StartDate: 2022-09-19 13:01:35+00:00 CpuId: 32x AMD (unknown model) [Zen 3], 7nm (SMT disabled) CommitSHA: 1ca6ba60d82da4ac98000992af78872ea73c2579 CommitTime: 2022-09-19 14:08:23 +0200 CommitAuthor: Dr. Mathieu Taillefumier CommitSubject: Add extra check for mutually exclude giving U (or J) and U_MINUS_J parameters Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=1ca6ba60d82da4ac98000992af78872ea73c2579 Sending build context to Docker daemon 364.4MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 2b55860d4c66: Already exists Digest: sha256:20fa2d7bb4de7723f542be5923b06c4d704370f0390e4ae9e1c833c8785644c1 Status: Downloaded newer image for ubuntu:22.04 ---> 2dc39ba059dc Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> bf0c853ea628 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 3f014c28f167 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 9e0fed4f46ea Step 5/42 : RUN mkdir scripts ---> Using cache ---> 51c38e746560 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 ---> 2dae48987405 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 0866f6db4185 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --mpi-mode=mpich --with-gcc=system --dry-run ---> Using cache ---> 31d8b226d31b Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 97d8aeb6f496 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 8aeabfd5037c Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 8618a3774453 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> b40da73828df Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 3865622e9bc2 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> b1774297145c Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> cc84a0fe72f2 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 741c87e87f58 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 369a45c1f56c Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 0e78fcf622f2 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 9342e2d1cb90 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 67e222b85720 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> ae8c57f75292 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> db4936363db4 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 1635680b38d0 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 28389d5adb2a Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> bb05014f324b Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 0ce76b45eb1c Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 2a73940fa03a Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 8d32cb99ac9e Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 7ec8fb186fb8 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 9be33207ce99 Step 31/42 : COPY ./src ./src ---> b79630a98436 Step 32/42 : COPY ./exts ./exts ---> ccdd0734f17f Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> 7a141fa3a176 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 8c39e7aec9db './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 8c39e7aec9db ---> 26cdd89b0135 Step 35/42 : COPY ./data ./data ---> 0d7cf5ad16b9 Step 36/42 : COPY ./tests ./tests ---> c0c6512e550a Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> de9d47e9e70e Step 38/42 : COPY ./benchmarks ./benchmarks ---> b2ba4088c5e0 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> e0b0f8e517c5 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 1d41068727d3 ========== 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 0.043 0.043 86.128 86.128 qs_mol_dyn_low 1 2.0 0.003 0.003 85.524 85.524 qs_forces 11 3.9 0.001 0.001 85.482 85.482 qs_energies 11 4.9 0.001 0.001 79.522 79.522 scf_env_do_scf 11 5.9 0.001 0.001 69.099 69.099 velocity_verlet 10 3.0 0.002 0.002 55.388 55.388 scf_env_do_scf_inner_loop 108 6.5 0.010 0.010 53.212 53.212 rebuild_ks_matrix 119 8.3 0.001 0.001 20.049 20.049 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.049 20.049 dbcsr_multiply_generic 2286 12.5 0.158 0.158 19.381 19.381 qs_scf_new_mos 108 7.5 0.001 0.001 19.291 19.291 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.290 19.290 qs_rho_update_rho_low 119 7.7 0.000 0.000 19.287 19.287 calculate_rho_elec 119 8.7 0.956 0.956 19.286 19.286 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.343 18.343 ot_scf_mini 108 9.5 0.002 0.002 17.991 17.991 init_scf_loop 11 6.9 0.000 0.000 15.762 15.762 grid_collocate_task_list 119 9.7 15.021 15.021 15.021 15.021 prepare_preconditioner 11 7.9 0.000 0.000 13.384 13.384 make_preconditioner 11 8.9 0.000 0.000 13.384 13.384 sum_up_and_integrate 119 10.3 0.183 0.183 12.347 12.347 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.264 12.264 integrate_v_rspace 119 11.3 0.089 0.089 12.164 12.164 ot_mini 108 10.5 0.001 0.001 11.755 11.755 make_m2s 4572 13.5 0.046 0.046 10.903 10.903 grid_integrate_task_list 119 12.3 10.270 10.270 10.270 10.270 qs_ot_get_derivative 108 11.5 0.001 0.001 6.126 6.126 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.064 6.064 pw_transfer 1439 11.6 0.063 0.063 5.905 5.905 dbcsr_make_dense_low 5837 15.5 0.066 0.066 5.802 5.802 make_dense_data 5837 16.5 5.133 5.133 5.721 5.721 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.669 5.669 ot_diis_step 108 11.5 0.004 0.004 5.625 5.625 make_images 4572 14.5 2.101 2.101 5.420 5.420 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.144 5.144 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.098 5.098 apply_single 119 13.6 0.000 0.000 5.098 5.098 fft_wrap_pw1pw2_140 487 13.2 0.484 0.484 4.871 4.871 multiply_cannon 2286 13.5 0.170 0.170 4.443 4.443 cp_fm_cholesky_decompose 22 10.9 4.212 4.212 4.212 4.212 multiply_cannon_loop 2286 14.5 0.049 0.049 3.989 3.989 multiply_cannon_multrec 2286 15.5 3.896 3.896 3.940 3.940 cp_fm_cholesky_invert 11 10.9 3.926 3.926 3.926 3.926 init_scf_run 11 5.9 0.002 0.002 3.793 3.793 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.792 3.792 dbcsr_complete_redistribute 329 12.2 1.896 1.896 3.599 3.599 dbcsr_copy 2102 12.0 0.192 0.192 3.456 3.456 wfi_extrapolate 11 7.9 0.001 0.001 3.315 3.315 density_rs2pw 119 9.7 0.003 0.003 3.309 3.309 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.307 3.307 dbcsr_copy_into_existing 22 7.9 3.234 3.234 3.234 3.234 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.227 3.227 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.954 2.954 qs_create_task_list 11 7.9 0.000 0.000 2.867 2.867 generate_qs_task_list 11 8.9 1.955 1.955 2.867 2.867 qs_ot_get_p 119 10.4 0.001 0.001 2.828 2.828 fft3d_s 1202 14.6 2.822 2.822 2.826 2.826 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.652 2.652 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.428 2.428 pw_poisson_solve 119 10.3 0.908 0.908 2.393 2.393 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.281 2.281 dbcsr_data_release 279534 16.0 2.216 2.216 2.216 2.216 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.942 1.942 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.926 1.926 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.845 1.845 potential_pw2rs 119 12.3 0.043 0.043 1.804 1.804 cp_fm_upper_to_full 72 14.2 1.786 1.786 1.786 1.786 ------------------------------------------------------------------------------- 