3 0.001 0.001 17.885 17.953 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.016 17.884 17.952 qs_ks_update_qs_env 119 7.6 0.001 0.001 15.862 15.927 qs_rho_update_rho_low 119 7.7 0.001 0.001 14.471 14.491 calculate_rho_elec 119 8.7 0.030 0.034 14.470 14.490 sum_up_and_integrate 119 10.3 0.033 0.036 13.550 13.611 integrate_v_rspace 119 11.3 0.004 0.005 13.517 13.579 dbcsr_multiply_generic 2286 12.5 0.073 0.077 13.275 13.458 qs_scf_new_mos 108 7.5 0.001 0.001 10.354 10.438 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.354 10.437 multiply_cannon 2286 13.5 0.150 0.163 9.715 9.989 ot_scf_mini 108 9.5 0.002 0.002 9.688 9.770 multiply_cannon_loop 2286 14.5 0.091 0.100 9.161 9.488 grid_collocate_task_list 119 9.7 9.177 9.465 9.177 9.465 grid_integrate_task_list 119 12.3 8.166 8.469 8.166 8.469 mp_waitall_1 169478 16.3 7.993 8.415 7.993 8.415 rs_pw_transfer 974 11.9 0.011 0.013 5.782 6.116 ot_mini 108 10.5 0.001 0.001 5.634 5.725 multiply_cannon_metrocomm3 18288 15.5 0.036 0.038 5.165 5.679 density_rs2pw 119 9.7 0.005 0.006 4.915 5.236 pw_transfer 1439 11.6 0.101 0.111 3.491 3.537 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.313 3.365 potential_pw2rs 119 12.3 0.007 0.008 3.328 3.345 multiply_cannon_multrec 18288 15.5 3.166 3.328 3.176 3.339 init_scf_loop 11 6.9 0.000 0.000 3.299 3.303 mp_waitany 9880 13.7 2.892 3.217 2.892 3.217 qs_ot_get_derivative 108 11.5 0.001 0.001 2.892 2.976 fft_wrap_pw1pw2_140 487 13.2 0.286 0.308 2.798 2.863 rs_pw_transfer_RS2PW_140 130 11.5 0.188 0.237 2.505 2.839 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.651 2.733 apply_single 119 13.6 0.000 0.000 2.651 2.733 ot_diis_step 108 11.5 0.003 0.004 2.721 2.721 init_scf_run 11 5.9 0.000 0.004 2.680 2.680 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.680 2.680 mp_alltoall_d11v 2130 13.8 2.242 2.506 2.242 2.506 make_m2s 4572 13.5 0.045 0.050 2.426 2.488 fft3d_ps 1201 14.6 1.257 1.317 2.395 2.456 wfi_extrapolate 11 7.9 0.001 0.001 2.452 2.452 rs_gather_matrices 119 12.3 0.081 0.090 1.981 2.288 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.180 2.185 make_images 4572 14.5 0.116 0.121 2.099 2.164 qs_ot_get_p 119 10.4 0.001 0.001 1.260 1.350 rs_pw_transfer_PW2RS_140 130 13.9 0.384 0.433 1.290 1.326 make_images_data 4572 15.5 0.036 0.043 1.171 1.279 prepare_preconditioner 11 7.9 0.000 0.000 1.248 1.274 make_preconditioner 11 8.9 0.000 0.000 1.248 1.274 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.137 1.148 hybrid_alltoall_any 4725 16.4 0.067 0.245 1.032 1.129 mp_sum_l 11218 13.2 0.687 1.111 0.687 1.111 multiply_cannon_metrocomm1 18288 15.5 0.017 0.019 0.535 1.004 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.943 0.997 mp_alltoall_z22v 1201 16.6 0.856 0.984 0.856 0.984 ------------------------------------------------------------------------------- Plot: name="H2O-64_timings_32omp", title="Timings of H2O-64 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32omp", name="rest", label="rest", y=48.20700000000001, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.116, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.357, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.184, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.563, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.369, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=16.815, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.177, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.166, 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=3.166, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.993, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.892, 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 0.028 111.229 111.229 qs_mol_dyn_low 1 2.0 0.003 0.003 110.568 110.568 qs_forces 11 3.9 0.001 0.001 110.528 110.528 qs_energies 11 4.9 0.001 0.001 102.758 102.758 scf_env_do_scf 11 5.9 0.001 0.001 90.159 90.159 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 72.026 72.026 velocity_verlet 10 3.0 0.002 0.002 71.345 71.345 rebuild_ks_matrix 107 8.3 0.001 0.001 33.729 33.729 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.728 33.728 qs_rho_update_rho_low 107 7.7 0.000 0.000 31.719 31.719 calculate_rho_elec 107 8.7 0.858 0.858 31.718 31.718 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.243 30.243 grid_collocate_task_list 107 9.7 27.578 27.578 27.578 27.578 sum_up_and_integrate 107 10.3 0.470 0.470 26.735 26.735 integrate_v_rspace 107 11.3 0.128 0.128 26.265 26.265 grid_integrate_task_list 107 12.3 24.396 24.396 24.396 24.396 init_scf_loop 11 6.9 0.000 0.000 17.989 17.989 dbcsr_multiply_generic 1966 12.4 0.151 0.151 17.926 17.926 qs_scf_new_mos 96 7.5 0.001 0.001 17.058 17.058 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.057 17.057 ot_scf_mini 96 9.5 0.002 0.002 15.833 15.833 prepare_preconditioner 11 7.9 0.000 0.000 13.751 13.751 make_preconditioner 11 8.9 0.000 0.000 13.751 13.751 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.602 12.602 ot_mini 96 10.5 0.001 0.001 10.273 10.273 make_m2s 3932 13.4 0.039 0.039 9.714 9.714 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.590 6.590 pw_transfer 1295 11.6 0.056 0.056 5.712 5.712 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.520 5.520 qs_ot_get_derivative 96 11.5 0.001 0.001 5.473 5.473 init_scf_run 11 5.9 0.002 0.002 5.381 5.381 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.379 5.379 dbcsr_make_dense_low 4961 15.5 0.058 0.058 5.064 5.064 make_images 3932 14.4 1.965 1.965 5.032 5.032 make_dense_data 4961 16.5 4.542 4.542 4.994 4.994 ot_diis_step 96 11.5 0.003 0.003 4.797 4.797 wfi_extrapolate 11 7.9 0.001 0.001 4.792 4.792 fft_wrap_pw1pw2_140 439 13.2 0.525 0.525 4.785 4.785 multiply_cannon 1966 13.4 0.179 0.179 4.680 4.680 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.478 4.478 apply_single 107 13.6 0.000 0.000 4.478 4.478 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.411 4.411 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.365 4.365 cp_fm_cholesky_decompose 22 10.9 4.291 4.291 4.291 4.291 multiply_cannon_loop 1966 14.4 0.066 0.066 4.184 4.184 multiply_cannon_multrec 1966 