StartDate: 2023-04-27 19:04:47+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 5dafbb2db87963ef458ed9b502d9aa232499ab07 CommitTime: 2023-04-27 15:56:23 +0200 CommitAuthor: Matthias Krack CommitSubject: Print only 1 instead of 3 backup copies by default #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=5dafbb2db87963ef458ed9b502d9aa232499ab07 Build-Cache: Yes #1 [internal] load build definition from Dockerfile.test_performance #1 transferring dockerfile: 3.23kB done #1 DONE 0.0s #2 [internal] load .dockerignore #2 transferring context: 124B done #2 DONE 0.0s #3 [internal] load metadata for docker.io/library/ubuntu:22.04 #3 DONE 0.2s #4 [internal] load build context #4 DONE 0.0s #5 importing cache manifest from us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master #5 ... #6 [auth] cp2k-org-project/cp2kci/img_cp2k-perf-openmp:pull token for us-central1-docker.pkg.dev #6 DONE 0.0s #7 [auth] cp2k-org-project/cp2kci/img_cp2k-sdbg:pull token for us-central1-docker.pkg.dev #7 DONE 0.0s #8 importing cache manifest from us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-sdbg:master #8 DONE 1.1s #5 importing cache manifest from us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master #5 DONE 1.1s #9 [ 1/40] FROM docker.io/library/ubuntu:22.04@sha256:67211c14fa74f070d27cc59d69a7fa9aeff8e28ea118ef3babc295a0428a6d21 #9 DONE 0.0s #4 [internal] load build context #4 transferring context: 358.20MB 2.7s done #4 DONE 2.7s #10 [ 6/40] 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/ #10 CACHED #11 [17/40] COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ #11 CACHED #12 [16/40] RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build #12 CACHED #13 [27/40] COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ #13 CACHED #14 [15/40] COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ #14 CACHED #15 [22/40] RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build #15 CACHED #16 [21/40] COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ #16 CACHED #17 [12/40] RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build #17 CACHED #18 [18/40] RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build #18 CACHED #19 [29/40] WORKDIR /opt/cp2k #19 CACHED #20 [31/40] COPY ./src ./src #20 CACHED #21 [24/40] RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build #21 CACHED #22 [ 3/40] COPY ./tools/toolchain/install_requirements*.sh ./ #22 CACHED #23 [32/40] COPY ./exts ./exts #23 CACHED #24 [26/40] RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build #24 CACHED #25 [ 9/40] COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ #25 CACHED #26 [11/40] COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ #26 CACHED #27 [20/40] RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build #27 CACHED #28 [ 2/40] WORKDIR /opt/cp2k-toolchain #28 CACHED #29 [ 8/40] RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run #29 CACHED #30 [23/40] COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ #30 CACHED #31 [14/40] RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build #31 CACHED #32 [ 4/40] RUN ./install_requirements.sh ubuntu:22.04 #32 CACHED #33 [ 7/40] COPY ./tools/toolchain/install_cp2k_toolchain.sh . #33 CACHED #34 [10/40] RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build #34 CACHED #35 [13/40] COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ #35 CACHED #36 [30/40] COPY ./Makefile . #36 CACHED #37 [19/40] COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ #37 CACHED #38 [28/40] RUN ./scripts/generate_arch_files.sh && rm -rf ./build #38 CACHED #39 [ 