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 0.015 0.029 47.489 47.498 qs_mol_dyn_low 1 2.0 0.003 0.004 47.369 47.373 qs_forces 11 3.9 0.001 0.001 47.329 47.330 qs_energies 11 4.9 0.001 0.001 44.050 44.053 scf_env_do_scf 11 5.9 0.000 0.002 40.440 40.440 scf_env_do_scf_inner_loop 108 6.5 0.002 0.017 37.353 37.353 velocity_verlet 10 3.0 0.001 0.003 28.324 28.325 rebuild_ks_matrix 119 8.3 0.000 0.001 18.306 18.416 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.023 18.306 18.415 qs_ks_update_qs_env 119 7.6 0.001 0.001 16.330 16.434 dbcsr_multiply_generic 2286 12.5 0.069 0.089 12.670 15.072 sum_up_and_integrate 119 10.3 0.019 0.022 13.995 14.125 integrate_v_rspace 119 11.3 0.004 0.005 13.976 14.107 qs_rho_update_rho_low 119 7.7 0.001 0.001 14.017 14.023 calculate_rho_elec 119 8.7 0.030 0.031 14.017 14.022 grid_collocate_task_list 119 9.7 9.006 10.935 9.006 10.935 grid_integrate_task_list 119 12.3 8.069 10.717 8.069 10.717 qs_scf_new_mos 108 7.5 0.001 0.001 9.953 10.064 qs_scf_loop_do_ot 108 8.5 0.001 0.001 9.953 10.064 multiply_cannon 2286 13.5 0.145 0.198 9.287 9.861 ot_scf_mini 108 9.5 0.002 0.003 9.343 9.451 multiply_cannon_loop 2286 14.5 0.094 0.121 8.768 9.213 mp_waitall_1 169478 16.3 7.694 8.197 7.694 8.197 rs_pw_transfer 974 11.9 0.011 0.014 5.641 6.073 multiply_cannon_metrocomm3 18288 15.5 0.038 0.049 5.096 5.753 ot_mini 108 10.5 0.001 0.001 5.417 5.535 density_rs2pw 119 9.7 0.005 0.006 4.694 5.111 pw_transfer 1439 11.6 0.104 0.121 3.294 3.363 mp_alltoall_d11v 2130 13.8 2.858 3.280 2.858 3.280 potential_pw2rs 119 12.3 0.006 0.007 3.233 3.238 fft_wrap_pw1pw2 1201 12.6 0.009 0.012 3.124 3.194 multiply_cannon_multrec 18288 15.5 2.875 3.142 2.885 3.159 rs_gather_matrices 119 12.3 0.075 0.085 2.637 3.076 init_scf_loop 11 6.9 0.000 0.000 3.074 3.074 mp_waitany 9880 13.7 2.533 3.010 2.533 3.010 mp_sum_l 11218 13.2 0.689 3.007 0.689 3.007 qs_ot_get_derivative 108 11.5 0.001 0.001 2.768 2.874 fft_wrap_pw1pw2_140 487 13.2 0.278 0.329 2.707 2.828 rs_pw_transfer_RS2PW_140 130 11.5 0.300 0.341 2.378 2.807 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.560 2.648 apply_single 119 13.6 0.000 0.001 2.560 2.648 ot_diis_step 108 11.5 0.003 0.004 2.628 2.628 init_scf_run 11 5.9 0.000 0.004 2.460 2.460 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.459 2.460 make_m2s 4572 13.5 0.045 0.056 2.262 2.315 fft3d_ps 1201 14.6 1.234 1.313 2.227 2.287 wfi_extrapolate 11 7.9 0.001 0.001 2.230 2.230 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.108 2.122 make_images 4572 14.5 0.115 0.136 1.943 1.997 rs_pw_transfer_PW2RS_140 130 13.9 0.615 0.666 1.379 1.407 qs_ot_get_p 119 10.4 0.001 0.001 1.218 1.367 make_images_data 4572 15.5 0.035 0.045 1.052 1.142 mp_sum_d 4129 12.0 0.860 1.138 0.860 1.138 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.862 1.137 prepare_preconditioner 11 7.9 0.000 0.000 1.102 1.129 make_preconditioner 11 8.9 0.000 0.000 1.102 1.129 multiply_cannon_metrocomm1 18288 15.5 0.018 0.026 0.496 1.064 hybrid_alltoall_any 4725 16.4 0.062 0.187 0.946 1.051 make_full_inverse_cholesky 11 9.9 0.000 0.000 0.995 1.014 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 0.976 0.976 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.891 0.954 ------------------------------------------------------------------------------- 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=43.67, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.021, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.27, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.133, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.212, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=3.926, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.896, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=16.986999999999995, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.006, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.069, 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="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.875, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=2.858, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.694, 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 0.036 0.036 109.573 109.573 qs_mol_dyn_low 1 2.0 0.003 0.003 108.929 108.929 qs_forces 11 3.9 0.001 0.001 108.890 108.890 qs_energies 11 4.9 0.001 0.001 101.220 101.220 scf_env_do_scf 11 5.9 0.001 0.001 88.826 88.826 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 71.191 71.191 velocity_verlet 10 3.0 0.002 0.002 70.279 70.279 rebuild_ks_matrix 107 8.3 0.001 0.001 33.174 33.174 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.174 33.174 qs_rho_update_rho_low 107 7.7 0.000 0.000 31.376 31.376 calculate_rho_elec 107 8.7 0.855 0.855 31.375 31.375 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.752 29.752 grid_collocate_task_list 107 9.7 27.421 27.421 27.421 27.421 sum_up_and_integrate 107 10.3 0.165 0.165 26.269 26.269 integrate_v_rspace 107 11.3 0.080 0.080 26.104 26.104 grid_integrate_task_list 107 12.3 24.358 24.358 24.358 24.358 init_scf_loop 11 6.9 0.000 0.000 17.493 17.493 dbcsr_multiply_generic 1966 12.4 0.140 0.140 16.927 16.927 qs_scf_new_mos 96 7.5 0.001 0.001 16.771 16.771 qs_scf_loop_do_ot 96 8.5 0.001 0.001 16.771 16.771 ot_scf_mini 96 9.5 0.002 0.002 15.656 15.656 prepare_preconditioner 11 7.9 0.000 0.000 13.509 13.509 make_preconditioner 11 8.9 0.000 0.000 13.509 13.509 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.384 12.384 ot_mini 96 10.5 0.001 0.001 10.298 10.298 make_m2s 3932 13.4 0.040 0.040 9.601 9.601 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.545 6.545 pw_transfer 1295 11.6 0.056 0.056 5.512 5.512 qs_ot_get_derivative 96 11.5 0.001 0.001 5.333 5.333 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.300 5.300 init_scf_run 11 5.9 0.002 0.002 5.223 5.223 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.221 5.221 dbcsr_make_dense_low 4961 15.5 0.104 0.104 5.171 5.171 make_dense_data 4961 16.5 4.473 4.473 5.054 5.054 ot_diis_step 96 11.5 0.003 0.003 4.962 4.962 make_images 3932 14.4 1.857 1.857 4.699 4.699 wfi_extrapolate 11 7.9 0.001 0.001 4.614 4.614 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.612 4.612 apply_single 107 13.6 0.000 0.000 4.612 4.612 fft_wrap_pw1pw2_140 439 13.2 0.445 0.445 4.586 4.586 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.524 4.524 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.281 4.281 cp_fm_cholesky_decompose 22 10.9 4.217 4.217 4.217 4.217 multiply_cannon 1966 13.4 0.182 0.182 4.010 4.010 cp_fm_cholesky_invert 11 10.9 3.955 3.955 3.955 3.955 dbcsr_complete_redistribute 317 12.2 1.913 1.913 3.774 3.774 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.656 3.656 multiply_cannon_loop 1966 14.4 0.035 0.035 3.571 3.571 multiply_cannon_multrec 1966 15.4 3.495 3.495 3.534 3.534 dbcsr_copy 1855 11.9 0.173 0.173 3.399 3.399 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.387 3.387 qs_create_task_list 11 7.9 0.000 0.000 3.285 3.285 generate_qs_task_list 11 8.9 2.397 2.397 3.285 3.285 dbcsr_copy_into_existing 22 7.9 3.197 3.197 3.197 3.197 density_rs2pw 107 9.7 0.003 0.003 3.099 