15.4 4.071 4.071 4.117 4.117 cp_fm_cholesky_invert 11 10.9 4.054 4.054 4.054 4.054 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.728 3.728 dbcsr_complete_redistribute 317 12.2 1.910 1.910 3.677 3.677 dbcsr_copy 1855 11.9 0.246 0.246 3.573 3.573 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.404 3.404 qs_create_task_list 11 7.9 0.000 0.000 3.353 3.353 generate_qs_task_list 11 8.9 2.403 2.403 3.353 3.353 density_rs2pw 107 9.7 0.004 0.004 3.282 3.282 dbcsr_copy_into_existing 22 7.9 3.246 3.246 3.246 3.246 copy_dbcsr_to_fm 147 11.2 0.002 0.002 2.973 2.973 fft3d_s 1082 14.6 2.697 2.697 2.702 2.702 qs_ot_get_p 107 10.4 0.001 0.001 2.497 2.497 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.450 2.450 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.339 2.339 ------------------------------------------------------------------------------- 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 69.995 70.005 qs_mol_dyn_low 1 2.0 0.003 0.003 69.893 69.897 qs_forces 11 3.9 0.001 0.001 69.852 69.852 qs_energies 11 4.9 0.001 0.001 65.141 65.142 scf_env_do_scf 11 5.9 0.000 0.002 60.276 60.277 scf_env_do_scf_inner_loop 96 6.5 0.003 0.018 55.678 55.678 velocity_verlet 10 3.0 0.002 0.003 41.674 41.675 rebuild_ks_matrix 107 8.3 0.000 0.000 30.224 30.313 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.015 30.223 30.312 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.604 26.683 sum_up_and_integrate 107 10.3 0.032 0.036 26.454 26.471 integrate_v_rspace 107 11.3 0.004 0.005 26.422 26.445 qs_rho_update_rho_low 107 7.7 0.000 0.001 25.638 25.645 calculate_rho_elec 107 8.7 0.027 0.028 25.637 25.644 grid_integrate_task_list 107 12.3 22.674 23.110 22.674 23.110 grid_collocate_task_list 107 9.7 21.877 22.255 21.877 22.255 dbcsr_multiply_generic 1966 12.4 0.065 0.075 11.765 11.961 qs_scf_new_mos 96 7.5 0.001 0.001 9.123 9.208 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.122 9.207 multiply_cannon 1966 13.4 0.133 0.142 8.636 8.956 ot_scf_mini 96 9.5 0.002 0.002 8.554 8.629 multiply_cannon_loop 1966 14.4 0.084 0.089 8.140 8.463 mp_waitall_1 146670 16.2 7.118 7.469 7.118 7.469 ot_mini 96 10.5 0.001 0.001 4.969 5.056 multiply_cannon_metrocomm3 15728 15.4 0.032 0.034 4.593 4.995 rs_pw_transfer 878 11.9 0.010 0.012 4.164 4.743 init_scf_loop 11 6.9 0.000 0.000 4.585 4.585 density_rs2pw 107 9.7 0.005 0.005 3.424 3.997 init_scf_run 11 5.9 0.000 0.004 3.835 3.835 scf_env_initial_rho_setup 11 6.9 0.000 0.004 3.834 3.834 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.750 3.760 wfi_extrapolate 11 7.9 0.001 0.001 3.475 3.475 pw_transfer 1295 11.6 0.093 0.100 3.110 3.177 potential_pw2rs 107 12.3 0.006 0.007 3.002 3.022 fft_wrap_pw1pw2 1081 12.6 0.009 0.009 2.948 3.013 multiply_cannon_multrec 15728 15.4 2.814 2.987 2.823 2.997 fft_wrap_pw1pw2_140 439 13.2 0.262 0.296 2.533 2.623 qs_ot_get_derivative 96 11.5 0.001 0.001 2.543 2.615 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.392 2.474 apply_single 107 13.6 0.000 0.000 2.392 2.474 ot_diis_step 96 11.5 0.003 0.003 2.400 2.400 make_m2s 3932 13.4 0.040 0.044 2.147 2.211 fft3d_ps 1081 14.6 1.132 1.233 2.107 2.192 mp_waitany 8968 13.7 1.505 2.159 1.505 2.159 make_images 3932 14.4 0.103 0.105 1.856 1.922 rs_pw_transfer_RS2PW_140 118 11.5 0.175 0.220 1.154 1.744 mp_alltoall_d11v 1998 13.7 0.946 1.594 0.946 1.594 ------------------------------------------------------------------------------- Plot: name="H2O-64_nonortho_timings_32omp", title="Timings of H2O-64_nonortho with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="rest", label="rest", y=46.351, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.578, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.396, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.542, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.291, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.071, 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=14.006999999999998, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.877, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.674, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.814, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.118, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.505, 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 0.184 0.184 105.657 105.657 qs_energies 1 2.0 0.000 0.000 104.833 104.833 scf_env_do_scf 1 3.0 0.000 0.000 103.720 103.720 qs_ks_update_qs_env 8 5.0 0.000 0.000 98.421 98.421 rebuild_ks_matrix 7 6.0 0.000 0.000 98.364 98.364 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 98.364 98.364 hfx_ks_matrix 7 8.0 0.000 0.000 89.253 89.253 integrate_four_center 7 9.0 1.618 1.618 89.212 89.212 integrate_four_center_main 7 10.0 0.525 0.525 81.597 81.597 integrate_four_center_bin 451 11.0 81.071 81.071 81.071 81.071 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 57.041 57.041 init_scf_loop 1 4.0 0.000 0.000 46.669 46.669 integrate_four_center_load 7 10.0 0.000 0.000 5.745 5.745 hfx_load_balance 1 11.0 0.001 0.001 5.745 5.745 qs_vxc_create 14 8.0 0.000 0.000 3.192 3.192 xc_vxc_pw_create 14 9.0 0.136 0.136 3.192 3.192 hfx_load_balance_count 1 12.0 2.866 2.866 2.866 2.866 hfx_load_balance_bin 1 12.0 2.863 2.863 2.863 2.863 prepare_preconditioner 1 5.0 0.000 0.000 2.523 2.523 make_preconditioner 1 6.0 0.000 0.000 2.523 2.523 calculate_rho_elec 15 7.4 0.118 0.118 2.502 2.502 xc_rho_set_and_dset_create 14 10.0 0.091 0.091 2.390 2.390 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.289 2.289 ------------------------------------------------------------------------------- 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 0.223 0.244 95.740 95.751 qs_energies 1 2.0 0.000 0.000 95.389 95.396 scf_env_do_scf 1 3.0 0.000 0.000 95.051 95.051 qs_ks_update_qs_env 8 5.0 0.000 0.000 93.065 93.066 rebuild_ks_matrix 7 6.0 0.000 0.000 93.056 93.057 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 93.056 93.057 hfx_ks_matrix 7 8.0 0.000 0.000 87.658 87.660 integrate_four_center 7 9.0 0.056 0.335 87.649 87.651 integrate_four_center_main 7 10.0 0.003 0.003 79.251 80.868 integrate_four_center_bin 448 11.0 79.248 80.865 