5/40] RUN mkdir scripts #39 CACHED #40 [25/40] COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ #40 CACHED #41 [33/40] COPY ./tools/build_utils ./tools/build_utils #41 CACHED #42 [34/40] 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 ) && rm -rf lib obj && ( [ ! -f ./exe/local/cp2k.psmp ] || ldd ./exe/local/cp2k.psmp | grep -q libmpi )" './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... #42 DONE 498.1s #43 [35/40] COPY ./data ./data #43 DONE 0.3s #44 [36/40] COPY ./tests ./tests #44 DONE 0.6s #45 [37/40] COPY ./tools/regtesting ./tools/regtesting #45 DONE 0.0s #46 [38/40] COPY ./benchmarks ./benchmarks #46 DONE 0.6s #47 [39/40] COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ #47 DONE 0.0s #48 [40/40] RUN ./test_performance.sh "local" 2>&1 | tee report.log ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 70 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 96.946 96.946 qs_mol_dyn_low 1 2.0 0.003 0.003 96.262 96.262 qs_forces 11 3.9 0.001 0.001 96.220 96.220 qs_energies 11 4.9 0.001 0.001 89.466 89.466 scf_env_do_scf 11 5.9 0.001 0.001 78.003 78.003 velocity_verlet 10 3.0 0.002 0.002 62.344 62.344 scf_env_do_scf_inner_loop 108 6.5 0.012 0.012 59.838 59.838 rebuild_ks_matrix 119 8.3 0.001 0.001 22.646 22.646 qs_ks_build_kohn_sham_matrix 119 9.3 0.014 0.014 22.645 22.645 dbcsr_multiply_generic 2286 12.5 0.167 0.167 22.111 22.111 qs_rho_update_rho_low 119 7.7 0.001 0.001 21.883 21.883 calculate_rho_elec 119 8.7 0.970 0.970 21.883 21.883 qs_scf_new_mos 108 7.5 0.001 0.001 21.491 21.491 qs_scf_loop_do_ot 108 8.5 0.001 0.001 21.490 21.490 qs_ks_update_qs_env 119 7.6 0.001 0.001 20.689 20.689 ot_scf_mini 108 9.5 0.003 0.003 19.981 19.981 init_scf_loop 11 6.9 0.000 0.000 17.991 17.991 grid_collocate_task_list 119 9.7 17.082 17.082 17.082 17.082 prepare_preconditioner 11 7.9 0.000 0.000 15.201 15.201 make_preconditioner 11 8.9 0.000 0.000 15.201 15.201 sum_up_and_integrate 119 10.3 0.877 0.877 14.769 14.769 make_full_inverse_cholesky 11 9.9 0.026 0.026 13.984 13.984 integrate_v_rspace 119 11.3 0.102 0.102 13.891 13.891 ot_mini 108 10.5 0.001 0.001 12.818 12.818 make_m2s 4572 13.5 0.049 0.049 11.701 11.701 grid_integrate_task_list 119 12.3 11.648 11.648 11.648 11.648 qs_ot_get_derivative 108 11.5 0.001 0.001 6.942 6.942 pw_transfer 1439 11.6 0.077 0.077 6.739 6.739 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.527 6.527 fft_wrap_pw1pw2 1201 12.6 0.007 0.007 6.493 6.493 make_images 4572 14.5 2.324 2.324 6.165 6.165 multiply_cannon 2286 13.5 0.218 0.218 6.127 6.127 dbcsr_make_dense_low 5837 15.5 0.075 0.075 5.978 5.978 make_dense_data 5837 16.5 5.325 5.325 5.888 5.888 ot_diis_step 108 11.5 0.004 0.004 5.872 5.872 fft_wrap_pw1pw2_140 487 13.2 0.518 0.518 5.605 5.605 multiply_cannon_loop 2286 14.5 0.042 0.042 5.584 5.584 multiply_cannon_multrec 2286 15.5 5.483 5.483 5.541 5.541 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.386 5.386 apply_single 119 13.6 0.000 0.000 5.386 5.386 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.201 5.201 cp_fm_cholesky_decompose 22 10.9 5.179 5.179 5.179 5.179 cp_fm_cholesky_invert 11 10.9 4.449 4.449 4.449 4.449 init_scf_run 11 5.9 0.002 0.002 4.283 4.283 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.281 4.281 dbcsr_copy 2102 12.0 0.267 0.267 4.032 4.032 dbcsr_complete_redistribute 329 12.2 1.999 1.999 3.878 3.878 density_rs2pw 119 9.7 0.005 0.005 3.830 3.830 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.823 3.823 wfi_extrapolate 11 7.9 0.001 0.001 3.725 3.725 dbcsr_copy_into_existing 22 7.9 3.725 3.725 3.725 3.725 