3.099 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.017 3.017 fft3d_s 1082 14.6 2.631 2.631 2.635 2.635 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.467 2.467 qs_ot_get_p 107 10.4 0.001 0.001 2.466 2.466 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.360 2.360 ------------------------------------------------------------------------------- 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 82.888 82.899 qs_mol_dyn_low 1 2.0 0.003 0.005 82.693 82.705 qs_forces 11 3.9 0.001 0.001 82.642 82.642 qs_energies 11 4.9 0.001 0.001 77.075 77.078 scf_env_do_scf 11 5.9 0.000 0.002 71.490 71.490 scf_env_do_scf_inner_loop 96 6.5 0.002 0.020 66.303 66.303 velocity_verlet 10 3.0 0.002 0.003 49.091 49.092 rebuild_ks_matrix 107 8.3 0.000 0.001 36.794 36.928 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.018 36.794 36.927 sum_up_and_integrate 107 10.3 0.019 0.021 32.044 32.866 integrate_v_rspace 107 11.3 0.004 0.005 32.025 32.849 qs_ks_update_qs_env 107 7.6 0.001 0.001 32.520 32.641 qs_rho_update_rho_low 107 7.7 0.000 0.001 31.459 31.476 calculate_rho_elec 107 8.7 0.027 0.031 31.458 31.476 grid_integrate_task_list 107 12.3 22.857 29.599 22.857 29.599 grid_collocate_task_list 107 9.7 21.985 28.460 21.985 28.460 dbcsr_multiply_generic 1966 12.4 0.062 0.074 12.534 18.306 rs_pw_transfer 878 11.9 0.010 0.012 10.126 10.978 density_rs2pw 107 9.7 0.005 0.006 9.167 10.028 qs_scf_new_mos 96 7.5 0.001 0.001 9.236 9.393 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.236 9.393 multiply_cannon 1966 13.4 0.124 0.147 8.665 9.325 multiply_cannon_loop 1966 14.4 0.090 0.104 8.191 8.878 ot_scf_mini 96 9.5 0.002 0.002 8.683 8.838 mp_waitany 8968 13.7 7.194 8.074 7.194 8.074 rs_pw_transfer_RS2PW_140 118 11.5 0.268 0.316 7.012 7.859 mp_waitall_1 146670 16.2 7.126 7.846 7.126 7.846 mp_alltoall_d11v 1998 13.7 6.257 7.839 6.257 7.839 rs_gather_matrices 107 12.3 0.066 0.084 6.028 7.588 mp_sum_l 9666 13.1 1.496 7.137 1.496 7.137 multiply_cannon_metrocomm3 15728 15.4 0.036 0.043 4.753 5.702 ot_mini 96 10.5 0.001 0.001 5.056 5.233 init_scf_loop 11 6.9 0.000 0.000 5.174 5.174 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.391 4.404 init_scf_run 11 5.9 0.000 0.005 4.392 4.392 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.392 4.392 wfi_extrapolate 11 7.9 0.001 0.001 3.993 3.993 pw_transfer 1295 11.6 0.094 0.108 3.152 3.205 potential_pw2rs 107 12.3 0.006 0.007 3.104 3.115 fft_wrap_pw1pw2 1081 12.6 0.009 0.010 2.999 3.057 multiply_cannon_multrec 15728 15.4 2.694 2.884 2.704 2.896 qs_ot_get_derivative 96 11.5 0.001 0.001 2.612 2.768 fft_wrap_pw1pw2_140 439 13.2 0.247 0.282 2.588 2.663 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.357 2.531 apply_single 107 13.6 0.000 0.000 2.357 2.531 ot_diis_step 96 11.5 0.003 0.004 2.424 2.425 fft3d_ps 1081 14.6 1.134 1.194 2.177 2.233 make_m2s 3932 13.4 0.040 0.054 2.034 2.080 make_images 3932 14.4 0.104 0.126 1.743 1.793 ------------------------------------------------------------------------------- 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=45.149, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.421, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.358, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.473, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.217, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=3.955, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", 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=17.46900000000001, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.985, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.857, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=7.194, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.126, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=6.257, 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 0.189 0.189 109.142 109.142 qs_energies 1 2.0 0.000 0.000 108.314 108.314 scf_env_do_scf 1 3.0 0.000 0.000 107.180 107.180 qs_ks_update_qs_env 8 5.0 0.000 0.000 102.390 102.390 rebuild_ks_matrix 7 6.0 0.000 0.000 102.336 102.336 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 102.336 102.336 hfx_ks_matrix 7 8.0 0.000 0.000 92.917 92.917 integrate_four_center 7 9.0 1.543 1.543 92.888 92.888 integrate_four_center_main 7 10.0 0.666 0.666 81.215 81.215 integrate_four_center_bin 456 11.0 80.549 80.549 80.549 80.549 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.975 56.975 init_scf_loop 1 4.0 0.000 0.000 50.196 50.196 integrate_four_center_load 7 10.0 0.000 0.000 9.889 9.889 hfx_load_balance 1 11.0 0.030 0.030 9.888 9.888 hfx_load_balance_bin 1 12.0 5.535 5.535 5.535 5.535 hfx_load_balance_count 1 12.0 4.307 4.307 4.307 4.307 qs_vxc_create 14 8.0 0.000 0.000 3.712 3.712 xc_vxc_pw_create 14 9.0 0.117 0.117 3.712 3.712 xc_rho_set_and_dset_create 14 10.0 0.095 0.095 2.996 2.996 calculate_rho_elec 15 7.4 0.118 0.118 2.431 2.431 xc_functional_eval 35 11.0 0.000 0.000 2.344 2.344 prepare_preconditioner 1 5.0 0.000 0.000 2.274 2.274 make_preconditioner 1 6.0 0.000 0.000 2.274 2.274 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.196 2.196 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-hyb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.227 0.250 133.737 133.748 qs_energies 1 2.0 0.000 0.000 133.374 133.381 scf_env_do_scf 1 3.0 0.000 0.000 133.002 133.003 qs_ks_update_qs_env 8 5.0 0.000 0.000 130.916 130.916 rebuild_ks_matrix 7 6.0 0.000 0.000 130.908 130.909 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 130.908 130.909 hfx_ks_matrix 7 8.0 0.000 0.000 124.780 124.782 integrate_four_center 7 9.0 0.062 0.569 124.771 124.772 integrate_four_center_main 7 10.0 0.003 0.003 79.320 112.384 integrate_four_center_bin 448 11.0 79.317 112.381 79.317 112.381 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 75.547 75.547 init_scf_loop 1 4.0 0.000 0.000 57.454 57.454 mp_sync 70 11.3 33.079 35.448 33.079 35.448 integrate_four_center_load 7 10.0 0.000 0.000 11.466 11.470 hfx_load_balance 1 11.0 0.001 0.001 11.466 11.470 mp_sum_l 1135 8.3 5.786 6.121 5.786 6.121 hfx_load_balance_dist 1 12.0 0.000 0.000 5.662 5.932 hfx_load_balance_bin 1 12.0 2.864 5.708 2.864 5.708 hfx_load_balance_count 1 12.0 2.865 5.683 2.865 5.683 qs_vxc_create 14 8.0 0.000 0.000 2.938 2.938 xc_vxc_pw_create 14 9.0 0.008 0.009 2.937 2.937 ------------------------------------------------------------------------------- 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=16.541999999999987, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.549, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.535, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=4.307, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.543, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.666, 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=9.760999999999996, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=79.317, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.864, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.865, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.062, 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=33.079, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=5.786, 