79.248 80.865 scf_env_do_scf_inner_loop 7 4.0 0.000 0.002 52.879 52.879 init_scf_loop 1 4.0 0.000 0.000 42.171 42.171 integrate_four_center_load 7 10.0 0.000 0.000 5.670 5.671 hfx_load_balance 1 11.0 0.001 0.001 5.670 5.671 mp_sync 70 11.3 2.062 3.544 2.062 3.544 hfx_load_balance_count 1 12.0 2.769 2.834 2.769 2.834 hfx_load_balance_bin 1 12.0 2.766 2.831 2.766 2.831 qs_vxc_create 14 8.0 0.000 0.000 2.425 2.425 xc_vxc_pw_create 14 9.0 0.007 0.008 2.424 2.424 xc_rho_set_and_dset_create 14 10.0 0.010 0.012 1.913 2.049 ------------------------------------------------------------------------------- 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=16.53, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=81.071, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.866, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.863, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.618, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.525, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.184, 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=8.612999999999985, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=79.248, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.769, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.766, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.056, 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=0.223, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=2.062, 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 87.028 87.028 qs_energies 1 2.0 0.000 0.000 86.643 86.643 mp2_main 1 3.0 0.000 0.000 83.744 83.744 mp2_gpw_main 1 4.0 0.000 0.000 83.639 83.639 rpa_ri_compute_en 1 5.0 0.000 0.000 79.958 79.958 rpa_num_int 1 6.0 0.001 0.001 79.952 79.952 compute_mat_P_omega 1 7.0 0.003 0.003 70.229 70.229 compute_mat_P_omega_contract 10 8.0 8.697 8.697 70.030 70.030 dbt_total 2336 9.6 0.011 0.011 56.728 56.728 dbt_contract 787 11.0 0.033 0.033 49.606 49.606 dbt_tas_total 1149 12.2 0.199 0.199 48.663 48.663 dbt_tas_multiply 807 12.1 0.003 0.003 47.280 47.280 dbt_tas_dbm 807 14.1 0.004 0.004 40.569 40.569 dbm_multiply 807 16.1 40.561 40.561 40.561 40.561 dbt_tas_mm_1N 524 15.1 0.001 0.001 33.277 33.277 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 31.679 31.679 compute_mat_P_omega_calc_M_occ 250 9.0 8.709 8.709 17.091 17.091 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.851 6.851 dbt_tas_mm_2 251 15.0 0.001 0.001 5.802 5.802 dbt_copy 1103 10.7 0.089 0.089 5.722 5.722 compute_QP_energies 1 7.0 0.000 0.000 5.005 5.005 compute_self_energy_cubic_gw 1 8.0 0.054 0.054 5.004 5.004 contract_cubic_gw 21 9.0 0.000 0.000 4.030 4.030 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.674 3.674 dbt_tas_reserve_blocks_index 3261 14.3 0.140 0.140 3.544 3.544 dbm_reserve_blocks 3628 15.3 3.482 3.482 3.482 3.482 scf_env_do_scf 1 3.0 0.000 0.000 2.797 2.797 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.797 2.797 dbt_reserve_blocks_index 2280 13.1 0.050 0.050 2.685 2.685 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.639 2.639 convert_to_new_pgrid 2421 14.1 0.100 0.100 2.461 2.461 dbt_tas_copy 574 11.4 1.436 1.436 2.375 2.375 dbm_copy 1614 15.1 2.361 2.361 2.361 2.361 dbt_crop 1042 12.0 1.396 1.396 2.227 2.227 dbt_tas_reshape 367 15.0 0.009 0.009 2.129 2.129 compute_W_cubic_GW 10 7.0 0.011 0.011 1.962 1.962 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.868 1.868 dbt_reshape 278 11.9 0.966 0.966 1.831 1.831 get_2c_integrals 1 6.0 0.000 0.000 1.747 1.747 ------------------------------------------------------------------------------- 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 0.028 32.896 32.910 qs_energies 1 2.0 0.000 0.000 32.767 32.770 mp2_main 1 3.0 0.000 0.000 31.814 31.816 mp2_gpw_main 1 4.0 0.000 0.000 31.778 31.780 rpa_ri_compute_en 1 5.0 0.000 0.000 30.505 30.507 rpa_num_int 1 6.0 0.000 0.002 30.505 30.507 dbt_total 2336 9.6 0.012 0.012 27.082 27.088 compute_mat_P_omega 1 7.0 0.001 0.005 25.237 25.268 compute_mat_P_omega_contract 10 8.0 0.423 0.442 25.117 25.122 dbt_contract 787 11.0 0.026 0.027 20.463 20.465 dbt_tas_total 1149 12.2 0.052 0.060 18.411 18.411 dbt_tas_multiply 807 12.1 0.002 0.002 18.357 18.358 dbt_tas_dbm 807 14.1 0.003 0.003 13.936 13.939 dbm_multiply 807 16.1 10.545 11.569 10.545 11.569 compute_mat_P_omega_calc_M_occ 250 9.0 0.404 0.421 7.483 7.484 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.348 7.349 mp_sync 8706 11.6 5.167 6.575 5.167 6.575 dbt_tas_mm_2 251 15.0 0.001 0.001 6.105 6.105 dbt_copy 1111 10.7 0.012 0.012 5.817 6.037 dbt_reshape 1098 11.7 2.184 2.309 5.551 5.766 dbt_tas_mm_1N 524 15.1 0.001 0.001 5.053 5.616 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.353 5.356 compute_QP_energies 1 7.0 0.000 0.000 3.612 3.613 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 3.612 3.612 contract_cubic_gw 21 9.0 0.000 0.000 2.996 2.996 dbt_communicate_buffer 1098 12.7 0.053 0.057 2.669 2.802 mp_waitall_2 3776 15.3 2.598 2.761 2.598 2.761 dbt_reserve_blocks_index 2849 13.1 0.065 0.069 1.689 1.896 dbt_reserve_blocks_index_array 2791 12.2 0.009 0.010 1.679 1.887 dbt_tas_reserve_blocks_index 3300 14.5 0.109 0.116 1.660 1.864 dbm_reserve_blocks 3696 15.4 1.646 1.845 1.646 1.845 dbt_crop 1042 12.0 0.907 1.001 1.429 1.566 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.271 1.271 dbt_tas_replicate 396 14.1 0.536 0.701 1.094 1.154 convert_to_new_pgrid 2421 14.1 0.025 0.029 0.857 1.016 parallel_gemm_fm 105 8.4 0.000 0.000 1.003 1.011 parallel_gemm_fm_cosma 105 9.4 1.002 1.011 1.002 1.011 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.988 0.991 dbm_copy 1608 15.1 0.826 0.984 0.826 0.984 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.916 0.918 scf_env_do_scf 1 3.0 0.000 0.000 0.917 0.917 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.917 0.917 dbt_tas_mm_3N 22 15.1 0.000 0.000 0.511 0.835 compute_W_cubic_GW 10 7.0 0.001 0.001 0.762 0.767 dbm_add 807 14.1 0.616 0.720 0.616 0.720 mp_max_i 1994 9.8 0.557 0.700 0.557 0.700 ------------------------------------------------------------------------------- 