StartDate: 2022-08-13 19:05:57+00:00 CpuId: 32x AMD (unknown model) [Zen 3], 7nm (SMT disabled) CommitSHA: 9a2d883152d90adc55a7b00eefea514ac22c4a6f CommitTime: 2022-08-13 14:07:00 +0200 CommitAuthor: Hans Pabst CommitSubject: DBM/benchmark: minor enhancements (#2242) Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=9a2d883152d90adc55a7b00eefea514ac22c4a6f Sending build context to Docker daemon 364.2MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu d19f32bd9e41: Already exists Digest: sha256:34fea4f31bf187bc915536831fd0afc9d214755bf700b5cdb1336c82516d154e Status: Downloaded newer image for ubuntu:22.04 ---> df5de72bdb3b Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 026e35f2a85c Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 61e4cd54df66 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 9302e3cfee49 Step 5/42 : RUN mkdir scripts ---> Using cache ---> ba1db08844ca 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 ---> 4fa59dbbe3c5 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 92a7ebae54e4 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --mpi-mode=mpich --with-gcc=system --dry-run ---> Using cache ---> fdcb02913a6b Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> bbf5a70e57e9 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 57713487903f Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> a7273f099530 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 5f5e186a6792 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> daaf389ae447 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 6767e014fd7d Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 8bd37651db46 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 7036e597e5e8 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> ff2b1e1cb16d Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> da0abcd2ccad Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> ea1516b197ec Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> c5c4ef116433 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 0e2954296d9e Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> d0b0ced73c5c Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> cc25e8fd9377 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 915029cf8ed8 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 20510d2c9104 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 55a50ff28104 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 02b1fc9204dc Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 67cf34b67198 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 74e513362a2c Step 30/42 : COPY ./Makefile . ---> Using cache ---> a24b1f25fab5 Step 31/42 : COPY ./src ./src ---> 01b189235ef9 Step 32/42 : COPY ./exts ./exts ---> 52970db029e5 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> eac9c846be97 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 4cf2ed5c30c8 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 4cf2ed5c30c8 ---> 9a01158c8271 Step 35/42 : COPY ./data ./data ---> 93ab54b925ff Step 36/42 : COPY ./tests ./tests ---> 406275029197 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> c411e427ae0c Step 38/42 : COPY ./benchmarks ./benchmarks ---> 3fb57cfecfc5 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 189180d7b791 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in a8b2330c38fa ========== 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 0.030 0.030 92.903 92.903 qs_mol_dyn_low 1 2.0 0.003 0.003 92.289 92.289 qs_forces 11 3.9 0.001 0.001 92.250 92.250 qs_energies 11 4.9 0.001 0.001 86.086 86.086 scf_env_do_scf 11 5.9 0.001 0.001 75.252 75.252 velocity_verlet 10 3.0 0.002 0.002 58.464 58.464 scf_env_do_scf_inner_loop 108 6.5 0.012 0.012 58.337 58.337 qs_scf_new_mos 108 7.5 0.001 0.001 23.137 23.137 qs_scf_loop_do_ot 108 8.5 0.001 0.001 23.137 23.137 ot_scf_mini 108 9.5 0.002 0.002 21.752 21.752 rebuild_ks_matrix 119 8.3 0.001 0.001 21.089 21.089 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 21.088 21.088 dbcsr_multiply_generic 2286 12.5 0.161 0.161 20.377 20.377 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.745 19.745 calculate_rho_elec 119 8.7 0.953 0.953 19.744 19.744 qs_ks_update_qs_env 119 7.6 0.001 0.001 19.377 19.377 init_scf_loop 11 6.9 0.000 0.000 16.760 16.760 grid_collocate_task_list 119 9.7 15.398 15.398 15.398 15.398 prepare_preconditioner 11 7.9 0.000 0.000 14.157 14.157 make_preconditioner 11 8.9 0.000 0.000 14.157 14.157 sum_up_and_integrate 119 10.3 0.195 0.195 13.248 13.248 integrate_v_rspace 119 11.3 0.090 0.090 13.053 13.053 make_full_inverse_cholesky 11 9.9 0.000 0.000 13.044 13.044 ot_mini 108 10.5 0.001 0.001 12.203 12.203 grid_integrate_task_list 119 12.3 11.022 11.022 11.022 11.022 make_m2s 4572 13.5 0.046 0.046 10.980 10.980 qs_ot_get_derivative 108 11.5 0.001 0.001 6.633 6.633 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.262 6.262 dbcsr_make_dense_low 5837 15.5 0.066 0.066 6.029 6.029 pw_transfer 1439 11.6 0.056 0.056 6.006 6.006 make_dense_data 5837 16.5 5.250 5.250 5.949 5.949 qs_ot_get_p 119 10.4 0.001 0.001 5.942 5.942 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.789 5.789 ot_diis_step 108 11.5 0.004 0.004 5.567 5.567 make_images 4572 14.5 2.089 2.089 5.374 5.374 multiply_cannon 2286 13.5 0.178 0.178 5.344 5.344 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.244 5.244 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.042 5.042 apply_single 119 13.6 0.000 0.000 5.041 5.041 fft_wrap_pw1pw2_140 487 13.2 0.433 0.433 4.940 4.940 multiply_cannon_loop 2286 14.5 0.093 0.093 4.877 4.877 multiply_cannon_multrec 2286 15.5 4.734 4.734 4.783 4.783 qs_ot_p2m_diag 50 11.0 0.154 0.154 4.618 4.618 cp_fm_cholesky_decompose 22 10.9 4.574 4.574 4.574 4.574 cp_fm_cholesky_invert 11 10.9 4.341 4.341 4.341 4.341 cp_dbcsr_syevd 50 12.0 0.002 0.002 4.213 4.213 cp_fm_diag_elpa 50 13.0 0.000 0.000 4.116 4.116 cp_fm_diag_elpa_base 50 14.0 4.055 4.055 4.115 4.115 init_scf_run 11 5.9 0.002 0.002 3.895 3.895 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.893 3.893 dbcsr_copy 2102 12.0 0.242 0.242 3.697 3.697 dbcsr_complete_redistribute 329 12.2 1.918 1.918 3.625 3.625 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.485 3.485 dbcsr_copy_into_existing 22 7.9 3.415 3.415 3.415 3.415 density_rs2pw 119 9.7 0.003 0.003 3.393 3.393 wfi_extrapolate 11 7.9 0.001 0.001 3.381 3.381 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.268 3.268 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.974 2.974 qs_create_task_list 11 7.9 0.000 0.000 2.898 2.898 generate_qs_task_list 11 8.9 1.973 1.973 2.898 2.898 fft3d_s 1202 14.6 2.867 2.867 2.872 2.872 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.676 2.676 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.569 2.569 pw_poisson_solve 119 10.3 0.877 0.877 2.361 2.361 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.309 2.309 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.056 2.056 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 2.031 2.031 potential_pw2rs 119 12.3 0.045 0.045 1.941 1.941 dbcsr_data_release 279534 16.0 1.924 1.924 1.924 1.924 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.881 1.881 ------------------------------------------------------------------------------- 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 0.008 0.027 51.204 51.215 qs_mol_dyn_low 1 2.0 0.004 0.009 