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 84.814 84.814 qs_energies 1 2.0 0.000 0.000 84.444 84.444 mp2_main 1 3.0 0.000 0.000 81.675 81.675 mp2_gpw_main 1 4.0 0.000 0.000 81.573 81.573 rpa_ri_compute_en 1 5.0 0.000 0.000 78.308 78.308 rpa_num_int 1 6.0 0.001 0.001 78.302 78.302 compute_mat_P_omega 1 7.0 0.003 0.003 68.260 68.260 compute_mat_P_omega_contract 10 8.0 8.860 8.860 68.066 68.066 dbt_total 2336 9.6 0.011 0.011 54.446 54.446 dbt_contract 787 11.0 0.033 0.033 47.723 47.723 dbt_tas_total 1149 12.2 0.253 0.253 46.723 46.723 dbt_tas_multiply 807 12.1 0.002 0.002 45.332 45.332 dbt_tas_dbm 807 14.1 0.003 0.003 38.721 38.721 dbm_multiply 807 16.1 38.711 38.711 38.711 38.711 dbt_tas_mm_1N 524 15.1 0.001 0.001 30.854 30.854 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 29.759 29.759 compute_mat_P_omega_calc_M_occ 250 9.0 8.883 8.883 16.732 16.732 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.290 7.290 dbt_tas_mm_2 251 15.0 0.001 0.001 6.322 6.322 dbt_copy 1103 10.7 0.052 0.052 5.316 5.316 compute_QP_energies 1 7.0 0.000 0.000 5.163 5.163 compute_self_energy_cubic_gw 1 8.0 0.053 0.053 5.163 5.163 contract_cubic_gw 21 9.0 0.000 0.000 4.141 4.141 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 3.256 3.256 dbt_tas_reserve_blocks_index 3261 14.3 0.145 0.145 3.171 3.171 dbm_reserve_blocks 3628 15.3 3.091 3.091 3.091 3.091 scf_env_do_scf 1 3.0 0.000 0.000 2.657 2.657 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.657 2.657 dbt_reserve_blocks_index 2280 13.1 0.048 0.048 2.400 2.400 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.391 2.391 convert_to_new_pgrid 2421 14.1 0.097 0.097 2.294 2.294 dbt_crop 1042 12.0 1.535 1.535 2.288 2.288 dbm_copy 1614 15.1 2.196 2.196 2.196 2.196 dbt_tas_copy 574 11.4 1.352 1.352 2.166 2.166 dbt_tas_reshape 367 15.0 0.006 0.006 2.126 2.126 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.051 2.051 compute_W_cubic_GW 10 7.0 0.012 0.012 1.980 1.980 dbt_reshape 278 11.9 0.944 0.944 1.764 1.764 get_2c_integrals 1 6.0 0.000 0.000 1.752 1.752 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.025 31.041 31.056 qs_energies 1 2.0 0.000 0.000 30.864 30.865 mp2_main 1 3.0 0.000 0.000 29.861 29.862 mp2_gpw_main 1 4.0 0.000 0.000 29.825 29.826 rpa_ri_compute_en 1 5.0 0.000 0.000 28.620 28.621 rpa_num_int 1 6.0 0.000 0.002 28.620 28.621 dbt_total 2336 9.6 0.010 0.012 25.404 25.407 compute_mat_P_omega 1 7.0 0.001 0.005 24.199 24.201 compute_mat_P_omega_contract 10 8.0 0.404 0.429 24.054 24.057 dbt_contract 787 11.0 0.024 0.028 19.151 19.157 dbt_tas_total 1149 12.2 0.051 0.068 17.166 17.166 dbt_tas_multiply 807 12.1 0.002 0.002 17.102 17.103 dbt_tas_dbm 807 14.1 0.003 0.003 12.675 12.681 dbm_multiply 807 16.1 9.837 10.859 9.837 10.859 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.268 7.268 compute_mat_P_omega_calc_M_occ 250 9.0 0.390 0.418 7.058 7.058 dbt_tas_mm_2 251 15.0 0.001 0.001 6.018 6.021 dbt_copy 1111 10.7 0.011 0.012 5.496 5.942 mp_sync 8706 11.6 4.498 5.802 4.498 5.802 dbt_reshape 1098 11.7 2.080 2.707 5.228 5.636 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.081 5.082 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.477 4.966 compute_QP_energies 1 7.0 0.000 0.000 2.872 2.872 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 2.869 2.871 mp_waitall_2 3776 15.3 2.460 2.671 2.460 2.671 dbt_communicate_buffer 1098 12.7 0.053 0.080 2.499 2.634 contract_cubic_gw 21 9.0 0.000 0.000 2.252 2.252 dbt_crop 1042 12.0 0.909 1.255 1.397 1.806 dbt_reserve_blocks_index_array 2791 12.2 0.009 0.011 1.527 1.741 dbt_reserve_blocks_index 2849 13.1 0.061 0.074 1.526 1.741 dbt_tas_reserve_blocks_index 3300 14.5 0.114 0.152 1.499 1.705 dbm_reserve_blocks 3696 15.4 1.476 1.657 1.476 1.657 dbt_tas_replicate 396 14.1 0.534 0.692 1.082 1.214 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.200 1.203 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.971 0.973 parallel_gemm_fm 105 8.4 0.000 0.000 0.905 0.914 parallel_gemm_fm_cosma 105 9.4 0.905 0.914 0.905 0.914 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.905 0.907 scf_env_do_scf 1 3.0 0.000 0.000 0.901 0.901 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.901 0.901 convert_to_new_pgrid 2421 14.1 0.024 0.030 0.791 0.867 dbm_copy 1608 15.1 0.761 0.840 0.761 0.840 mp_max_i 1992 9.8 0.639 0.828 0.639 0.828 dbm_add 807 14.1 0.662 0.704 0.662 0.704 compute_W_cubic_GW 10 7.0 0.001 0.001 0.698 0.703 ------------------------------------------------------------------------------- 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=22.128999999999998, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=38.711, 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=8.883, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.86, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.091, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.196, 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_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=9.135000000000002, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.837, 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=0.39, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.404, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.476, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.761, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.08, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.46, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.498, 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 0.018 395.706 395.706 qs_forces 1 2.0 0.000 0.000 395.035 395.035 rebuild_ks_matrix 7 6.6 0.000 0.000 393.548 393.548 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 393.548 393.548 hfx_ks_matrix 7 8.6 0.000 0.000 391.500 391.500 dbt_total 4903 11.6 0.026 0.026 338.093 338.093 hfx_ri_update_ks 7 9.6 0.000 0.000 333.258 333.258 hfx_ri_update_ks_Pmat 7 10.6 32.024 32.024 333.256 333.256 dbt_tas_total 2391 14.1 1.335 1.335 312.274 312.274 qs_energies 1 3.0 0.000 0.000 292.668 292.668 scf_env_do_scf 1 4.0 0.000 0.000 292.350 292.350 qs_ks_update_qs_env 8 6.0 0.000 0.000 291.229 291.229 dbt_contract 1473 13.0 0.123 0.123 290.104 290.104 dbt_tas_multiply 1482 14.0 0.004 0.004 280.282 280.282 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.004 269.018 269.018 dbt_tas_dbm 1482 16.0 0.005 0.005 254.950 254.950 dbm_multiply 1482 18.0 254.933 254.933 254.933 254.933 dbt_tas_mm_2 649 17.1 0.004 0.004 239.028 239.028 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 187.133 187.133 init_scf_loop 2 5.0 0.000 0.000 105.215 105.215 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 102.322 102.322 hfx_ri_update_forces 1 7.0 1.583 1.583 58.239 58.239 hfx_ri_forces_Pmat_3c 1 8.0 1.569 1.569 40.516 40.516 dbt_tas_reshape 906 14.4 0.019 0.019 24.436 24.436 dbt_copy 2373 12.3 0.131 0.131 15.959 15.959 dbt_tas_merge 649 14.1 14.011 14.011 15.468 15.468 dbt_tas_reshape_buffer_fill 906 15.4 14.791 14.791 14.791 14.791 precalc_derivatives 1 8.0 2.156 2.156 13.321 13.321 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 11.845 11.845 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 