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=22.25200000000001, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=40.561, 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=8.709, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.697, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.482, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.361, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.966, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", 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=9.103000000000002, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.545, 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=0.404, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.423, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.646, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.826, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.184, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.598, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.167, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.018 0.018 321.245 321.245 qs_forces 1 2.0 0.000 0.000 320.689 320.689 rebuild_ks_matrix 7 6.6 0.000 0.000 319.260 319.260 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 319.260 319.260 hfx_ks_matrix 7 8.6 0.000 0.000 317.208 317.208 hfx_ri_update_ks 7 9.6 0.000 0.000 277.025 277.025 hfx_ri_update_ks_Pmat 7 10.6 31.212 31.212 277.021 277.021 dbt_total 841 11.0 0.005 0.005 263.141 263.141 qs_energies 1 3.0 0.000 0.000 244.297 244.297 scf_env_do_scf 1 4.0 0.000 0.000 244.010 244.010 dbt_contract 207 12.4 0.038 0.038 243.895 243.895 dbt_tas_total 375 13.4 1.487 1.487 243.424 243.424 qs_ks_update_qs_env 8 6.0 0.000 0.000 242.917 242.917 dbt_tas_multiply 216 13.5 0.001 0.001 239.047 239.047 dbt_tas_dbm 216 15.5 0.001 0.001 227.058 227.058 dbm_multiply 216 17.5 227.055 227.055 227.055 227.055 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 221.197 221.197 dbt_tas_mm_2 91 16.5 0.001 0.001 212.787 212.787 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 155.572 155.572 init_scf_loop 2 5.0 0.000 0.000 88.435 88.435 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 76.346 76.346 hfx_ri_update_forces 1 7.0 1.598 1.598 40.180 40.180 hfx_ri_forces_Pmat_3c 1 8.0 4.693 4.693 23.452 23.452 dbt_copy 409 11.7 0.040 0.040 14.861 14.861 precalc_derivatives 1 8.0 2.152 2.152 13.065 13.065 dbt_reshape 132 13.2 6.158 6.158 10.303 10.303 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 10.051 10.051 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.937 9.937 build_3c_derivatives 3 9.0 2.804 2.804 7.406 7.406 dbt_tas_reserve_blocks_index 1287 15.4 0.272 0.272 7.245 7.245 dbm_reserve_blocks 1461 16.2 7.215 7.215 7.215 7.215 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.864 6.864 ------------------------------------------------------------------------------- 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 0.025 45.788 45.797 qs_forces 1 2.0 0.000 0.000 45.666 45.666 rebuild_ks_matrix 7 6.6 0.000 0.000 44.994 44.995 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 44.994 44.995 hfx_ks_matrix 7 8.6 0.000 0.000 43.999 44.004 dbt_total 841 11.0 0.005 0.005 39.137 39.167 dbt_contract 207 12.4 0.021 0.022 30.743 30.756 dbt_tas_total 375 13.4 0.045 0.141 28.511 28.512 dbt_tas_multiply 216 13.5 0.001 0.001 27.565 27.565 hfx_ri_update_ks 7 9.6 0.000 0.000 25.617 25.617 hfx_ri_update_ks_Pmat 7 10.6 1.258 1.337 25.616 25.616 qs_energies 1 3.0 0.000 0.000 24.009 24.009 scf_env_do_scf 1 4.0 0.000 0.001 23.867 23.867 qs_ks_update_qs_env 8 6.0 0.000 0.000 23.348 23.348 dbt_tas_dbm 216 15.5 0.001 0.001 22.037 22.040 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 21.648 21.648 dbm_multiply 216 17.5 19.345 20.484 19.345 20.484 hfx_ri_update_forces 1 7.0 0.058 0.060 18.381 18.386 hfx_ri_forces_Pmat_3c 1 8.0 0.176 0.190 13.755 13.763 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 13.359 13.359 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 11.938 11.938 init_scf_loop 2 5.0 0.000 0.000 10.507 10.507 dbt_tas_mm_2 91 16.5 0.001 0.001 10.033 10.034 mp_sync 2909 12.8 4.767 7.814 4.767 7.814 dbt_copy 421 11.8 0.010 0.012 6.962 7.204 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.979 6.430 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.128 5.128 dbt_reshape 252 12.8 2.371 2.448 4.770 4.950 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.187 4.385 precalc_derivatives 1 8.0 0.081 0.086 3.548 3.548 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.264 3.264 dbm_reserve_blocks 1477 16.3 2.754 3.061 2.754 3.061 dbt_tas_reserve_blocks_index 1302 15.5 0.214 0.226 2.724 3.035 dbt_crop 372 13.7 1.772 1.858 2.434 2.606 mp_waitall_2 1204 16.3 2.372 2.525 2.372 2.525 dbt_reserve_blocks_index 938 14.4 0.095 0.105 2.136 2.372 dbt_reserve_blocks_index_array 915 13.4 0.005 0.005 2.111 2.347 build_3c_derivatives 3 9.0 0.222 0.239 2.006 2.011 dbt_tas_replicate 175 15.2 0.704 0.734 1.737 1.795 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.761 1.763 dbt_communicate_buffer 252 13.8 0.011 0.012 1.616 1.697 dbt_tas_copy 169 12.8 0.849 0.903 1.512 1.627 convert_to_new_pgrid 648 15.5 0.037 0.077 1.396 1.578 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.484 1.484 dbm_copy 452 16.3 1.222 1.386 1.222 1.386 dbt_tas_communicate_buffer 352 16.4 0.013 0.014 0.999 1.085 ------------------------------------------------------------------------------- Plot: name="RI-HFX_H2O-32_timings_32omp", title="Timings of RI-HFX_H2O-32 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="rest", label="rest", y=44.912000000000035, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=227.055, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.212, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.215, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.158, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.693, 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=12.745000000000005, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=19.345, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.258, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.754, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.371, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.176, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.767, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.372, 