51.085 51.089 qs_forces 11 3.9 0.001 0.001 51.037 51.037 qs_energies 11 4.9 0.001 0.001 47.565 47.567 scf_env_do_scf 11 5.9 0.001 0.002 43.731 43.731 scf_env_do_scf_inner_loop 108 6.5 0.003 0.019 40.486 40.486 velocity_verlet 10 3.0 0.001 0.003 30.215 30.216 rebuild_ks_matrix 119 8.3 0.000 0.001 19.683 19.776 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.021 19.683 19.776 qs_ks_update_qs_env 119 7.6 0.001 0.001 17.581 17.664 qs_rho_update_rho_low 119 7.7 0.001 0.001 15.292 15.302 calculate_rho_elec 119 8.7 0.031 0.036 15.292 15.302 sum_up_and_integrate 119 10.3 0.018 0.021 15.237 15.272 integrate_v_rspace 119 11.3 0.004 0.005 15.219 15.256 dbcsr_multiply_generic 2286 12.5 0.073 0.091 13.353 13.541 grid_collocate_task_list 119 9.7 9.708 11.700 9.708 11.700 grid_integrate_task_list 119 12.3 8.719 11.486 8.719 11.486 qs_scf_new_mos 108 7.5 0.001 0.001 10.778 10.883 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.777 10.882 ot_scf_mini 108 9.5 0.002 0.003 10.096 10.208 multiply_cannon 2286 13.5 0.130 0.154 9.625 10.005 multiply_cannon_loop 2286 14.5 0.094 0.126 8.982 9.420 mp_waitall_1 169478 16.3 8.013 8.832 8.013 8.832 rs_pw_transfer 974 11.9 0.011 0.016 6.239 6.734 ot_mini 108 10.5 0.001 0.001 5.912 6.026 density_rs2pw 119 9.7 0.005 0.007 5.169 5.618 multiply_cannon_metrocomm3 18288 15.5 0.039 0.053 5.033 5.592 mp_alltoall_d11v 2130 13.8 3.183 3.679 3.183 3.679 mp_waitany 9880 13.7 2.887 3.606 2.887 3.606 potential_pw2rs 119 12.3 0.006 0.008 3.525 3.552 pw_transfer 1439 11.6 0.091 0.108 3.460 3.547 multiply_cannon_multrec 18288 15.5 3.108 3.491 3.118 3.505 rs_gather_matrices 119 12.3 0.085 0.098 2.937 3.438 fft_wrap_pw1pw2 1201 12.6 0.009 0.011 3.303 3.377 init_scf_loop 11 6.9 0.000 0.000 3.232 3.233 qs_ot_get_derivative 108 11.5 0.001 0.001 3.079 3.184 rs_pw_transfer_RS2PW_140 130 11.5 0.263 0.308 2.603 3.098 fft_wrap_pw1pw2_140 487 13.2 0.271 0.330 2.802 2.944 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.692 2.808 apply_single 119 13.6 0.000 0.001 2.691 2.807 ot_diis_step 108 11.5 0.004 0.005 2.804 2.804 init_scf_run 11 5.9 0.000 0.005 2.625 2.625 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.625 2.625 make_m2s 4572 13.5 0.047 0.059 2.471 2.526 fft3d_ps 1201 14.6 1.218 1.374 2.400 2.487 wfi_extrapolate 11 7.9 0.001 0.001 2.379 2.379 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.267 2.282 make_images 4572 14.5 0.123 0.145 2.129 2.191 multiply_cannon_metrocomm1 18288 15.5 0.019 0.028 0.540 1.744 mp_sum_d 4129 12.0 1.124 1.540 1.124 1.540 qs_ot_get_p 119 10.4 0.001 0.001 1.400 1.526 rs_pw_transfer_PW2RS_140 130 13.9 0.589 0.699 1.450 1.486 make_images_data 4572 15.5 0.037 0.045 1.124 1.277 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.922 1.173 prepare_preconditioner 11 7.9 0.000 0.000 1.140 1.157 make_preconditioner 11 8.9 0.000 0.000 1.140 1.157 mp_alltoall_z22v 1201 16.6 0.916 1.150 0.916 1.150 mp_sum_l 11218 13.2 0.801 1.129 0.801 1.129 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.049 1.114 hybrid_alltoall_any 4725 16.4 0.065 0.213 0.985 1.085 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.039 1.064 ------------------------------------------------------------------------------- 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=51.925000000000004, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.398, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=11.022, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.25, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.734, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.574, 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_alltoall_d11v", label="mp_alltoall_d11v", 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=18.473, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.708, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.719, 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="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.108, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.013, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=3.183, 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 0.027 0.027 116.420 116.420 qs_mol_dyn_low 1 2.0 0.003 0.003 115.767 115.767 qs_forces 11 3.9 0.001 0.001 115.729 115.729 qs_energies 11 4.9 0.001 0.001 107.732 107.732 scf_env_do_scf 11 5.9 0.001 0.001 94.787 94.787 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 76.273 76.273 velocity_verlet 10 3.0 0.002 0.002 73.515 73.515 rebuild_ks_matrix 107 8.3 0.001 0.001 34.479 34.479 qs_ks_build_kohn_sham_matrix 107 9.3 0.010 0.010 34.479 34.479 qs_rho_update_rho_low 107 7.7 0.000 0.000 32.129 32.129 calculate_rho_elec 107 8.7 0.858 0.858 32.128 32.128 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.948 30.948 grid_collocate_task_list 107 9.7 28.074 28.074 28.074 28.074 sum_up_and_integrate 107 10.3 0.170 0.170 27.352 27.352 integrate_v_rspace 107 11.3 0.087 0.087 27.181 27.181 grid_integrate_task_list 107 12.3 25.280 25.280 25.280 25.280 qs_scf_new_mos 96 7.5 0.001 0.001 20.168 20.168 qs_scf_loop_do_ot 96 8.5 0.001 0.001 20.167 20.167 ot_scf_mini 96 9.5 0.002 0.002 18.741 18.741 dbcsr_multiply_generic 1966 12.4 0.137 0.137 18.427 18.427 init_scf_loop 11 6.9 0.000 0.000 18.381 18.381 prepare_preconditioner 11 7.9 0.000 0.000 14.251 14.251 make_preconditioner 11 8.9 0.000 0.000 14.251 14.251 make_full_inverse_cholesky 11 9.9 0.000 0.000 13.114 13.114 ot_mini 96 10.5 0.001 0.001 10.503 10.503 make_m2s 3932 13.4 0.039 0.039 9.897 9.897 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.760 6.760 pw_transfer 1295 11.6 0.050 0.050 5.682 5.682 init_scf_run 11 5.9 0.002 0.002 5.544 5.544 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.542 5.542 qs_ot_get_derivative 96 11.5 0.001 0.001 5.493 5.493 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.473 5.473 dbcsr_make_dense_low 4961 15.5 0.073 0.073 5.261 5.261 make_dense_data 4961 16.5 4.569 4.569 5.176 5.176 ot_diis_step 96 11.5 0.003 0.003 5.007 5.007 qs_ot_get_p 107 10.4 0.001 0.001 4.987 4.987 multiply_cannon 1966 13.4 0.168 0.168 4.957 4.957 make_images 3932 14.4 1.913 1.913 4.951 4.951 wfi_extrapolate 11 7.9 0.001 0.001 4.886 4.886 fft_wrap_pw1pw2_140 439 13.2 0.457 0.457 4.671 4.671 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.607 4.607 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.585 4.585 apply_single 107 13.6 0.000 0.000 4.585 4.585 cp_fm_cholesky_decompose 22 10.9 4.578 4.578 4.578 4.578 multiply_cannon_loop 1966 14.4 0.121 0.121 4.511 4.511 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.395 4.395 multiply_cannon_multrec 1966 15.4 4.345 4.345 4.389 4.389 cp_fm_cholesky_invert 11 10.9 4.328 4.328 4.328 4.328 dbcsr_copy 1855 11.9 0.206 0.206 3.818 3.818 qs_ot_p2m_diag 44 11.0 0.137 0.137 3.752 3.752 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.695 3.695 dbcsr_complete_redistribute 317 12.2 1.888 1.888 3.645 3.645 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.600 3.600 dbcsr_copy_into_existing 22 7.9 3.552 3.552 3.552 3.552 cp_dbcsr_syevd 44 12.0 0.002 0.002 3.381 3.381 qs_create_task_list 11 7.9 0.000 0.000 3.320 3.320 generate_qs_task_list 11 8.9 2.405 2.405 3.320 3.320 cp_fm_diag_elpa 44 13.0 0.000 0.000 3.299 3.299 cp_fm_diag_elpa_base 44 14.0 3.245 3.245 3.299 3.299 density_rs2pw 107 9.7 0.003 0.003 3.196 3.196 copy_dbcsr_to_fm 147 11.2 0.002 0.002 2.988 2.988 