11.456 11.456 dbt_tas_mm_3T 659 17.1 0.002 0.002 10.631 10.631 dbm_reserve_blocks 8426 16.7 10.343 10.343 10.343 10.343 dbt_tas_reserve_blocks_index 7520 15.9 0.327 0.327 9.731 9.731 dbt_crop 2763 14.2 6.911 6.911 9.616 9.616 dbt_reshape 850 13.9 5.086 5.086 8.988 8.988 reshape_mm_small 906 15.6 0.134 0.134 8.168 8.168 dbt_tas_replicate 906 15.6 5.995 5.995 8.000 8.000 ------------------------------------------------------------------------------- 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 0.024 55.950 55.960 qs_forces 1 2.0 0.000 0.000 55.732 55.732 rebuild_ks_matrix 7 6.6 0.000 0.000 54.922 54.923 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 54.922 54.923 hfx_ks_matrix 7 8.6 0.000 0.000 53.917 53.930 dbt_total 4903 11.6 0.025 0.028 48.314 48.328 dbt_contract 1473 13.0 0.089 0.100 37.834 37.849 hfx_ri_update_ks 7 9.6 0.000 0.000 37.469 37.469 hfx_ri_update_ks_Pmat 7 10.6 1.400 1.868 37.468 37.468 dbt_tas_total 2391 14.1 0.112 0.137 35.622 35.625 qs_energies 1 3.0 0.001 0.013 34.486 34.487 scf_env_do_scf 1 4.0 0.000 0.001 34.204 34.204 qs_ks_update_qs_env 8 6.0 0.000 0.000 33.691 33.692 dbt_tas_multiply 1482 14.0 0.004 0.005 31.819 31.821 dbt_tas_dbm 1482 16.0 0.005 0.006 24.562 24.580 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 21.233 21.233 dbm_multiply 1482 18.0 16.783 21.119 16.783 21.119 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.004 20.879 20.881 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 19.916 19.916 hfx_ri_update_forces 1 7.0 0.063 0.078 16.448 16.461 dbt_tas_mm_2 649 17.1 0.003 0.004 14.864 14.878 mp_sync 17597 13.5 11.746 14.344 11.746 14.344 init_scf_loop 2 5.0 0.000 0.000 14.287 14.287 hfx_ri_forces_Pmat_3c 1 8.0 0.051 0.066 11.718 11.755 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 7.606 7.607 dbt_copy 2391 12.4 0.029 0.032 5.571 5.959 dbt_tas_mm_3T 659 17.1 0.002 0.002 4.086 4.905 dbt_crop 2763 14.2 2.878 4.023 3.568 4.728 dbt_reshape 1250 13.5 1.905 2.393 3.961 4.187 dbt_tas_mm_3N 163 16.5 0.000 0.001 3.847 3.910 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.761 3.761 precalc_derivatives 1 8.0 0.098 0.139 3.509 3.509 dbt_tas_merge 649 14.1 1.550 2.111 2.593 3.132 mp_waitall_2 5961 16.5 2.646 2.848 2.646 2.848 dbm_reserve_blocks 8460 16.8 2.027 2.344 2.027 2.344 dbt_tas_reserve_blocks_index 7551 16.0 0.260 0.343 1.952 2.305 dbt_tas_replicate 909 15.6 0.594 0.745 2.111 2.192 mp_max_i 3372 12.5 1.748 2.095 1.748 2.095 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.000 0.000 2.089 2.095 dbt_tas_communicate_buffer 1825 16.3 0.058 0.076 1.886 2.076 build_3c_derivatives 9 9.0 0.229 0.352 2.025 2.027 dbt_reserve_blocks_index 5473 15.1 0.109 0.132 1.593 1.860 dbt_reserve_blocks_index_array 5438 14.1 0.014 0.016 1.591 1.856 dbt_tas_reshape 916 14.4 0.007 0.009 1.529 1.607 dbt_communicate_buffer 1250 14.5 0.041 0.058 1.413 1.526 mp_alltoall_i 4327 15.3 1.338 1.470 1.338 1.470 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.001 0.002 1.353 1.355 convert_to_new_pgrid 4446 16.0 0.037 0.044 1.229 1.336 dbm_copy 3043 16.9 1.191 1.303 1.191 1.303 dbm_add 1482 16.0 0.920 1.132 0.920 1.132 ------------------------------------------------------------------------------- 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=62.692999999999984, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=254.933, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=32.024, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=14.791, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_merge", label="dbt_tas_merge", y=14.011, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=10.343, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_crop", label="dbt_crop", y=6.911, 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=16.92, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=16.783, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.4, 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=1.55, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.027, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_crop", label="dbt_crop", y=2.878, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=11.746, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.646, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.015 0.015 202.199 202.199 qs_energies 1 2.0 0.000 0.000 202.021 202.021 mp2_main 1 3.0 0.000 0.000 197.254 197.254 mp2_gpw_main 1 4.0 0.001 0.001 196.872 196.872 mp2_ri_gpw_compute_in 1 5.0 0.381 0.381 155.978 155.978 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 144.628 144.628 mp2_eri_3c_integrate_gpw 2656 7.0 0.014 0.014 115.538 115.538 integrate_v_rspace 2666 8.0 0.575 0.575 102.850 102.850 grid_integrate_task_list 2666 9.0 100.326 100.326 100.326 100.326 mp2_ri_gpw_compute_en 1 5.0 0.086 0.086 40.872 40.872 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.836 9.836 39.042 39.042 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.117 2.117 22.227 22.227 dbcsr_multiply_generic 5322 8.0 0.163 0.163 20.178 20.178 ao_to_mo_and_store_B_mult_1 2656 7.0 0.008 0.008 20.155 20.155 local_gemm 2080 8.0 20.111 20.111 20.111 20.111 calculate_wavefunction 2656 8.0 8.115 8.115 11.436 11.436 pw_transfer 63872 10.6 1.030 1.030 11.090 11.090 get_2c_integrals 1 6.0 0.000 0.000 10.969 10.969 multiply_cannon 5322 9.0 0.416 0.416 10.321 10.321 compute_2c_integrals 1 7.0 0.006 0.006 10.107 10.107 compute_2c_integrals_loop_lm 1 8.0 0.011 0.011 10.088 10.088 mp2_eri_2c_integrate_gpw 1 9.0 3.401 3.401 10.077 10.077 fft_wrap_pw1pw2 53228 11.4 0.109 0.109 9.852 9.852 multiply_cannon_loop 5322 10.0 0.112 0.112 9.013 9.013 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.180 2.180 8.833 8.833 make_m2s 10644 9.0 0.059 0.059 7.746 7.746 multiply_cannon_multrec 5322 11.0 7.559 7.559 7.597 7.597 make_images 10644 10.0 3.140 3.140 7.454 7.454 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 7.197 7.197 fft_wrap_pw1pw2_20 21271 12.4 0.468 0.468 6.910 6.910 fft3d_s 53229 13.4 6.374 6.374 6.406 6.406 dbcsr_complete_redistribute 2689 9.0 1.165 1.165 5.761 5.761 dbcsr_finalize 10708 9.5 0.124 0.124 5.133 5.133 mp2_ri_gpw_compute_en_ener 2080 7.0 5.063 5.063 5.063 5.063 dbcsr_merge_all 8011 10.3 3.621 3.621 4.556 4.556 scf_env_do_scf 1 3.0 0.000 0.000 4.374 4.374 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.374 4.374 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.005 0.021 40.197 40.208 qs_energies 1 2.0 0.000 0.001 40.127 40.127 mp2_main 1 3.0 0.000 0.001 37.837 37.838 mp2_gpw_main 1 4.0 0.001 0.002 37.721 37.721 mp2_ri_gpw_compute_in 1 5.0 0.051 0.052 17.326 22.847 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.937 21.459 mp2_ri_gpw_compute_en 1 5.0 0.154 0.166 20.305 20.831 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.904 19.491 integrate_v_rspace 93 8.1 0.100 0.107 13.864 19.338 grid_integrate_task_list 93 9.1 13.461 18.998 13.461 18.998 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.803 0.863 14.119 14.139 mp2_ri_gpw_compute_en_expansio 65 7.0 0.104 0.118 10.677 10.909 local_gemm 65 8.0 10.573 10.806 10.573 10.806 mp_min_d 2 7.0 5.542 6.085 5.542 6.085 mp2_ri_get_integ_group_size 1 6.0 0.000 0.000 5.523 