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 0.014 198.713 198.713 qs_energies 1 2.0 0.000 0.000 198.529 198.529 mp2_main 1 3.0 0.000 0.000 193.490 193.490 mp2_gpw_main 1 4.0 0.001 0.001 193.075 193.075 mp2_ri_gpw_compute_in 1 5.0 0.384 0.384 146.020 146.020 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 134.502 134.502 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 103.184 103.184 integrate_v_rspace 2666 8.0 0.617 0.617 90.154 90.154 grid_integrate_task_list 2666 9.0 87.584 87.584 87.584 87.584 mp2_ri_gpw_compute_en 1 5.0 0.085 0.085 47.030 47.030 mp2_ri_gpw_compute_en_RI_loop 1 6.0 10.168 10.168 45.172 45.172 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.104 2.104 27.919 27.919 local_gemm 2080 8.0 25.815 25.815 25.815 25.815 dbcsr_multiply_generic 5322 8.0 0.174 0.174 21.462 21.462 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 21.442 21.442 pw_transfer 63872 10.6 1.032 1.032 11.759 11.759 calculate_wavefunction 2656 8.0 8.170 8.170 11.709 11.709 get_2c_integrals 1 6.0 0.000 0.000 11.133 11.133 multiply_cannon 5322 9.0 0.473 0.473 11.033 11.033 fft_wrap_pw1pw2 53228 11.4 0.115 0.115 10.510 10.510 compute_2c_integrals 1 7.0 0.006 0.006 10.233 10.233 compute_2c_integrals_loop_lm 1 8.0 0.014 0.014 10.211 10.211 mp2_eri_2c_integrate_gpw 1 9.0 3.314 3.314 10.198 10.198 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.360 2.360 9.770 9.770 multiply_cannon_loop 5322 10.0 0.132 0.132 9.628 9.628 make_m2s 10644 9.0 0.064 0.064 8.222 8.222 multiply_cannon_multrec 5322 11.0 8.019 8.019 8.059 8.059 copy_dbcsr_to_fm 2679 8.0 0.027 0.027 7.928 7.928 make_images 10644 10.0 3.285 3.285 7.882 7.882 fft_wrap_pw1pw2_20 21271 12.4 0.469 0.469 7.551 7.551 fft3d_s 53229 13.4 6.493 6.493 6.526 6.526 dbcsr_complete_redistribute 2689 9.0 1.144 1.144 6.228 6.228 dbcsr_finalize 10708 9.5 0.220 0.220 5.669 5.669 mp2_ri_gpw_compute_en_ener 2080 7.0 5.058 5.058 5.058 5.058 dbcsr_merge_all 8011 10.3 3.883 3.883 4.983 4.983 scf_env_do_scf 1 3.0 0.000 0.000 4.651 4.651 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.651 4.651 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.021 35.416 35.426 qs_energies 1 2.0 0.000 0.000 35.341 35.341 mp2_main 1 3.0 0.000 0.001 33.183 33.184 mp2_gpw_main 1 4.0 0.001 0.002 33.027 33.027 mp2_ri_gpw_compute_in 1 5.0 0.051 0.052 17.332 17.596 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 16.105 16.373 mp2_ri_gpw_compute_en 1 5.0 0.161 0.173 15.603 15.875 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.913 1.071 14.657 14.662 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.903 14.194 integrate_v_rspace 93 8.1 0.107 0.117 13.764 14.055 grid_integrate_task_list 93 9.1 13.459 13.749 13.459 13.749 mp2_ri_gpw_compute_en_expansio 65 7.0 0.112 0.130 10.924 11.017 local_gemm 65 8.0 10.812 10.902 10.812 10.902 mp2_ri_gpw_compute_en_comm 17 7.0 0.070 0.092 2.441 2.936 mp_sendrecv_dm3 1054 8.0 1.883 2.524 1.883 2.524 dbcsr_multiply_generic 176 8.0 0.008 0.009 1.888 2.093 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.871 2.077 scf_env_do_scf 1 3.0 0.000 0.000 2.022 2.022 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 2.022 2.022 get_2c_integrals 1 6.0 0.000 0.000 1.157 1.186 multiply_cannon 176 9.0 0.016 0.017 1.094 1.168 multiply_cannon_loop 176 10.0 0.002 0.002 1.038 1.111 eigensolver 11 5.8 0.001 0.001 1.076 1.078 qs_scf_new_mos 10 5.0 0.000 0.000 1.058 1.064 multiply_cannon_multrec 246 11.0 0.887 0.934 0.892 0.939 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.908 0.909 make_m2s 352 9.0 0.003 0.003 0.756 0.906 cp_fm_redistribute_end 11 7.8 0.339 0.897 0.354 0.901 make_images 352 10.0 0.052 0.053 0.744 0.894 compute_2c_integrals 1 7.0 0.003 0.004 0.854 0.874 cp_fm_diag_elpa_base 11 7.8 0.533 0.856 0.544 0.873 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.760 0.780 mp2_eri_2c_integrate_gpw 1 9.0 0.199 0.207 0.759 0.779 pw_transfer 2120 10.5 0.044 0.047 0.760 0.774 fft_wrap_pw1pw2 1768 11.4 0.004 0.005 0.701 0.712 ------------------------------------------------------------------------------- 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=58.956999999999994, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=87.584, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=25.815, 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=10.168, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.17, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.019, 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=7.461999999999996, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.459, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.812, 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=0.913, 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=0.887, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.883, 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 0.086 126.490 126.490 qs_energies 1 2.0 0.000 0.000 125.093 125.093 scf_env_do_scf 1 3.0 0.000 0.000 118.461 118.461 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 118.461 118.461 qs_ks_update_qs_env 15 5.0 0.000 0.000 49.518 49.518 rebuild_ks_matrix 15 6.0 0.000 0.000 49.305 49.305 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 49.305 49.305 qs_scf_new_mos 15 5.0 0.000 0.000 43.819 43.819 eigensolver 15 6.0 0.001 0.001 35.976 35.976 qs_vxc_create 15 8.0 0.017 0.017 33.969 33.969 calculate_dispersion_nonloc 15 9.0 6.723 6.723 29.524 29.524 cp_fm_diag_elpa 15 7.0 0.000 0.000 23.499 23.499 cp_fm_diag_elpa_base 15 8.0 20.903 20.903 23.499 23.499 pw_transfer 1191 10.0 0.059 0.059 23.433 23.433 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 23.251 23.251 qs_rho_update_rho_low 16 5.0 0.000 0.000 22.134 22.134 calculate_rho_elec 16 6.0 0.218 0.218 22.134 22.134 grid_collocate_task_list 16 7.0 20.741 20.741 20.741 20.741 fft_wrap_pw1pw2_150 765 12.0 3.622 3.622 16.877 16.877 sum_up_and_integrate 15 8.0 0.110 0.110 14.140 14.140 integrate_v_rspace 