fft3d_s 1082 14.6 2.717 2.717 2.721 2.721 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.651 2.651 ------------------------------------------------------------------------------- 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 0.022 86.532 86.542 qs_mol_dyn_low 1 2.0 0.003 0.011 86.430 86.437 qs_forces 11 3.9 0.001 0.002 86.381 86.381 qs_energies 11 4.9 0.001 0.001 80.611 80.613 scf_env_do_scf 11 5.9 0.000 0.002 74.697 74.698 scf_env_do_scf_inner_loop 96 6.5 0.002 0.016 69.281 69.281 velocity_verlet 10 3.0 0.001 0.003 51.536 51.537 rebuild_ks_matrix 107 8.3 0.000 0.001 38.171 38.324 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.020 38.171 38.324 sum_up_and_integrate 107 10.3 0.017 0.019 33.906 33.956 integrate_v_rspace 107 11.3 0.004 0.005 33.889 33.942 qs_ks_update_qs_env 107 7.6 0.001 0.001 33.802 33.939 qs_rho_update_rho_low 107 7.7 0.000 0.001 32.218 32.230 calculate_rho_elec 107 8.7 0.027 0.028 32.218 32.229 grid_integrate_task_list 107 12.3 23.895 30.325 23.895 30.325 grid_collocate_task_list 107 9.7 23.213 29.028 23.213 29.028 dbcsr_multiply_generic 1966 12.4 0.065 0.078 13.346 13.606 rs_pw_transfer 878 11.9 0.010 0.013 9.986 10.970 qs_scf_new_mos 96 7.5 0.001 0.001 10.480 10.628 qs_scf_loop_do_ot 96 8.5 0.001 0.001 10.480 10.627 multiply_cannon 1966 13.4 0.115 0.136 9.840 10.405 ot_scf_mini 96 9.5 0.002 0.002 9.876 10.006 multiply_cannon_loop 1966 14.4 0.090 0.127 9.265 9.841 density_rs2pw 107 9.7 0.005 0.006 8.675 9.605 mp_waitall_1 146670 16.2 8.474 9.465 8.474 9.465 mp_waitany 8968 13.7 6.740 7.917 6.740 7.917 mp_alltoall_d11v 1998 13.7 6.798 7.689 6.798 7.689 rs_gather_matrices 107 12.3 0.065 0.081 6.571 7.422 rs_pw_transfer_RS2PW_140 118 11.5 0.234 0.268 6.413 7.391 multiply_cannon_metrocomm3 15728 15.4 0.036 0.049 5.506 6.160 ot_mini 96 10.5 0.001 0.001 5.874 6.019 init_scf_loop 11 6.9 0.000 0.000 5.404 5.404 init_scf_run 11 5.9 0.000 0.004 4.665 4.666 scf_env_initial_rho_setup 11 6.9 0.001 0.010 4.665 4.665 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.518 4.538 wfi_extrapolate 11 7.9 0.001 0.001 4.241 4.241 potential_pw2rs 107 12.3 0.006 0.008 3.385 3.407 multiply_cannon_multrec 15728 15.4 2.923 3.354 2.932 3.367 qs_ot_get_derivative 96 11.5 0.001 0.001 3.094 3.228 pw_transfer 1295 11.6 0.081 0.095 3.055 3.126 fft_wrap_pw1pw2 1081 12.6 0.008 0.010 2.915 2.977 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.667 2.805 apply_single 107 13.6 0.000 0.000 2.666 2.805 ot_diis_step 96 11.5 0.003 0.004 2.741 2.742 fft_wrap_pw1pw2_140 439 13.2 0.238 0.298 2.489 2.581 make_m2s 3932 13.4 0.041 0.050 2.191 2.275 fft3d_ps 1081 14.6 1.076 1.211 2.101 2.199 make_images 3932 14.4 0.108 0.130 1.888 1.951 ------------------------------------------------------------------------------- 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=49.574, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=28.074, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.28, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.578, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.569, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.345, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 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=14.48899999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=23.213, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=23.895, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.923, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=6.798, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.474, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=6.74, 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 0.176 0.176 115.750 115.750 qs_energies 1 2.0 0.000 0.000 114.941 114.941 scf_env_do_scf 1 3.0 0.000 0.000 113.780 113.780 qs_ks_update_qs_env 8 5.0 0.000 0.000 108.451 108.451 rebuild_ks_matrix 7 6.0 0.000 0.000 108.397 108.397 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 108.397 108.397 hfx_ks_matrix 7 8.0 0.000 0.000 98.509 98.509 integrate_four_center 7 9.0 1.310 1.310 98.492 98.492 integrate_four_center_main 7 10.0 0.567 0.567 85.665 85.665 integrate_four_center_bin 449 11.0 85.098 85.098 85.098 85.098 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 59.157 59.157 init_scf_loop 1 4.0 0.000 0.000 54.606 54.606 integrate_four_center_load 7 10.0 0.000 0.000 11.293 11.293 hfx_load_balance 1 11.0 0.001 0.001 11.293 11.293 hfx_load_balance_count 1 12.0 5.652 5.652 5.652 5.652 hfx_load_balance_bin 1 12.0 5.624 5.624 5.624 5.624 qs_vxc_create 14 8.0 0.000 0.000 3.916 3.916 xc_vxc_pw_create 14 9.0 0.131 0.131 3.915 3.915 xc_rho_set_and_dset_create 14 10.0 0.108 0.108 3.020 3.020 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.483 2.483 prepare_preconditioner 1 5.0 0.000 0.000 2.480 2.480 make_preconditioner 1 6.0 0.000 0.000 2.480 2.480 calculate_rho_elec 15 7.4 0.118 0.118 2.435 2.435 xc_functional_eval 35 11.0 0.000 0.000 2.342 2.342 ------------------------------------------------------------------------------- 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 0.194 0.221 136.879 136.893 qs_energies 1 2.0 0.000 0.000 136.548 136.548 scf_env_do_scf 1 3.0 0.000 0.000 136.170 136.170 qs_ks_update_qs_env 8 5.0 0.000 0.000 134.007 134.007 rebuild_ks_matrix 7 6.0 0.000 0.000 133.999 133.999 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 133.999 133.999 hfx_ks_matrix 7 8.0 0.000 0.000 127.606 127.608 integrate_four_center 7 9.0 0.053 0.354 127.597 127.599 integrate_four_center_main 7 10.0 0.003 0.003 81.726 115.115 integrate_four_center_bin 448 11.0 81.723 115.111 81.723 115.111 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 77.045 77.045 init_scf_loop 1 4.0 0.000 0.000 59.124 59.124 mp_sync 70 11.3 33.413 35.741 33.413 35.741 integrate_four_center_load 7 10.0 0.000 0.000 11.765 11.769 hfx_load_balance 1 11.0 0.001 0.001 11.765 11.769 mp_sum_l 1135 8.3 5.966 6.303 5.966 6.303 hfx_load_balance_dist 1 12.0 0.000 0.000 5.825 6.107 hfx_load_balance_bin 1 12.0 2.932 5.897 2.932 5.897 hfx_load_balance_count 1 12.0 2.927 5.785 2.927 5.785 qs_vxc_create 14 8.0 0.000 0.000 3.033 3.033 xc_vxc_pw_create 14 9.0 0.008 0.010 3.033 3.033 ------------------------------------------------------------------------------- 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=17.49900000000001, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=85.098, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.652, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.624, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.31, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.567, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="H2O-hyb_timings_32mpi", title="Timings of H2O-hyb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32mpi", name="rest", label="rest", y=9.861999999999995, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=81.723, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.927, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.932, 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="mp_sync", label="mp_sync", y=33.413, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=5.966, 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 0.012 0.012 85.182 85.182 qs_energies 1 2.0 0.000 0.000 84.811 84.811 mp2_main 1 3.0 0.000 0.000 80.957 80.957 mp2_gpw_main 1 4.0 0.000 0.000 80.614 80.614 