6.049 mp2_ri_gpw_compute_en_comm 17 7.0 0.070 0.091 2.279 2.814 mp_sendrecv_dm3 1054 8.0 1.739 2.390 1.739 2.390 scf_env_do_scf 1 3.0 0.000 0.000 2.162 2.163 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 2.162 2.163 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.748 1.973 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.731 1.956 get_2c_integrals 1 6.0 0.000 0.000 1.320 1.345 qs_scf_new_mos 10 5.0 0.000 0.000 1.041 1.110 multiply_cannon 176 9.0 0.015 0.016 1.033 1.097 compute_2c_integrals 1 7.0 0.003 0.004 1.027 1.050 multiply_cannon_loop 176 10.0 0.002 0.002 0.976 1.041 eigensolver 11 5.8 0.001 0.001 1.016 1.018 compute_2c_integrals_loop_lm 1 8.0 0.001 0.004 0.749 0.961 mp2_eri_2c_integrate_gpw 1 9.0 0.202 0.325 0.748 0.961 pw_transfer 2120 10.5 0.044 0.054 0.820 0.905 multiply_cannon_multrec 246 11.0 0.839 0.878 0.844 0.883 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.855 0.857 cp_fm_redistribute_end 11 7.8 0.322 0.849 0.336 0.852 make_m2s 352 9.0 0.003 0.003 0.680 0.843 fft_wrap_pw1pw2 1768 11.4 0.004 0.005 0.763 0.839 make_images 352 10.0 0.051 0.059 0.668 0.831 cp_fm_diag_elpa_base 11 7.8 0.499 0.805 0.510 0.819 ------------------------------------------------------------------------------- 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=56.25200000000001, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=100.326, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=20.111, 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=9.836, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.115, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.559, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_min_d", label="mp_min_d", 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=7.240000000000002, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.461, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.573, 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=0.803, 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=0.839, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.739, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_min_d", label="mp_min_d", y=5.542, 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 0.082 0.082 124.739 124.739 qs_energies 1 2.0 0.000 0.000 123.406 123.406 scf_env_do_scf 1 3.0 0.000 0.000 116.755 116.755 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 116.755 116.755 qs_ks_update_qs_env 15 5.0 0.000 0.000 49.733 49.733 rebuild_ks_matrix 15 6.0 0.000 0.000 49.523 49.523 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 49.523 49.523 qs_scf_new_mos 15 5.0 0.000 0.000 42.440 42.440 eigensolver 15 6.0 0.001 0.001 34.697 34.697 qs_vxc_create 15 8.0 0.052 0.052 34.384 34.384 calculate_dispersion_nonloc 15 9.0 7.090 7.090 30.077 30.077 pw_transfer 1191 10.0 0.060 0.060 22.880 22.880 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 22.695 22.695 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.677 22.677 cp_fm_diag_elpa_base 15 8.0 20.107 20.107 22.677 22.677 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.849 21.849 calculate_rho_elec 16 6.0 0.224 0.224 21.849 21.849 grid_collocate_task_list 16 7.0 20.450 20.450 20.450 20.450 fft_wrap_pw1pw2_150 765 12.0 3.523 3.523 16.722 16.722 sum_up_and_integrate 15 8.0 0.040 0.040 13.777 13.777 integrate_v_rspace 15 9.0 0.020 0.020 13.737 13.737 grid_integrate_task_list 15 10.0 13.220 13.220 13.220 13.220 fft3d_s 1087 13.0 10.181 10.181 10.248 10.248 cp_fm_cholesky_restore 45 7.0 9.838 9.838 9.838 9.838 pw_scatter_s 585 13.1 7.042 7.042 7.042 7.042 fft_wrap_pw1pw2_200 197 12.3 0.683 0.683 5.702 5.702 copy_dbcsr_to_fm 16 5.9 0.000 0.000 5.675 5.675 dbcsr_complete_redistribute 46 8.3 2.375 2.375 5.569 5.569 cp_fm_upper_to_full 30 8.0 4.750 4.750 4.750 4.750 vdW_energy 15 10.0 4.505 4.505 4.505 4.505 xc_vxc_pw_create 15 9.0 0.211 0.211 4.255 4.255 gspace_mixing 14 5.0 0.171 0.171 4.020 4.020 broyden_mixing 14 6.0 3.423 3.423 3.424 3.424 init_scf_run 1 3.0 0.000 0.000 3.181 3.181 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.021 3.021 xc_pw_derive 90 11.0 0.001 0.001 2.665 2.665 ------------------------------------------------------------------------------- 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 0.031 61.795 61.807 qs_energies 1 2.0 0.000 0.000 61.445 61.450 scf_env_do_scf 1 3.0 0.000 0.001 57.231 57.232 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 57.231 57.232 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.631 24.680 rebuild_ks_matrix 15 6.0 0.000 0.000 24.596 24.645 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 24.596 24.645 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.489 20.492 calculate_rho_elec 16 6.0 0.007 0.007 20.489 20.492 grid_collocate_task_list 16 7.0 19.144 19.619 19.144 19.619 sum_up_and_integrate 15 8.0 0.006 0.008 13.918 13.999 integrate_v_rspace 15 9.0 0.001 0.001 13.912 13.996 grid_integrate_task_list 15 10.0 12.831 13.402 12.831 13.402 qs_scf_new_mos 15 5.0 0.000 0.000 12.790 13.191 eigensolver 15 6.0 0.001 0.002 11.781 11.795 qs_vxc_create 15 8.0 0.001 0.001 10.368 10.377 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.577 8.582 cp_fm_diag_elpa_base 15 8.0 8.421 8.433 8.574 8.578 calculate_dispersion_nonloc 15 9.0 0.970 1.791 8.519 8.536 pw_transfer 1191 10.0 0.092 0.101 7.943 8.035 fft_wrap_pw1pw2 1086 11.0 0.013 0.014 7.762 7.855 fft3d_ps 1086 13.0 2.587 2.800 6.069 6.215 fft_wrap_pw1pw2_150 765 12.0 0.292 0.307 5.355 5.415 mp_alltoall_z22v 1086 15.0 2.865 3.200 2.865 3.200 cp_fm_cholesky_restore 45 7.0 3.051 3.093 3.051 3.093 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.501 2.501 yz_to_x 501 13.9 0.254 0.380 2.270 2.476 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.167 2.374 fft_wrap_pw1pw2_200 197 12.3 0.183 0.202 2.302 2.370 xc_vxc_pw_create 15 9.0 0.015 0.018 1.848 1.873 rs_pw_transfer 158 9.4 0.001 0.002 1.283 1.538 init_scf_run 1 3.0 0.000 0.001 1.478 1.479 vdW_energy 15 10.0 1.343 1.425 1.343 1.425 build_core_ppnl 1 5.0 1.272 1.401 1.272 1.401 density_rs2pw 16 7.0 0.001 0.001 1.232 1.385 xc_pw_derive 90 11.0 0.001 0.002 1.254 1.332 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.300 1.300 x_to_yz 585 14.1 0.336 0.362 1.185 1.279 ------------------------------------------------------------------------------- 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=50.94300000000001, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.45, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.107, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.22, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.181, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=9.838, 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=15.482999999999997, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.144, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.421, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.831, 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=3.051, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=2.865, 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 0.083 350.071 350.071 qs_energies 1 2.0 0.000 0.000 349.926 349.926 ls_scf 1 3.0 