15 9.0 0.021 0.021 14.030 14.030 grid_integrate_task_list 15 10.0 13.481 13.481 13.481 13.481 fft3d_s 1087 13.0 10.344 10.344 10.351 10.351 cp_fm_cholesky_restore 45 7.0 10.173 10.173 10.173 10.173 pw_scatter_s 585 13.1 7.339 7.339 7.339 7.339 fft_wrap_pw1pw2_200 197 12.3 0.797 0.797 6.180 6.180 dbcsr_complete_redistribute 46 8.3 2.230 2.230 5.623 5.623 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.582 5.582 cp_fm_upper_to_full 30 8.0 4.898 4.898 4.898 4.898 xc_vxc_pw_create 15 9.0 0.233 0.233 4.428 4.428 vdW_energy 15 10.0 4.394 4.394 4.394 4.394 gspace_mixing 14 5.0 0.170 0.170 4.207 4.207 broyden_mixing 14 6.0 3.569 3.569 3.569 3.569 init_scf_run 1 3.0 0.000 0.000 3.118 3.118 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.045 3.045 xc_pw_derive 90 11.0 0.001 0.001 2.910 2.910 calculate_dm_sparse 15 6.0 0.020 0.020 2.619 2.619 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 2.532 2.532 ------------------------------------------------------------------------------- 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 65.833 65.845 qs_energies 1 2.0 0.001 0.013 65.395 65.407 scf_env_do_scf 1 3.0 0.000 0.001 61.237 61.237 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 61.237 61.237 qs_ks_update_qs_env 15 5.0 0.000 0.000 25.093 25.107 rebuild_ks_matrix 15 6.0 0.000 0.000 25.052 25.066 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 25.051 25.066 qs_rho_update_rho_low 16 5.0 0.000 0.000 22.550 22.554 calculate_rho_elec 16 6.0 0.007 0.007 22.549 22.554 grid_collocate_task_list 16 7.0 19.555 20.251 19.555 20.251 sum_up_and_integrate 15 8.0 0.013 0.016 15.435 15.483 integrate_v_rspace 15 9.0 0.000 0.001 15.422 15.476 qs_scf_new_mos 15 5.0 0.000 0.001 14.236 14.301 grid_integrate_task_list 15 10.0 13.149 13.766 13.149 13.766 eigensolver 15 6.0 0.001 0.002 13.228 13.277 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.385 9.396 cp_fm_diag_elpa_base 15 8.0 9.230 9.252 9.377 9.378 qs_vxc_create 15 8.0 0.001 0.001 9.316 9.334 calculate_dispersion_nonloc 15 9.0 0.912 0.944 7.424 7.443 pw_transfer 1191 10.0 0.087 0.094 6.954 7.030 fft_wrap_pw1pw2 1086 11.0 0.012 0.014 6.771 6.855 fft3d_ps 1086 13.0 2.477 2.646 5.074 5.262 fft_wrap_pw1pw2_150 765 12.0 0.287 0.326 4.294 4.320 cp_fm_cholesky_restore 45 7.0 3.689 3.750 3.689 3.750 rs_pw_transfer 158 9.4 0.001 0.002 2.883 3.247 density_rs2pw 16 7.0 0.001 0.001 2.858 3.131 mp_waitany 520 11.3 2.061 2.816 2.061 2.816 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.459 2.459 fft_wrap_pw1pw2_200 197 12.3 0.193 0.220 2.365 2.450 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.154 2.360 mp_alltoall_z22v 1086 15.0 1.998 2.267 1.998 2.267 rs_pw_transfer_RS2PW_200 18 8.8 0.029 0.032 1.418 2.235 mp_alltoall_d11v 217 9.2 1.967 2.125 1.967 2.125 rs_gather_matrices 15 10.0 0.020 0.024 1.758 1.922 xc_vxc_pw_create 15 9.0 0.015 0.019 1.891 1.917 x_to_yz 585 14.1 0.336 0.354 1.318 1.478 init_scf_run 1 3.0 0.000 0.001 1.417 1.418 yz_to_x 501 13.9 0.239 0.284 1.255 1.404 vdW_energy 15 10.0 1.346 1.400 1.346 1.400 build_core_ppnl 1 5.0 1.263 1.393 1.263 1.393 xc_pw_derive 90 11.0 0.001 0.001 1.277 1.352 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.326 1.326 ------------------------------------------------------------------------------- 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=50.848, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.903, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.741, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.481, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.344, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.173, 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=17.733000000000004, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=9.23, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.555, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.149, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.689, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.477, 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 0.083 0.083 278.110 278.110 qs_energies 1 2.0 0.000 0.000 277.968 277.968 ls_scf 1 3.0 0.000 0.000 276.730 276.730 ls_scf_main 1 4.0 0.002 0.002 267.520 267.520 density_matrix_trs4 11 5.0 0.012 0.012 175.350 175.350 arnoldi_extremal 12 6.1 0.000 0.000 88.936 88.936 arnoldi_normal_ev 12 7.1 0.014 0.014 88.935 88.935 dbcsr_matrix_vector_mult 652 9.0 0.171 0.171 87.013 87.013 ls_scf_dm_to_ks 11 5.0 0.000 0.000 86.929 86.929 build_subspace 23 8.1 0.078 0.078 86.903 86.903 dbcsr_matrix_vector_mult_local 652 10.0 85.551 85.551 85.560 85.560 matrix_ls_to_qs 11 6.0 0.000 0.000 83.635 83.635 dbcsr_multiply_generic 185 6.1 0.819 0.819 75.546 75.546 multiply_cannon 185 7.1 0.285 0.285 45.441 45.441 dbcsr_copy_into_existing 11 7.0 45.208 45.208 45.209 45.209 dbcsr_complete_redistribute 23 7.5 30.731 30.731 42.141 42.141 matrix_decluster 11 7.0 0.000 0.000 38.425 38.425 multiply_cannon_loop 185 8.1 0.245 0.245 33.245 33.245 make_m2s 370 7.1 0.038 0.038 25.435 25.435 make_images 370 8.1 10.691 10.691 23.815 23.815 multiply_cannon_multrec 185 9.1 23.453 23.453 23.635 23.635 dbcsr_finalize 646 7.5 0.162 0.162 15.260 15.260 dbcsr_merge_all 597 8.5 2.397 2.397 14.032 14.032 setup_rec_index_2d 370 8.1 11.818 11.818 11.818 11.818 dbcsr_sort_indices 1103 9.9 10.868 10.868 10.868 10.868 tree_to_linear_d 110 9.4 10.333 10.333 10.333 10.333 calculate_norms 370 9.1 9.365 9.365 9.365 9.365 quick_finalize 395 10.0 0.341 0.341 9.350 9.350 dbcsr_special_finalize 370 9.1 0.002 0.002 8.649 8.649 ls_scf_init_scf 1 4.0 0.000 0.000 8.505 8.505 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.170 8.170 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.507 7.507 ------------------------------------------------------------------------------- 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 0.040 0.053 68.521 68.532 qs_energies 1 2.0 0.000 0.000 68.391 68.392 ls_scf 1 3.0 0.000 0.000 68.340 68.341 ls_scf_main 1 4.0 0.000 0.008 65.727 65.729 density_matrix_trs4 11 5.0 0.006 0.017 63.156 63.219 dbcsr_multiply_generic 185 6.1 0.059 0.084 59.819 60.125 multiply_cannon 185 