rpa_ri_compute_en 1 5.0 0.000 0.000 77.208 77.208 rpa_num_int 1 6.0 0.001 0.001 77.203 77.203 compute_mat_P_omega 1 7.0 0.003 0.003 66.211 66.211 compute_mat_P_omega_contract 10 8.0 8.431 8.431 65.994 65.994 dbt_total 2336 9.6 0.011 0.011 54.055 54.055 dbt_contract 787 11.0 0.033 0.033 47.456 47.456 dbt_tas_total 1149 12.2 0.230 0.230 46.121 46.121 dbt_tas_multiply 807 12.1 0.002 0.002 44.832 44.832 dbt_tas_dbm 807 14.1 0.003 0.003 38.147 38.147 dbm_multiply 807 16.1 38.139 38.139 38.139 38.139 dbt_tas_mm_1N 524 15.1 0.001 0.001 26.687 26.687 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 23.918 23.918 compute_mat_P_omega_calc_M_occ 250 9.0 8.456 8.456 17.903 17.903 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 10.532 10.532 dbt_tas_mm_2 251 15.0 0.001 0.001 9.469 9.469 compute_QP_energies 1 7.0 0.000 0.000 5.777 5.777 compute_self_energy_cubic_gw 1 8.0 0.047 0.047 5.776 5.776 dbt_copy 1103 10.7 0.124 0.124 5.294 5.294 contract_cubic_gw 21 9.0 0.000 0.000 4.801 4.801 scf_env_do_scf 1 3.0 0.000 0.000 3.723 3.723 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 3.723 3.723 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 3.399 3.399 dbt_tas_reserve_blocks_index 3261 14.3 0.152 0.152 3.115 3.115 dbm_reserve_blocks 3628 15.3 3.030 3.030 3.030 3.030 convert_to_new_pgrid 2421 14.1 0.188 0.188 2.629 2.629 dbt_crop 1042 12.0 1.603 1.603 2.525 2.525 dbm_copy 1614 15.1 2.441 2.441 2.441 2.441 dbt_reserve_blocks_index 2280 13.1 0.054 0.054 2.325 2.325 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.318 2.318 dbt_tas_copy 574 11.4 1.390 1.390 2.215 2.215 qs_scf_new_mos 17 5.0 0.000 0.000 2.190 2.190 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.181 2.181 compute_W_cubic_GW 10 7.0 0.004 0.004 2.112 2.112 eigensolver 18 5.9 0.001 0.001 2.097 2.097 cp_fm_diag_elpa 18 6.9 0.000 0.000 1.988 1.988 cp_fm_diag_elpa_base 18 7.9 1.952 1.952 1.987 1.987 dbt_tas_reshape 367 15.0 0.027 0.027 1.859 1.859 dbt_tas_mm_3N 22 15.1 0.000 0.000 1.800 1.800 get_2c_integrals 1 6.0 0.000 0.000 1.770 1.770 dbt_reshape 278 11.9 0.944 0.944 1.732 1.732 ------------------------------------------------------------------------------- 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 0.016 0.032 33.244 33.255 qs_energies 1 2.0 0.000 0.000 33.160 33.161 mp2_main 1 3.0 0.000 0.001 32.121 32.122 mp2_gpw_main 1 4.0 0.000 0.000 32.084 32.085 rpa_ri_compute_en 1 5.0 0.000 0.000 30.849 30.849 rpa_num_int 1 6.0 0.000 0.002 30.848 30.849 dbt_total 2336 9.6 0.011 0.012 27.303 27.313 compute_mat_P_omega 1 7.0 0.001 0.005 25.870 25.900 compute_mat_P_omega_contract 10 8.0 0.410 0.459 25.734 25.737 dbt_contract 787 11.0 0.025 0.028 20.678 20.685 dbt_tas_total 1149 12.2 0.052 0.070 18.555 18.556 dbt_tas_multiply 807 12.1 0.002 0.002 18.494 18.497 dbt_tas_dbm 807 14.1 0.003 0.004 13.441 13.469 dbm_multiply 807 16.1 10.219 11.084 10.219 11.084 compute_mat_P_omega_calc_M_occ 250 9.0 0.389 0.441 7.760 7.760 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.528 7.528 mp_sync 8706 11.6 5.302 6.799 5.302 6.799 dbt_tas_mm_2 251 15.0 0.001 0.002 6.166 6.184 dbt_copy 1111 10.7 0.011 0.012 5.632 6.081 dbt_reshape 1098 11.7 2.125 2.860 5.360 5.780 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.484 5.487 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.733 5.254 compute_QP_energies 1 7.0 0.000 0.000 3.220 3.221 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 3.218 3.220 mp_waitall_2 3776 15.3 2.717 2.894 2.717 2.894 dbt_communicate_buffer 1098 12.7 0.054 0.075 2.579 2.699 contract_cubic_gw 21 9.0 0.000 0.000 2.618 2.619 dbt_crop 1042 12.0 0.895 1.245 1.384 1.823 dbt_reserve_blocks_index 2849 13.1 0.065 0.081 1.532 1.784 dbt_reserve_blocks_index_array 2791 12.2 0.009 0.011 1.532 1.784 dbt_tas_reserve_blocks_index 3300 14.5 0.115 0.154 1.501 1.747 dbm_reserve_blocks 3696 15.4 1.477 1.711 1.477 1.711 dbt_tas_replicate 396 14.1 0.539 0.951 1.431 1.588 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 1.231 1.233 cp_gemm 105 8.4 0.000 0.000 1.037 1.047 cp_gemm_cosma 105 9.4 1.037 1.047 1.037 1.047 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.013 1.023 scf_env_do_scf 1 3.0 0.000 0.000 1.004 1.004 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 1.004 1.004 convert_to_new_pgrid 2421 14.1 0.025 0.036 0.820 0.962 dbm_copy 1608 15.1 0.789 0.934 0.789 0.934 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.925 0.927 mp_max_i 1992 9.8 0.671 0.879 0.671 0.879 compute_W_cubic_GW 10 7.0 0.001 0.002 0.802 0.807 dbm_add 807 14.1 0.653 0.728 0.653 0.728 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 0.682 0.682 dbt_tas_communicate_buffer 792 16.5 0.024 0.035 0.590 0.675 ------------------------------------------------------------------------------- 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=23.741, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=38.139, 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=8.456, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.431, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.03, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.441, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.944, 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=9.816000000000003, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.219, 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=0.389, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.41, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.477, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.789, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.125, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.302, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.717, 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 0.018 370.841 370.841 qs_forces 1 2.0 0.000 0.000 370.274 370.274 rebuild_ks_matrix 7 6.6 0.000 0.000 368.809 368.809 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 368.809 368.809 hfx_ks_matrix 7 8.6 0.000 0.000 366.777 366.777 dbt_total 4861 11.6 0.027 0.027 319.693 319.693 hfx_ri_update_ks 7 9.6 0.000 0.000 310.683 310.683 hfx_ri_update_ks_Pmat 7 10.6 31.706 31.706 310.678 310.678 dbt_tas_total 2391 14.1 1.222 1.222 292.086 292.086 qs_energies 1 3.0 0.000 0.000 272.597 272.597 scf_env_do_scf 1 4.0 0.000 0.000 272.318 272.318 dbt_contract 1473 13.0 0.174 0.174 271.529 271.529 qs_ks_update_qs_env 8 6.0 0.000 0.000 271.181 271.181 dbt_tas_multiply 1482 14.0 0.004 0.004 261.376 261.376 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.004 241.238 241.238 dbt_tas_dbm 1482 16.0 0.006 0.006 237.940 237.940 dbm_multiply 1482 18.0 237.923 237.923 237.923 237.923 dbt_tas_mm_2 649 17.1 0.004 0.004 211.758 211.758 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 172.894 172.894 init_scf_loop 2 5.0 0.000 0.000 99.421 99.421 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 97.631 97.631 hfx_ri_update_forces 1 7.0 0.000 0.000 56.091 56.091 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 40.958 40.958 dbt_tas_reshape 906 14.4 0.009 0.009 23.456 23.456 dbt_tas_mm_3T 659 17.1 0.002 0.002 18.864 18.864 dbt_copy 2331 12.4 0.211 0.211 17.414 17.414 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 16.019 16.019 dbt_tas_merge 649 14.1 13.162 13.162 14.574 14.574 dbt_tas_reshape_buffer_fill 906 15.4 13.842 13.842 13.842 13.842 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 