0.000 0.000 348.689 348.689 ls_scf_main 1 4.0 0.002 0.002 339.523 339.523 density_matrix_trs4 11 5.0 0.012 0.012 249.472 249.472 arnoldi_extremal 12 6.1 0.000 0.000 166.110 166.110 arnoldi_normal_ev 12 7.1 0.014 0.014 166.110 166.110 build_subspace 23 8.1 0.076 0.076 163.169 163.169 dbcsr_matrix_vector_mult 652 9.0 0.168 0.168 163.160 163.160 dbcsr_matrix_vector_mult_local 652 10.0 161.712 161.712 161.721 161.721 ls_scf_dm_to_ks 11 5.0 0.000 0.000 84.853 84.853 matrix_ls_to_qs 11 6.0 0.000 0.000 81.616 81.616 dbcsr_multiply_generic 185 6.1 0.816 0.816 72.311 72.311 dbcsr_copy_into_existing 11 7.0 44.499 44.499 44.499 44.499 multiply_cannon 185 7.1 0.285 0.285 43.882 43.882 dbcsr_complete_redistribute 23 7.5 29.772 29.772 40.776 40.776 matrix_decluster 11 7.0 0.000 0.000 37.116 37.116 multiply_cannon_loop 185 8.1 0.219 0.219 31.659 31.659 make_m2s 370 7.1 0.037 0.037 24.150 24.150 multiply_cannon_multrec 185 9.1 22.909 22.909 22.934 22.934 make_images 370 8.1 10.344 10.344 22.608 22.608 dbcsr_finalize 646 7.5 0.359 0.359 14.674 14.674 dbcsr_merge_all 597 8.5 2.097 2.097 13.403 13.403 setup_rec_index_2d 370 8.1 11.853 11.853 11.853 11.853 dbcsr_sort_indices 1103 9.9 10.011 10.011 10.011 10.011 tree_to_linear_d 110 9.4 9.986 9.986 9.986 9.986 quick_finalize 395 10.0 0.442 0.442 8.756 8.756 calculate_norms 370 9.1 8.506 8.506 8.506 8.506 ls_scf_init_scf 1 4.0 0.000 0.000 8.494 8.494 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.161 8.161 dbcsr_special_finalize 370 9.1 0.002 0.002 8.104 8.104 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.522 7.522 ------------------------------------------------------------------------------- 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 67.011 67.021 qs_energies 1 2.0 0.000 0.000 66.914 66.914 ls_scf 1 3.0 0.000 0.000 66.853 66.853 ls_scf_main 1 4.0 0.001 0.010 64.113 64.114 density_matrix_trs4 11 5.0 0.006 0.019 61.422 61.493 dbcsr_multiply_generic 185 6.1 0.058 0.078 57.505 57.774 multiply_cannon 185 7.1 0.034 0.039 47.938 49.136 multiply_cannon_loop 185 8.1 0.117 0.139 45.492 46.576 multiply_cannon_multrec 1480 9.1 28.229 32.889 28.502 33.213 mp_waitall_1 11936 10.3 14.312 16.132 14.312 16.132 multiply_cannon_metrocomm3 1480 9.1 0.014 0.017 8.451 12.211 make_m2s 370 7.1 0.034 0.039 6.491 6.553 make_images 370 8.1 0.625 0.708 6.364 6.428 calculate_norms 2960 9.1 5.061 6.410 5.061 6.410 multiply_cannon_metrocomm1 1480 9.1 0.008 0.009 3.302 6.349 arnoldi_extremal 12 6.1 0.000 0.000 3.127 3.145 arnoldi_normal_ev 12 7.1 0.001 0.003 3.127 3.145 build_subspace 23 8.1 0.020 0.025 3.024 3.026 make_images_data 370 9.1 0.009 0.011 2.791 3.024 mp_sum_l 1119 5.6 1.978 2.887 1.978 2.887 dbcsr_matrix_vector_mult 652 9.0 0.009 0.042 2.143 2.845 hybrid_alltoall_any 393 9.9 0.179 0.819 2.424 2.597 dbcsr_matrix_vector_mult_local 652 10.0 1.633 2.553 1.635 2.556 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.354 2.412 ls_scf_init_scf 1 4.0 0.000 0.000 2.151 2.151 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.106 2.130 dbcsr_complete_redistribute 23 7.5 1.205 1.614 1.933 2.117 matrix_ls_to_qs 11 6.0 0.000 0.000 1.882 2.073 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.921 1.934 matrix_decluster 11 7.0 0.000 0.000 1.740 1.897 make_images_pack 370 9.1 1.619 1.801 1.622 1.806 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.073 1.786 dbcsr_finalize 646 7.5 0.008 0.009 1.416 1.517 buffer_matrices_ensure_size 370 8.1 1.351 1.486 1.351 1.486 ------------------------------------------------------------------------------- Plot: name="bench_dftb_timings_32omp", title="Timings of bench_dftb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32omp", name="rest", label="rest", y=70.82000000000005, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=161.712, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=44.499, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=29.772, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.909, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.853, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.506, 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=14.592999999999996, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.633, 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=1.205, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=28.229, 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=5.061, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.978, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.312, 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 70.907 70.907 lib_test 1 2.0 0.000 0.000 70.899 70.899 dbcsr_run_tests 3 3.0 0.002 0.002 70.899 70.899 test_multiplies_multiproc 3 4.0 0.001 0.001 55.295 55.295 dbcsr_redistribute 9 5.0 35.658 35.658 37.228 37.228 dbcsr_multiply_generic 9 5.0 0.002 0.002 16.338 16.338 dbcsr_make_random_matrix 9 4.0 12.567 12.567 15.499 15.499 multiply_cannon 9 6.0 0.001 0.001 11.714 11.714 multiply_cannon_loop 9 7.0 0.002 0.002 11.359 11.359 multiply_cannon_multrec 9 8.0 11.357 11.357 11.357 11.357 dbcsr_finalize 27 5.7 0.003 0.003 5.418 5.418 dbcsr_merge_all 18 6.5 1.952 1.952 4.692 4.692 dbcsr_data_release 975 7.6 2.777 2.777 2.777 2.777 tree_to_linear_d 9 7.0 1.843 1.843 1.843 1.843 make_m2s 18 6.0 0.001 0.001 1.580 1.580 make_images 18 7.0 0.546 0.546 1.531 1.531 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.003 0.014 18.148 18.152 lib_test 1 2.0 0.000 0.000 18.121 18.138 dbcsr_run_tests 3 3.0 0.000 0.001 18.117 18.135 test_multiplies_multiproc 3 4.0 0.000 0.002 17.273 17.338 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.386 15.485 multiply_cannon 9 6.0 0.002 0.002 13.643 13.948 multiply_cannon_loop 9 7.0 0.002 0.002 13.354 13.624 multiply_cannon_multrec 72 8.0 11.253 11.898 11.254 11.899 mp_waitall_1 576 9.2 2.396 3.073 2.396 3.073 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.856 2.433 dbcsr_make_random_matrix 9 4.0 0.670 0.920 0.813 1.005 dbcsr_data_release 444 7.6 0.792 0.937 0.792 0.937 mp_sum_l 390 2.5 0.410 0.861 0.410 0.861 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.407 0.857 dbcsr_finalize 27 5.7 0.000 0.000 0.713 0.789 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.237 0.779 dbcsr_destroy 111 5.9 0.000 0.000 0.631 0.771 make_m2s 18 6.0 0.001 0.001 0.651 0.694 make_images 18 7.0 0.021 0.025 0.648 0.691 dbcsr_merge_all 18 6.5 0.100 0.119 0.550 0.616 dbcsr_checksum 6 5.0 0.154 0.531 0.534 0.534 dbcsr_redistribute 9 5.0 0.239 0.278 0.396 0.424 make_images_data 18 8.0 0.000 0.001 0.335 0.399 mp_sum_d 191 1.2 0.381 0.397 0.381 0.397 dbcsr_data_copy_aa2 18 7.5 0.334 0.393 0.334 0.393 ------------------------------------------------------------------------------- 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=6.595999999999989, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.658, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.567, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.357, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.777, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.952, 