7.1 0.034 0.037 49.908 50.672 multiply_cannon_loop 185 8.1 0.121 0.142 47.396 48.658 multiply_cannon_multrec 1480 9.1 29.339 32.106 29.627 32.422 mp_waitall_1 11936 10.3 15.148 17.352 15.148 17.352 multiply_cannon_metrocomm3 1480 9.1 0.014 0.019 8.872 12.262 make_m2s 370 7.1 0.035 0.037 6.969 7.020 make_images 370 8.1 0.628 0.668 6.841 6.890 multiply_cannon_metrocomm1 1480 9.1 0.008 0.010 3.469 6.353 calculate_norms 2960 9.1 5.246 6.298 5.246 6.298 make_images_data 370 9.1 0.009 0.011 3.066 3.285 mp_sum_l 1119 5.6 1.859 2.985 1.859 2.985 hybrid_alltoall_any 393 9.9 0.203 1.228 2.677 2.896 arnoldi_extremal 12 6.1 0.000 0.001 2.387 2.409 arnoldi_normal_ev 12 7.1 0.001 0.004 2.387 2.408 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.237 2.349 build_subspace 23 8.1 0.020 0.026 2.292 2.293 dbcsr_complete_redistribute 23 7.5 1.194 1.257 1.982 2.123 matrix_ls_to_qs 11 6.0 0.000 0.000 1.934 2.081 dbcsr_matrix_vector_mult 652 9.0 0.009 0.043 1.963 2.021 ls_scf_init_scf 1 4.0 0.000 0.000 1.994 1.994 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.968 1.975 make_images_pack 370 9.1 1.732 1.954 1.736 1.958 matrix_decluster 11 7.0 0.000 0.000 1.792 1.937 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.793 1.796 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 0.984 1.792 dbcsr_matrix_vector_mult_local 652 10.0 1.621 1.689 1.622 1.691 buffer_matrices_ensure_size 370 8.1 1.434 1.603 1.434 1.603 dbcsr_finalize 646 7.5 0.008 0.008 1.418 1.565 ------------------------------------------------------------------------------- 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=71.98399999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=85.551, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=45.208, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.731, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.453, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.818, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.365, 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 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=12.381999999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.621, 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=1.194, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=29.339, 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=5.246, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=15.148, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.732, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.859, 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 70.857 70.857 lib_test 1 2.0 0.000 0.000 70.850 70.850 dbcsr_run_tests 3 3.0 0.002 0.002 70.850 70.850 test_multiplies_multiproc 3 4.0 0.001 0.001 55.104 55.104 dbcsr_redistribute 9 5.0 35.560 35.560 37.149 37.149 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.632 16.632 dbcsr_make_random_matrix 9 4.0 12.668 12.668 15.638 15.638 multiply_cannon 9 6.0 0.001 0.001 11.818 11.818 multiply_cannon_loop 9 7.0 0.020 0.020 11.462 11.462 multiply_cannon_multrec 9 8.0 11.441 11.441 11.442 11.442 dbcsr_finalize 27 5.7 0.009 0.009 5.586 5.586 dbcsr_merge_all 18 6.5 2.054 2.054 4.842 4.842 dbcsr_data_release 975 7.6 2.799 2.799 2.799 2.799 tree_to_linear_d 9 7.0 1.932 1.932 1.932 1.932 make_m2s 18 6.0 0.001 0.001 1.628 1.628 make_images 18 7.0 0.551 0.551 1.575 1.575 ------------------------------------------------------------------------------- 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 0.010 18.343 18.347 lib_test 1 2.0 0.000 0.000 18.314 18.334 dbcsr_run_tests 3 3.0 0.000 0.001 18.314 18.333 test_multiplies_multiproc 3 4.0 0.000 0.002 17.471 17.536 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.057 16.160 multiply_cannon 9 6.0 0.001 0.002 14.197 14.502 multiply_cannon_loop 9 7.0 0.002 0.004 13.884 14.209 multiply_cannon_multrec 72 8.0 11.624 12.153 11.625 12.154 mp_waitall_1 576 9.2 2.587 3.168 2.587 3.168 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.972 2.538 dbcsr_data_release 444 7.6 0.783 0.903 0.783 0.903 mp_sum_l 390 2.5 0.450 0.892 0.450 0.892 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.446 0.889 dbcsr_make_random_matrix 9 4.0 0.662 0.668 0.816 0.845 dbcsr_finalize 27 5.7 0.000 0.000 0.732 0.810 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.280 0.791 make_m2s 18 6.0 0.001 0.001 0.709 0.769 make_images 18 7.0 0.021 0.023 0.705 0.766 dbcsr_destroy 111 5.9 0.000 0.000 0.625 0.732 dbcsr_merge_all 18 6.5 0.105 0.130 0.572 0.679 dbcsr_redistribute 9 5.0 0.246 0.280 0.425 0.455 make_images_data 18 8.0 0.000 0.001 0.367 0.451 dbcsr_data_copy_aa2 18 7.5 0.339 0.414 0.339 0.414 hybrid_alltoall_any 18 9.0 0.028 0.114 0.326 0.403 ------------------------------------------------------------------------------- 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=6.334999999999994, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.56, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.668, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.441, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.799, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.054, 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=1.8859999999999992, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.246, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.662, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.624, 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=0.105, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.587, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.45, 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 0.051 0.051 131.268 131.268 qs_mol_dyn_low 1 2.0 0.003 0.003 129.859 129.859 velocity_verlet 5 3.0 0.003 0.003 105.988 105.988 qmmm_el_coupling 6 3.8 0.000 0.000 86.390 86.390 qmmm_elec_with_gaussian 6 4.8 0.013 0.013 86.380 86.380 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 85.740 85.740 qmmm_elec_gaussian_low_G 6 6.8 84.851 84.851 84.851 84.851 qs_forces 6 3.8 0.000 0.000 35.035 35.035 qs_energies 6 4.8 0.000 0.000 31.119 31.119 scf_env_do_scf 6 5.8 0.001 0.001 28.822 28.822 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 