13.088 13.088 precalc_derivatives 1 8.0 0.006 0.006 12.085 12.085 dbm_reserve_blocks 8303 16.8 10.480 10.480 10.480 10.480 dbt_tas_reserve_blocks_index 7397 16.0 0.352 0.352 10.080 10.080 dbt_reshape 856 13.9 5.705 5.705 9.912 9.912 dbt_crop 2763 14.2 6.830 6.830 9.858 9.858 dbt_reserve_blocks_index 4998 15.2 0.127 0.127 7.696 7.696 dbt_reserve_blocks_index_array 4963 14.3 0.018 0.018 7.628 7.628 reshape_mm_small 906 15.6 0.140 0.140 7.562 7.562 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-HFX_H2O-32_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.020 59.362 59.373 qs_forces 1 2.0 0.000 0.000 59.180 59.180 rebuild_ks_matrix 7 6.6 0.000 0.000 58.420 58.421 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.003 58.420 58.421 hfx_ks_matrix 7 8.6 0.000 0.001 57.374 57.384 dbt_total 4861 11.6 0.026 0.030 52.007 52.032 dbt_contract 1473 13.0 0.091 0.103 40.058 40.074 hfx_ri_update_ks 7 9.6 0.000 0.000 39.873 39.873 hfx_ri_update_ks_Pmat 7 10.6 1.411 1.880 39.872 39.872 dbt_tas_total 2391 14.1 0.112 0.141 37.905 37.906 qs_energies 1 3.0 0.000 0.001 36.534 36.534 scf_env_do_scf 1 4.0 0.000 0.001 36.352 36.352 qs_ks_update_qs_env 8 6.0 0.000 0.000 35.796 35.797 dbt_tas_multiply 1482 14.0 0.005 0.005 33.725 33.729 dbt_tas_dbm 1482 16.0 0.005 0.006 25.896 25.927 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.004 22.656 22.656 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 22.626 22.626 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 21.392 21.392 dbm_multiply 1482 18.0 17.001 21.321 17.001 21.321 hfx_ri_update_forces 1 7.0 0.000 0.000 17.500 17.510 dbt_tas_mm_2 649 17.1 0.003 0.004 16.100 16.125 mp_sync 17513 13.6 13.172 15.872 13.172 15.872 init_scf_loop 2 5.0 0.000 0.000 14.959 14.959 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 12.121 12.136 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 7.881 7.881 dbt_copy 2349 12.4 0.030 0.033 6.462 6.865 dbt_reshape 1256 13.5 2.101 2.520 4.475 4.733 dbt_crop 2763 14.2 2.950 3.778 3.640 4.537 dbt_tas_mm_3T 659 17.1 0.002 0.002 3.905 4.531 precalc_derivatives 1 8.0 0.001 0.002 4.151 4.151 dbt_tas_mm_3N 163 16.5 0.000 0.001 3.896 3.926 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.827 3.827 dbt_tas_merge 649 14.1 1.579 2.138 2.728 3.275 mp_waitall_2 5988 16.5 2.906 3.205 2.906 3.205 dbm_reserve_blocks 8337 16.9 2.133 2.444 2.133 2.444 dbt_tas_reserve_blocks_index 7428 16.1 0.256 0.322 2.053 2.405 mp_max_i 3372 12.5 1.973 2.354 1.973 2.354 dbt_tas_replicate 909 15.6 0.596 0.755 2.240 2.348 dbt_tas_communicate_buffer 1825 16.3 0.059 0.075 2.024 2.214 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.000 0.000 2.195 2.204 dbt_reserve_blocks_index 5398 15.2 0.119 0.138 1.732 1.993 dbt_reserve_blocks_index_array 5363 14.2 0.013 0.018 1.730 1.991 mp_alltoall_i 4339 15.3 1.785 1.967 1.785 1.967 build_3c_derivatives 9 9.0 0.229 0.317 1.883 1.884 dbt_tas_reshape 916 14.4 0.008 0.010 1.747 1.856 dbt_communicate_buffer 1256 14.5 0.043 0.058 1.536 1.656 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.001 0.002 1.460 1.464 mp_sum_l 38201 15.3 1.175 1.441 1.175 1.441 convert_to_new_pgrid 4446 16.0 0.037 0.045 1.230 1.377 dbm_copy 3043 16.9 1.193 1.342 1.193 1.342 ------------------------------------------------------------------------------- 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=56.898000000000025, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=237.923, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.706, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=13.842, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_merge", label="dbt_tas_merge", y=13.162, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=10.48, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_crop", label="dbt_crop", y=6.83, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", 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=18.21, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=17.001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.411, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_merge", label="dbt_tas_merge", y=1.579, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.133, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_crop", label="dbt_crop", y=2.95, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.906, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=13.172, 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 0.014 207.496 207.496 qs_energies 1 2.0 0.000 0.000 207.309 207.309 mp2_main 1 3.0 0.000 0.000 202.055 202.055 mp2_gpw_main 1 4.0 0.001 0.001 201.631 201.631 mp2_ri_gpw_compute_in 1 5.0 0.364 0.364 148.641 148.641 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 129.165 129.165 mp2_eri_3c_integrate_gpw 2656 7.0 0.014 0.014 100.755 100.755 integrate_v_rspace 2666 8.0 0.689 0.689 86.152 86.152 grid_integrate_task_list 2666 9.0 83.387 83.387 83.387 83.387 mp2_ri_gpw_compute_en 1 5.0 0.076 0.076 52.967 52.967 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.983 9.983 51.210 51.210 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.084 2.084 34.323 34.323 offload_gemm 2080 8.0 32.240 32.240 32.240 32.240 calculate_wavefunction 5312 9.0 16.979 16.979 24.701 24.701 dbcsr_multiply_generic 5322 8.0 0.174 0.174 22.003 22.003 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 21.982 21.982 get_2c_integrals 1 6.0 0.000 0.000 19.111 19.111 compute_2c_integrals 1 7.0 0.005 0.005 18.239 18.239 compute_2c_integrals_loop_lm 1 8.0 0.013 0.013 18.221 18.221 mp2_eri_2c_integrate_gpw 1 9.0 3.305 3.305 18.208 18.208 pw_transfer 63872 10.6 0.992 0.992 11.971 11.971 multiply_cannon 5322 9.0 0.443 0.443 11.464 11.464 fft_wrap_pw1pw2 53228 11.4 0.115 0.115 10.666 10.666 multiply_cannon_loop 5322 10.0 0.338 0.338 10.032 10.032 make_m2s 10644 9.0 0.065 0.065 8.407 8.407 multiply_cannon_multrec 5322 11.0 8.210 8.210 8.249 8.249 make_images 10644 10.0 3.368 3.368 8.101 8.101 fft_wrap_pw1pw2_20 21271 12.4 0.628 0.628 7.331 7.331 fft3d_s 53229 13.4 6.672 6.672 6.715 6.715 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.186 2.186 6.326 6.326 mp2_ri_gpw_compute_en_ener 2080 7.0 5.009 5.009 5.009 5.009 scf_env_do_scf 1 3.0 0.000 0.000 4.777 4.777 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.776 4.776 copy_dbcsr_to_fm 2679 8.0 0.027 0.027 4.653 4.653 ------------------------------------------------------------------------------- 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 0.022 42.732 42.743 qs_energies 1 2.0 0.000 0.000 42.651 42.651 mp2_main 1 3.0 0.000 0.001 40.003 40.004 mp2_gpw_main 1 4.0 0.001 0.002 39.882 39.882 mp2_ri_gpw_compute_in 1 5.0 0.042 0.043 18.748 24.583 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 16.953 22.791 mp2_ri_gpw_compute_en 1 5.0 0.073 0.085 21.055 21.534 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 14.874 20.723 integrate_v_rspace 93 8.1 0.103 0.126 14.832 20.565 grid_integrate_task_list 93 9.1 14.413 20.215 14.413 20.215 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.516 0.646 14.130 14.204 mp2_ri_gpw_compute_en_expansio 65 7.0 0.070 0.085 11.247 11.444 offload_gemm 65 8.0 11.177 11.376 11.177 11.376 mp_min_d 2 7.0 5.903 6.535 5.903 6.535 mp2_ri_get_integ_group_size 1 6.0 0.000 0.000 5.839 6.317 scf_env_do_scf 1 3.0 0.000 0.000 2.515 2.516 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 2.515 2.516 