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=2.2880000000000003, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.239, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.67, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.253, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.792, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.1, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.396, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.41, 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 0.048 0.048 132.840 132.840 qs_mol_dyn_low 1 2.0 0.003 0.003 131.498 131.498 velocity_verlet 5 3.0 0.003 0.003 107.253 107.253 qmmm_el_coupling 6 3.8 0.000 0.000 87.765 87.765 qmmm_elec_with_gaussian 6 4.8 0.088 0.088 87.761 87.761 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.066 87.066 qmmm_elec_gaussian_low_G 6 6.8 86.186 86.186 86.186 86.186 qs_forces 6 3.8 0.000 0.000 35.251 35.251 qs_energies 6 4.8 0.000 0.000 31.222 31.222 scf_env_do_scf 6 5.8 0.001 0.001 28.960 28.960 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 25.268 25.268 rebuild_ks_matrix 45 8.4 0.000 0.000 24.530 24.530 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.530 24.530 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.967 20.967 pw_transfer 966 12.3 0.050 0.050 16.977 16.977 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.767 16.767 fft_wrap_pw1pw2_150 507 15.2 2.192 2.192 16.361 16.361 qs_vxc_create 45 10.4 0.001 0.001 13.296 13.296 xc_vxc_pw_create 45 11.4 0.686 0.686 13.296 13.296 xc_pw_derive 270 13.4 0.002 0.002 9.172 9.172 fft3d_s 802 15.6 7.628 7.628 7.636 7.636 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.116 7.116 calculate_rho_elec 45 8.9 0.563 0.563 7.116 7.116 xc_rho_set_and_dset_create 45 12.4 0.665 0.665 6.953 6.953 pw_scatter_s 429 15.8 5.683 5.683 5.683 5.683 xc_pw_divergence 45 12.4 0.001 0.001 5.601 5.601 qmmm_forces 6 3.8 0.001 0.001 5.414 5.414 qmmm_forces_with_gaussian 6 4.8 0.092 0.092 5.062 5.062 pw_integral_ab 2539 7.4 4.407 4.407 4.407 4.407 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.236 4.236 qs_ks_ddapc 45 10.4 0.001 0.001 4.184 4.184 init_scf_loop 6 6.8 0.000 0.000 3.688 3.688 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.570 3.570 qmmm_forces_gaussian_low_G 6 6.8 3.539 3.539 3.539 3.539 density_rs2pw 45 9.9 0.001 0.001 3.290 3.290 grid_collocate_task_list 45 9.9 3.263 3.263 3.263 3.263 pw_poisson_solve 51 9.9 1.324 1.324 3.084 3.084 sum_up_and_integrate 45 10.4 0.116 0.116 2.940 2.940 integrate_v_rspace 45 11.4 0.006 0.006 2.823 2.823 ------------------------------------------------------------------------------- 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 0.037 0.057 57.472 57.483 qs_mol_dyn_low 1 2.0 0.003 0.005 56.160 56.257 qs_forces 6 3.8 0.000 0.001 40.026 40.026 qs_energies 6 4.8 0.000 0.001 38.184 38.184 scf_env_do_scf 6 5.8 0.000 0.001 37.213 37.213 scf_env_do_scf_inner_loop 113 6.2 0.002 0.019 35.713 35.714 rebuild_ks_matrix 119 8.1 0.000 0.000 26.145 26.161 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.019 26.145 26.161 qs_ks_update_qs_env 119 7.3 0.001 0.001 24.583 24.595 velocity_verlet 5 3.0 0.002 0.004 23.909 23.913 pw_transfer 2446 12.3 0.200 0.229 16.928 17.484 fft_wrap_pw1pw2 2059 13.4 0.023 0.025 16.479 17.035 fft_wrap_pw1pw2_150 1321 14.9 1.273 1.405 15.877 16.429 qs_vxc_create 119 10.1 0.002 0.003 13.405 13.408 xc_vxc_pw_create 119 11.1 0.153 0.219 13.403 13.406 fft3d_ps 2059 15.4 6.948 7.638 12.288 12.893 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.742 10.743 calculate_rho_elec 119 8.3 0.049 0.056 10.741 10.742 xc_pw_derive 714 13.1 0.011 0.012 10.095 10.410 sum_up_and_integrate 119 10.1 0.053 0.061 9.329 9.405 integrate_v_rspace 119 11.1 0.003 0.004 9.275 9.348 qmmm_forces 6 3.8 0.002 0.002 7.966 7.967 qmmm_forces_with_gaussian 6 4.8 0.435 0.468 7.473 7.879 rs_pw_transfer 988 11.5 0.011 0.015 7.267 7.500 xc_rho_set_and_dset_create 119 12.1 0.362 0.726 6.390 7.420 qmmm_el_coupling 6 3.8 0.000 0.000 7.230 7.323 qmmm_elec_with_gaussian 6 4.8 0.447 0.493 7.228 7.321 xc_pw_divergence 119 12.1 0.005 0.006 6.665 6.920 density_rs2pw 119 9.3 0.005 0.007 6.226 6.491 potential_pw2rs 119 12.1 0.006 0.007 5.637 5.647 grid_collocate_task_list 119 9.3 4.376 4.678 4.376 4.678 mp_alltoall_z22v 2059 17.4 3.873 4.417 3.873 4.417 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.827 4.064 grid_integrate_task_list 119 12.1 3.417 3.692 3.417 3.692 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.412 3.682 qmmm_forces_gaussian_low_G 6 6.8 3.148 3.386 3.148 3.386 x_to_yz 1095 16.8 0.814 0.922 2.763 3.107 qmmm_elec_gaussian_low_G 6 6.8 2.822 3.093 2.822 3.093 rs_pw_transfer_PW2RS_150 125 13.9 1.336 1.404 2.877 2.927 mp_waitany 4028 12.8 2.385 2.807 2.385 2.807 yz_to_x 964 16.0 0.592 0.784 2.516 2.771 pw_restrict_s3 18 5.8 1.388 1.679 2.585 2.746 rs_pw_transfer_RS2PW_150 125 11.2 1.025 1.260 2.399 2.638 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.152 2.254 pw_prolongate_s3 18 6.8 1.198 1.392 2.152 2.254 qs_scf_new_mos 113 7.2 0.000 0.000 2.218 2.224 qs_scf_loop_do_ot 113 8.2 0.000 0.000 2.218 2.223 ot_scf_mini 113 9.2 0.001 0.001 2.127 2.132 dbcsr_multiply_generic 2588 12.3 0.055 0.067 2.002 2.048 mp_waitall_1 188862 16.2 1.733 2.043 1.733 2.043 qs_ks_ddapc 119 10.1 0.002 0.002 1.889 1.965 mp_sum_dm3 33 5.7 1.770 1.886 1.770 1.886 pw_gather_p 964 15.0 1.299 1.645 1.299 1.645 pw_scatter_p 1095 15.8 1.568 1.602 1.568 1.602 pw_integral_ab 2761 7.7 1.228 1.327 1.423 1.578 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.571 1.572 init_scf_loop 6 6.8 0.000 0.000 1.497 1.497 xc_functional_eval 238 13.1 0.003 0.004 0.739 1.371 ot_mini 113 10.2 0.000 0.001 1.291 1.298 qmmm_env_create 1 2.0 0.026 0.033 1.159 1.162 ------------------------------------------------------------------------------- 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=22.133999999999986, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.186, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.628, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.683, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.407, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.539, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.263, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=31.66, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.822, 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=1.228, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.148, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.376, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.948, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.417, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.873, yerr=0.0 Summary: Performance test took 37 minutes. Status: OK Removing intermediate container 1d41068727d3 ---> 67dab12491b8 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 90af5f38857c Removing intermediate container 90af5f38857c ---> 33df421d3df4 Step 42/42 : ENTRYPOINT [] ---> Running in 45381ac26adb Removing intermediate container 45381ac26adb ---> cc25f586fc18 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built cc25f586fc18 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: 2022-09-19 13:50:42+00:00