25.155 25.155 rebuild_ks_matrix 45 8.4 0.000 0.000 24.073 24.073 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.073 24.073 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.609 20.609 pw_transfer 966 12.3 0.052 0.052 17.264 17.264 fft_wrap_pw1pw2 801 13.6 0.006 0.006 17.029 17.029 fft_wrap_pw1pw2_150 507 15.2 2.208 2.208 16.611 16.611 qs_vxc_create 45 10.4 0.001 0.001 13.393 13.393 xc_vxc_pw_create 45 11.4 0.680 0.680 13.392 13.392 xc_pw_derive 270 13.4 0.002 0.002 9.459 9.459 fft3d_s 802 15.6 7.809 7.809 7.817 7.817 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.300 7.300 calculate_rho_elec 45 8.9 0.562 0.562 7.300 7.300 xc_rho_set_and_dset_create 45 12.4 0.599 0.599 6.926 6.926 xc_pw_divergence 45 12.4 0.001 0.001 5.733 5.733 pw_scatter_s 429 15.8 5.653 5.653 5.653 5.653 qmmm_forces 6 3.8 0.001 0.001 5.251 5.251 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 4.911 4.911 pw_integral_ab 2539 7.4 4.454 4.454 4.454 4.454 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.186 4.186 qs_ks_ddapc 45 10.4 0.001 0.001 4.147 4.147 init_scf_loop 6 6.8 0.000 0.000 3.658 3.658 qmmm_forces_gaussian_low_G 6 6.8 3.480 3.480 3.480 3.480 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.471 3.471 grid_collocate_task_list 45 9.9 3.430 3.430 3.430 3.430 sum_up_and_integrate 45 10.4 0.338 0.338 3.395 3.395 density_rs2pw 45 9.9 0.002 0.002 3.308 3.308 integrate_v_rspace 45 11.4 0.006 0.006 3.057 3.057 ------------------------------------------------------------------------------- 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 0.039 0.056 54.836 54.847 qs_mol_dyn_low 1 2.0 0.003 0.004 53.826 53.888 qs_forces 6 3.8 0.001 0.001 39.275 39.275 qs_energies 6 4.8 0.000 0.000 37.460 37.461 scf_env_do_scf 6 5.8 0.000 0.001 36.535 36.535 scf_env_do_scf_inner_loop 113 6.2 0.002 0.016 35.043 35.044 rebuild_ks_matrix 119 8.1 0.000 0.001 26.110 26.121 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.017 26.110 26.121 qs_ks_update_qs_env 119 7.3 0.001 0.001 24.579 24.589 velocity_verlet 5 3.0 0.002 0.003 22.714 22.717 pw_transfer 2446 12.3 0.195 0.209 17.533 17.947 fft_wrap_pw1pw2 2059 13.4 0.023 0.026 17.091 17.541 fft_wrap_pw1pw2_150 1321 14.9 1.342 1.564 16.482 16.890 qs_vxc_create 119 10.1 0.002 0.003 13.906 13.909 xc_vxc_pw_create 119 11.1 0.151 0.210 13.904 13.907 fft3d_ps 2059 15.4 7.018 7.900 12.811 13.587 xc_pw_derive 714 13.1 0.008 0.010 10.487 10.802 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.356 10.357 calculate_rho_elec 119 8.3 0.049 0.055 10.356 10.357 sum_up_and_integrate 119 10.1 0.085 0.106 8.917 8.931 integrate_v_rspace 119 11.1 0.003 0.004 8.832 8.859 qmmm_forces 6 3.8 0.002 0.002 7.393 7.394 qmmm_forces_with_gaussian 6 4.8 0.008 0.010 7.036 7.249 xc_pw_divergence 119 12.1 0.004 0.005 6.820 7.063 xc_rho_set_and_dset_create 119 12.1 0.363 0.450 6.729 6.919 qmmm_el_coupling 6 3.8 0.000 0.000 6.252 6.366 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 6.251 6.364 rs_pw_transfer 988 11.5 0.011 0.012 6.113 6.363 density_rs2pw 119 9.3 0.006 0.007 5.766 5.977 mp_alltoall_z22v 2059 17.4 4.372 5.391 4.372 5.391 potential_pw2rs 119 12.1 0.006 0.008 5.158 5.183 grid_collocate_task_list 119 9.3 4.423 4.665 4.423 4.665 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.859 3.926 grid_integrate_task_list 119 12.1 3.407 3.618 3.407 3.618 x_to_yz 1095 16.8 0.806 0.901 3.115 3.617 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.326 3.437 yz_to_x 964 16.0 0.560 0.696 2.622 3.265 qmmm_forces_gaussian_low_G 6 6.8 3.169 3.234 3.169 3.234 qmmm_elec_gaussian_low_G 6 6.8 2.739 2.847 2.739 2.847 pw_restrict_s3 18 5.8 1.379 1.438 2.546 2.750 mp_waitany 4028 12.8 2.308 2.720 2.308 2.720 rs_pw_transfer_PW2RS_150 125 13.9 0.758 0.871 2.404 2.459 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.156 2.269 pw_prolongate_s3 18 6.8 1.165 1.200 2.156 2.269 rs_pw_transfer_RS2PW_150 125 11.2 0.594 0.702 1.799 2.054 qs_ks_ddapc 119 10.1 0.002 0.002 1.905 1.985 qs_scf_new_mos 113 7.2 0.000 0.000 1.941 1.946 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.940 1.945 ot_scf_mini 113 9.2 0.001 0.001 1.858 1.862 mp_waitall_1 188862 16.2 1.623 1.828 1.623 1.828 dbcsr_multiply_generic 2588 12.3 0.056 0.058 1.744 1.772 pw_integral_ab 2761 7.7 1.199 1.313 1.484 1.582 pw_scatter_p 1095 15.8 1.541 1.575 1.541 1.575 pw_gather_p 964 15.0 1.344 1.561 1.344 1.561 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.541 1.542 init_scf_loop 6 6.8 0.000 0.000 1.489 1.489 mp_sum_dm3 33 5.7 1.280 1.339 1.280 1.339 ot_mini 113 10.2 0.000 0.000 1.136 1.141 pw_copy 1670 12.6 0.995 1.130 0.995 1.130 ------------------------------------------------------------------------------- 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=21.590999999999994, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=84.851, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.809, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.653, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.454, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.48, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.43, 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=28.509, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.739, 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=1.199, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.169, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.423, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.372, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.407, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.018, yerr=0.0 Summary: Performance test took 34 minutes. Status: OK Removing intermediate container 7e65c1b9ee48 ---> 936f2df1fc11 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in ad492acbb8d3 Removing intermediate container ad492acbb8d3 ---> e6796274a612 Step 42/42 : ENTRYPOINT [] ---> Running in afb8cfc01217 Removing intermediate container afb8cfc01217 ---> 47b6dc6d4eca [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 47b6dc6d4eca Successfully tagged us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2022-11-20 19:56:35+00:00