mp2_ri_gpw_compute_en_comm 17 7.0 0.082 0.150 2.059 2.478 mp_sendrecv_dm3 510 8.0 1.571 2.132 1.571 2.132 dbcsr_multiply_generic 176 8.0 0.008 0.008 1.787 1.937 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.769 1.917 get_2c_integrals 1 6.0 0.000 0.000 1.739 1.761 compute_2c_integrals 1 7.0 0.003 0.003 1.421 1.442 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 1.035 1.358 mp2_eri_2c_integrate_gpw 1 9.0 0.214 0.340 1.033 1.357 qs_scf_new_mos 10 5.0 0.000 0.000 1.263 1.339 eigensolver 11 5.8 0.001 0.001 1.207 1.209 calculate_wavefunction 166 9.0 0.518 0.730 0.899 1.154 multiply_cannon 176 9.0 0.014 0.016 1.073 1.135 multiply_cannon_loop 176 10.0 0.002 0.002 1.015 1.076 cp_fm_diag_elpa 11 6.8 0.000 0.000 1.003 1.011 cp_fm_redistribute_end 11 7.8 0.381 1.004 0.387 1.004 cp_fm_diag_elpa_base 11 7.8 0.595 0.959 0.607 0.974 multiply_cannon_multrec 246 11.0 0.878 0.918 0.883 0.924 pw_transfer 2120 10.5 0.041 0.052 0.817 0.903 ------------------------------------------------------------------------------- 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=56.697, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=83.387, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="offload_gemm", label="offload_gemm", y=32.24, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=16.979, 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=9.983, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.21, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_min_d", label="mp_min_d", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 Plot: name="RI-MP2_ammonia_timings_32mpi", title="Timings of RI-MP2_ammonia with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="rest", label="rest", y=7.756, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.413, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="offload_gemm", label="offload_gemm", y=11.177, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.518, 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=0.516, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.878, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_min_d", label="mp_min_d", y=5.903, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.571, 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 0.081 0.081 127.952 127.952 qs_energies 1 2.0 0.000 0.000 126.619 126.619 scf_env_do_scf 1 3.0 0.000 0.000 119.538 119.538 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 119.538 119.538 qs_ks_update_qs_env 15 5.0 0.000 0.000 50.238 50.238 rebuild_ks_matrix 15 6.0 0.000 0.000 50.028 50.028 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 50.028 50.028 qs_scf_new_mos 15 5.0 0.000 0.000 44.151 44.151 eigensolver 15 6.0 0.001 0.001 36.460 36.460 qs_vxc_create 15 8.0 0.046 0.046 34.148 34.148 calculate_dispersion_nonloc 15 9.0 7.216 7.216 29.798 29.798 cp_fm_diag_elpa 15 7.0 0.000 0.000 23.698 23.698 cp_fm_diag_elpa_base 15 8.0 21.065 21.065 23.697 23.697 pw_transfer 1191 10.0 0.053 0.053 22.493 22.493 qs_rho_update_rho_low 16 5.0 0.000 0.000 22.335 22.335 calculate_rho_elec 16 6.0 0.216 0.216 22.335 22.335 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 22.321 22.321 grid_collocate_task_list 16 7.0 21.051 21.051 21.051 21.051 fft_wrap_pw1pw2_150 765 12.0 3.249 3.249 16.418 16.418 sum_up_and_integrate 15 8.0 0.040 0.040 14.520 14.520 integrate_v_rspace 15 9.0 0.021 0.021 14.480 14.480 grid_integrate_task_list 15 10.0 13.971 13.971 13.971 13.971 cp_fm_cholesky_restore 45 7.0 10.526 10.526 10.526 10.526 fft3d_s 1087 13.0 10.226 10.226 10.233 10.233 pw_scatter_s 585 13.1 6.983 6.983 6.983 6.983 fft_wrap_pw1pw2_200 197 12.3 0.620 0.620 5.718 5.718 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.529 5.529 dbcsr_complete_redistribute 46 8.3 2.346 2.346 5.444 5.444 cp_fm_upper_to_full 30 8.0 4.867 4.867 4.867 4.867 vdW_energy 15 10.0 4.448 4.448 4.448 4.448 xc_vxc_pw_create 15 9.0 0.211 0.211 4.304 4.304 gspace_mixing 14 5.0 0.171 0.171 4.067 4.067 init_scf_run 1 3.0 0.000 0.000 3.538 3.538 broyden_mixing 14 6.0 3.471 3.471 3.471 3.471 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.089 3.089 xc_pw_derive 90 11.0 0.001 0.001 2.758 2.758 ------------------------------------------------------------------------------- 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 0.026 64.401 64.412 qs_energies 1 2.0 0.000 0.000 64.132 64.137 scf_env_do_scf 1 3.0 0.000 0.001 59.883 59.883 scf_env_do_scf_inner_loop 15 4.0 0.001 0.004 59.883 59.883 qs_ks_update_qs_env 15 5.0 0.000 0.000 25.698 25.721 rebuild_ks_matrix 15 6.0 0.000 0.000 25.665 25.688 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.004 25.664 25.688 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.541 21.545 calculate_rho_elec 16 6.0 0.007 0.013 21.540 21.545 grid_collocate_task_list 16 7.0 20.059 20.636 20.059 20.636 sum_up_and_integrate 15 8.0 0.006 0.009 14.882 14.930 integrate_v_rspace 15 9.0 0.001 0.001 14.876 14.926 grid_integrate_task_list 15 10.0 13.695 14.210 13.695 14.210 qs_scf_new_mos 15 5.0 0.000 0.000 13.400 13.494 eigensolver 15 6.0 0.001 0.002 12.431 12.461 qs_vxc_create 15 8.0 0.001 0.001 10.484 10.492 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.087 9.092 cp_fm_diag_elpa_base 15 8.0 8.934 8.970 9.085 9.090 calculate_dispersion_nonloc 15 9.0 0.982 1.823 8.630 8.658 pw_transfer 1191 10.0 0.078 0.095 8.036 8.132 fft_wrap_pw1pw2 1086 11.0 0.011 0.013 7.874 8.009 fft3d_ps 1086 13.0 2.451 2.889 6.240 6.583 fft_wrap_pw1pw2_150 765 12.0 0.255 0.290 5.354 5.453 mp_alltoall_z22v 1086 15.0 3.214 3.975 3.214 3.975 cp_fm_cholesky_restore 45 7.0 3.185 3.255 3.185 3.255 yz_to_x 501 13.9 0.222 0.332 2.459 2.830 qs_energies_init_hamiltonians 1 3.0 0.000 0.001 2.556 2.556 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.211 2.440 fft_wrap_pw1pw2_200 197 12.3 0.173 0.194 2.332 2.375 xc_vxc_pw_create 15 9.0 0.015 0.018 1.854 1.875 x_to_yz 585 14.1 0.328 0.359 1.305 1.613 rs_pw_transfer 158 9.4 0.001 0.002 1.290 1.543 density_rs2pw 16 7.0 0.001 0.001 1.337 1.516 init_scf_run 1 3.0 0.000 0.000 1.464 1.466 vdW_energy 15 10.0 1.347 1.457 1.347 1.457 build_core_ppnl 1 5.0 1.296 1.446 1.296 1.446 scf_env_initial_rho_setup 1 4.0 0.000 0.001 1.370 1.371 xc_pw_derive 90 11.0 0.001 0.002 1.253 1.323 ------------------------------------------------------------------------------- Plot: name="diag_cu144_broy_timings_32omp", title="Timings of diag_cu144_broy with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32omp", name="rest", label="rest", y=51.113, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=21.065, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.051, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.971, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.526, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.226, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", 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=15.313999999999993, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.934, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.059, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.695, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.185, 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="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.214, 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 0.078 301.626 301.626 qs_energies 1 2.0 0.000 0.000 301.450 301.450 ls_scf 1 3.0 0.000 0.000 300.205 300.205 ls_scf_main 1 4.0 0.002 0.002 290.840 290.840 density_matrix_trs4 11 5.0 0.012 0.012 196.253 196.253 arnoldi_extremal 12 6.1 0.000 0.000 110.009 110.009 arnoldi_normal_ev 12 7.1 0.014 0.014 110.008 110.008 dbcsr_matrix_vector_mult 652 9.0 0.174 0.174 108.169 108.169 build_subspace 23 8.1 0.076 0.076 107.967 107.967 dbcsr_matrix_vector_mult_local 652 10.0 106.777 106.777 106.787 106.787 ls_scf_dm_to_ks 11 5.0 0.000 0.000 89.386 89.386 matrix_ls_to_qs 11 6.0 0.000 0.000 86.184 86.184 dbcsr_multiply_generic 185 6.1 0.851 0.851 75.218 75.218 dbcsr_copy_into_existing 11 7.0 48.196 48.196 48.196 48.196 multiply_cannon 185 7.1 0.294 0.294 45.505 45.505 dbcsr_complete_redistribute 23 7.5 30.562 30.562 41.622 41.622 matrix_decluster 11 7.0 0.000 0.000 37.987 37.987 multiply_cannon_loop 185 8.1 0.233 0.233 33.215 33.215 make_m2s 370 7.1 0.037 0.037 25.218 25.218 make_images 370 8.1 10.570 10.570 23.527 23.527 multiply_cannon_multrec 185 9.1 23.301 23.301 23.390 23.390 dbcsr_finalize 646 7.5 0.158 0.158 14.637 14.637 dbcsr_merge_all 597 8.5 2.235 2.235 13.410 13.410 setup_rec_index_2d 370 8.1 11.909 11.909 11.909 11.909 dbcsr_sort_indices 1103 9.9 10.807 10.807 10.807 10.807 tree_to_linear_d 110 9.4 9.916 9.916 9.916 9.916 calculate_norms 370 9.1 9.593 9.593 9.593 9.593 quick_finalize 395 10.0 0.405 0.405 9.359 9.359 ls_scf_init_scf 1 4.0 0.000 0.000 8.670 8.670 dbcsr_special_finalize 370 9.1 0.002 0.002 8.657 8.657 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.336 8.336 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.681 7.681 ------------------------------------------------------------------------------- From /workspace/artifacts/bench_dftb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.009 0.022 67.986 67.997 qs_energies 1 2.0 0.000 0.000 67.890 67.890 ls_scf 1 3.0 0.000 0.000 67.831 67.831 ls_scf_main 1 4.0 0.001 0.008 65.330 65.331 density_matrix_trs4 11 5.0 0.006 0.019 62.593 62.675 dbcsr_multiply_generic 185 6.1 0.058 0.075 58.197 58.556 multiply_cannon 185 7.1 0.032 0.043 48.427 49.762 multiply_cannon_loop 185 8.1 0.109 0.132 46.008 47.043 multiply_cannon_multrec 1480 9.1 27.975 32.407 28.242 32.742 mp_waitall_1 11936 10.3 15.556 19.485 15.556 19.485 multiply_cannon_metrocomm3 1480 9.1 0.013 0.017 9.100 15.361 multiply_cannon_metrocomm1 1480 9.1 0.008 0.010 3.727 9.278 make_m2s 370 7.1 0.034 0.037 6.741 6.802 calculate_norms 2960 9.1 4.769 6.772 4.769 6.772 make_images 370 8.1 0.638 0.735 6.612 6.674 arnoldi_extremal 12 6.1 0.000 0.000 3.477 3.493 arnoldi_normal_ev 12 7.1 0.001 0.004 3.477 3.493 build_subspace 23 8.1 0.019 0.026 3.369 3.372 make_images_data 370 9.1 0.009 0.014 2.962 3.197 dbcsr_matrix_vector_mult 652 9.0 0.009 0.045 2.365 3.044 hybrid_alltoall_any 393 9.9 0.181 0.725 2.555 2.887 mp_sum_l 1119 5.6 2.081 2.884 2.081 2.884 dbcsr_matrix_vector_mult_local 652 10.0 1.777 2.745 1.778 2.747 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.386 2.452 dbcsr_complete_redistribute 23 7.5 1.210 1.616 1.956 2.126 matrix_ls_to_qs 11 6.0 0.000 0.000 1.899 2.082 make_images_pack 370 9.1 1.612 1.993 1.616 2.000 ls_scf_init_scf 1 4.0 0.000 0.000 1.906 1.907 matrix_decluster 11 7.0 0.000 0.000 1.757 1.906 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.879 1.885 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 1.721 1.722 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.160 1.671 buffer_matrices_ensure_size 370 8.1 1.295 1.508 1.295 1.508 mp_sum_d 1403 6.7 1.039 1.391 1.039 1.391 dbcsr_finalize 646 7.5 0.007 0.010 1.264 1.389 ------------------------------------------------------------------------------- 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=71.28799999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=106.777, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=48.196, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.562, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.301, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.909, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.593, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=14.618000000000002, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.777, 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=1.21, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=27.975, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="setup_rec_index_2d", label="setup_rec_index_2d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.769, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.081, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=15.556, 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 69.253 69.253 lib_test 1 2.0 0.000 0.000 69.245 69.245 dbcsr_run_tests 3 3.0 0.002 0.002 69.245 69.245 test_multiplies_multiproc 3 4.0 0.001 0.001 54.040 54.040 dbcsr_redistribute 9 5.0 34.905 34.905 36.408 36.408 dbcsr_multiply_generic 9 5.0 0.008 0.008 16.017 16.017 dbcsr_make_random_matrix 9 4.0 12.338 12.338 15.109 15.109 multiply_cannon 9 6.0 0.001 0.001 11.478 11.478 multiply_cannon_loop 9 7.0 0.029 0.029 11.105 11.105 multiply_cannon_multrec 9 8.0 11.076 11.076 11.076 11.076 dbcsr_finalize 27 5.7 0.037 0.037 5.258 5.258 dbcsr_merge_all 18 6.5 1.953 1.953 4.563 4.563 dbcsr_data_release 975 7.6 2.511 2.511 2.511 2.511 tree_to_linear_d 9 7.0 1.807 1.807 1.807 1.807 make_m2s 18 6.0 0.001 0.001 1.507 1.507 make_images 18 7.0 0.519 0.519 1.453 1.453 ------------------------------------------------------------------------------- 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 0.012 17.453 17.457 lib_test 1 2.0 0.000 0.000 17.419 17.435 dbcsr_run_tests 3 3.0 0.000 0.001 17.418 17.435 test_multiplies_multiproc 3 4.0 0.000 0.002 16.594 16.639 dbcsr_multiply_generic 9 5.0 0.001 0.001 14.789 14.884 multiply_cannon 9 6.0 0.001 0.002 13.160 13.462 multiply_cannon_loop 9 7.0 0.002 0.002 12.891 13.152 multiply_cannon_multrec 72 8.0 10.634 11.728 10.635 11.729 mp_waitall_1 576 9.2 2.555 3.289 2.555 3.289 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.925 2.763 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.324 1.132 dbcsr_make_random_matrix 9 4.0 0.668 0.926 0.793 1.014 mp_sum_l 390 2.5 0.446 0.899 0.446 0.899 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.440 0.894 make_m2s 18 6.0 0.001 0.001 0.642 0.684 make_images 18 7.0 0.021 0.026 0.638 0.681 dbcsr_data_release 444 7.6 0.598 0.672 0.598 0.672 dbcsr_finalize 27 5.7 0.000 0.000 0.553 0.610 dbcsr_destroy 111 5.9 0.000 0.000 0.501 0.588 dbcsr_checksum 6 5.0 0.153 0.546 0.546 0.546 dbcsr_merge_all 18 6.5 0.082 0.102 0.454 0.543 dbcsr_redistribute 9 5.0 0.224 0.275 0.393 0.428 mp_sum_d 191 1.2 0.394 0.413 0.394 0.413 make_images_data 18 8.0 0.000 0.001 0.336 0.401 hybrid_alltoall_any 18 9.0 0.026 0.100 0.295 0.363 ------------------------------------------------------------------------------- Plot: name="dbcsr_timings_32omp", title="Timings of dbcsr with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32omp", name="rest", label="rest", y=6.469999999999992, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=34.905, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.338, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.076, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.511, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.953, 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=2.2459999999999987, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.224, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.668, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.634, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.598, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.082, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.555, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.446, 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 0.047 0.047 129.144 129.144 qs_mol_dyn_low 1 2.0 0.003 0.003 127.811 127.811 velocity_verlet 5 3.0 0.003 0.003 104.122 104.122 qmmm_el_coupling 6 3.8 0.000 0.000 83.779 83.779 qmmm_elec_with_gaussian 6 4.8 0.089 0.089 83.761 83.761 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 83.057 83.057 qmmm_elec_gaussian_low_G 6 6.8 82.144 82.144 82.144 82.144 qs_forces 6 3.8 0.000 0.000 35.236 35.236 qs_energies 6 4.8 0.000 0.000 31.306 31.306 scf_env_do_scf 6 5.8 0.001 0.001 29.117 29.117 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 25.050 25.050 rebuild_ks_matrix 45 8.4 0.000 0.000 24.279 24.279 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.279 24.279 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.781 20.781 pw_transfer 966 12.3 0.047 0.047 16.474 16.474 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.271 16.271 fft_wrap_pw1pw2_150 507 15.2 2.020 2.020 15.835 15.835 qs_vxc_create 45 10.4 0.001 0.001 13.069 13.069 xc_vxc_pw_create 45 11.4 0.647 0.647 13.069 13.069 xc_pw_derive 270 13.4 0.002 0.002 9.045 9.045 fft3d_s 802 15.6 7.344 7.344 7.354 7.354 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.046 7.046 calculate_rho_elec 45 8.9 0.563 0.563 7.046 7.046 xc_rho_set_and_dset_create 45 12.4 0.656 0.656 6.959 6.959 pw_scatter_s 429 15.8 5.650 5.650 5.650 5.650 qmmm_forces 6 3.8 0.001 0.001 5.574 5.574 xc_pw_divergence 45 12.4 0.001 0.001 5.416 5.416 qmmm_forces_with_gaussian 6 4.8 0.108 0.108 5.249 5.249 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.412 4.412 pw_integral_ab 2539 7.4 4.339 4.339 4.339 4.339 qs_ks_ddapc 45 10.4 0.001 0.001 4.076 4.076 init_scf_loop 6 6.8 0.000 0.000 4.062 4.062 qmmm_forces_gaussian_low_G 6 6.8 3.688 3.688 3.688 3.688 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.504 3.504 grid_collocate_task_list 45 9.9 3.286 3.286 3.286 3.286 density_rs2pw 45 9.9 0.001 0.001 3.197 3.197 sum_up_and_integrate 45 10.4 0.116 0.116 3.047 3.047 pw_poisson_solve 51 9.9 1.306 1.306 3.034 3.034 integrate_v_rspace 45 11.4 0.006 0.006 2.931 2.931 fist_calc_energy_force 6 3.8 0.001 0.001 2.617 2.617 ------------------------------------------------------------------------------- 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 0.031 0.049 56.037 56.047 qs_mol_dyn_low 1 2.0 0.003 0.006 54.847 54.903 qs_forces 6 3.8 0.000 0.001 39.146 39.146 qs_energies 6 4.8 0.000 0.001 37.329 37.329 scf_env_do_scf 6 5.8 0.000 0.001 36.392 36.392 scf_env_do_scf_inner_loop 113 6.2 0.002 0.015 34.920 34.920 rebuild_ks_matrix 119 8.1 0.000 0.000 25.609 25.619 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.020 25.609 25.619 qs_ks_update_qs_env 119 7.3 0.001 0.001 24.076 24.084 velocity_verlet 5 3.0 0.002 0.003 23.330 23.333 pw_transfer 2446 12.3 0.164 0.188 16.278 16.750 fft_wrap_pw1pw2 2059 13.4 0.021 0.033 15.906 16.432 fft_wrap_pw1pw2_150 1321 14.9 1.103 1.302 15.158 15.656 fft3d_ps 2059 15.4 6.299 7.577 12.020 12.812 qs_vxc_create 119 10.1 0.002 0.002 12.764 12.772 xc_vxc_pw_create 119 11.1 0.142 0.217 12.762 12.770 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.612 10.614 calculate_rho_elec 119 8.3 0.049 0.055 10.611 10.614 xc_pw_derive 714 13.1 0.009 0.012 9.540 9.819 sum_up_and_integrate 119 10.1 0.049 0.063 9.513 9.597 integrate_v_rspace 119 11.1 0.003 0.004 9.464 9.559 qmmm_forces 6 3.8 0.002 0.002 7.852 7.853 qmmm_forces_with_gaussian 6 4.8 0.338 0.390 7.188 7.764 rs_pw_transfer 988 11.5 0.010 0.016 7.058 7.267 qmmm_el_coupling 6 3.8 0.000 0.000 6.788 6.976 qmmm_elec_with_gaussian 6 4.8 0.313 0.352 6.786 6.975 xc_rho_set_and_dset_create 119 12.1 0.341 0.580 6.202 6.914 xc_pw_divergence 119 12.1 0.004 0.006 6.154 6.405 density_rs2pw 119 9.3 0.005 0.008 6.106 6.292 mp_alltoall_z22v 2059 17.4 4.423 5.994 4.423 5.994 potential_pw2rs 119 12.1 0.005 0.008 5.478 5.497 grid_collocate_task_list 119 9.3 4.297 4.568 4.297 4.568 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.839 4.106 grid_integrate_task_list 119 12.1 3.383 4.002 3.383 4.002 x_to_yz 1095 16.8 0.760 0.873 3.053 3.743 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.333 3.595 qmmm_forces_gaussian_low_G 6 6.8 3.160 3.427 3.160 3.427 yz_to_x 964 16.0 0.486 0.665 2.616 3.406 mp_waitany 4028 12.8 2.533 3.206 2.533 3.206 qmmm_elec_gaussian_low_G 6 6.8 2.742 2.998 2.742 2.998 rs_pw_transfer_PW2RS_150 125 13.9 1.134 1.397 2.765 2.876 pw_restrict_s3 18 5.8 1.329 1.627 2.391 2.701 rs_pw_transfer_RS2PW_150 125 11.2 0.903 1.122 2.294 2.519 dbcsr_multiply_generic 2588 12.3 0.056 0.069 1.892 2.246 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 1.944 2.208 pw_prolongate_s3 18 6.8 1.098 1.335 1.944 2.208 qs_scf_new_mos 113 7.2 0.000 0.000 2.031 2.037 qs_scf_loop_do_ot 113 8.2 0.000 0.000 2.031 2.037 mp_waitall_1 188862 16.2 1.760 2.031 1.760 2.031 ot_scf_mini 113 9.2 0.001 0.001 1.948 1.955 qs_ks_ddapc 119 10.1 0.002 0.002 1.770 1.881 mp_sum_dm3 33 5.7 1.723 1.863 1.723 1.863 pw_gather_p 964 15.0 1.192 1.660 1.192 1.660 pw_scatter_p 1095 15.8 1.544 1.592 1.544 1.592 mp_sum_d 5820 12.2 1.024 1.577 1.024 1.577 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.544 1.544 pw_integral_ab 2761 7.7 1.031 1.203 1.370 1.518 init_scf_loop 6 6.8 0.000 0.000 1.470 1.470 ot_mini 113 10.2 0.001 0.001 1.188 1.194 rs_pw_transfer_PW2RS_40 119 14.1 0.201 0.247 0.922 1.138 ------------------------------------------------------------------------------- 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=22.692999999999998, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=82.144, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.344, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.65, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.339, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.688, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.286, 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=30.701999999999998, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.742, 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=1.031, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.16, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.297, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.423, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.383, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.299, yerr=0.0 Summary: Performance test took 37 minutes. Status: OK Removing intermediate container a8b2330c38fa ---> 7278c2a210c1 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 4a9ac949856f Removing intermediate container 4a9ac949856f ---> 7ead9ebace29 Step 42/42 : ENTRYPOINT [] ---> Running in a1519117065b Removing intermediate container a1519117065b ---> bef38c2a31a2 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built bef38c2a31a2 Successfully tagged gcr.io/cp2k-org-project/img_cp2k-perf-openmp-arch-14b:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2022-08-13 19:54:27+00:00