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.333 3.333 qs_ot_get_p 119 10.4 0.001 0.001 3.197 3.197 copy_dbcsr_to_fm 153 11.3 0.003 0.003 3.193 3.193 fft3d_s 1202 14.6 3.164 3.164 3.170 3.170 qs_create_task_list 11 7.9 0.000 0.000 2.935 2.935 generate_qs_task_list 11 8.9 1.960 1.960 2.935 2.935 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.929 2.929 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.755 2.755 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.509 2.509 dbcsr_data_release 279534 16.0 2.351 2.351 2.351 2.351 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.183 2.183 potential_pw2rs 119 12.3 0.051 0.051 2.142 2.142 pw_poisson_solve 119 10.3 0.371 0.371 2.123 2.123 qs_ot_get_derivative_taylor 59 13.0 0.002 0.002 2.104 2.104 hybrid_alltoall_any 4725 16.4 1.667 1.667 1.969 1.969 ------------------------------------------------------------------------------- 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 0.009 0.025 54.361 54.372 qs_mol_dyn_low 1 2.0 0.004 0.006 54.204 54.209 qs_forces 11 3.9 0.002 0.002 54.155 54.155 qs_energies 11 4.9 0.001 0.001 50.685 50.687 scf_env_do_scf 11 5.9 0.001 0.002 46.407 46.408 scf_env_do_scf_inner_loop 108 6.5 0.004 0.023 42.873 42.875 velocity_verlet 10 3.0 0.002 0.004 31.719 31.721 rebuild_ks_matrix 119 8.3 0.001 0.001 19.809 19.927 qs_ks_build_kohn_sham_matrix 119 9.3 0.019 0.021 19.808 19.926 qs_ks_update_qs_env 119 7.6 0.001 0.001 17.649 17.756 qs_rho_update_rho_low 119 7.7 0.001 0.001 16.368 16.376 calculate_rho_elec 119 8.7 0.034 0.035 16.367 16.375 dbcsr_multiply_generic 2286 12.5 0.090 0.096 15.271 15.511 sum_up_and_integrate 119 10.3 0.042 0.049 14.730 14.754 integrate_v_rspace 119 11.3 0.005 0.006 14.688 14.721 qs_scf_new_mos 108 7.5 0.001 0.001 12.125 12.248 qs_scf_loop_do_ot 108 8.5 0.001 0.001 12.125 12.247 multiply_cannon 2286 13.5 0.178 0.202 11.068 11.604 ot_scf_mini 108 9.5 0.003 0.004 11.367 11.491 grid_collocate_task_list 119 9.7 10.785 11.069 10.785 11.069 multiply_cannon_loop 2286 14.5 0.107 0.117 10.386 10.901 grid_integrate_task_list 119 12.3 9.632 9.814 9.632 9.814 mp_waitall_1 158411 16.6 8.565 9.110 8.565 9.110 ot_mini 108 10.5 0.001 0.001 6.615 6.751 multiply_cannon_metrocomm3 18288 15.5 0.043 0.047 5.954 6.563 rs_pw_transfer 974 11.9 0.013 0.015 5.346 5.721 density_rs2pw 119 9.7 0.006 0.008 4.843 5.219 pw_transfer 1439 11.6 0.108 0.116 5.080 5.209 fft_wrap_pw1pw2 1201 12.6 0.011 0.012 4.882 4.998 fft_wrap_pw1pw2_140 487 13.2 0.894 1.047 4.135 4.409 potential_pw2rs 119 12.3 0.008 0.009 4.252 4.301 multiply_cannon_multrec 18288 15.5 3.463 3.650 3.475 3.667 qs_ot_get_derivative 108 11.5 0.001 0.001 3.411 3.535 init_scf_loop 11 6.9 0.000 0.000 3.517 3.520 fft3d_ps 1201 14.6 1.586 1.759 3.081 3.343 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.084 3.206 apply_single 119 13.6 0.000 0.001 3.084 3.206 ot_diis_step 108 11.5 0.004 0.004 3.169 3.169 init_scf_run 11 5.9 0.000 0.005 3.086 3.088 scf_env_initial_rho_setup 11 6.9 0.000 0.004 3.086 3.088 make_m2s 4572 13.5 0.053 0.059 2.818 2.899 wfi_extrapolate 11 7.9 0.001 0.001 2.675 2.675 make_images 4572 14.5 0.134 0.139 2.442 2.521 mp_waitany 9880 13.7 1.929 2.348 1.929 2.348 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.332 2.343 rs_pw_transfer_RS2PW_140 130 11.5 0.208 0.253 1.435 1.818 qs_ot_get_p 119 10.4 0.001 0.001 1.500 1.655 mp_alltoall_z22v 1201 16.6 1.189 1.653 1.189 1.653 rs_pw_transfer_PW2RS_140 130 13.9 0.428 0.516 1.517 1.574 make_images_data 4572 15.5 0.039 0.045 1.291 1.442 prepare_preconditioner 11 7.9 0.000 0.000 1.364 1.399 make_preconditioner 11 8.9 0.000 0.000 1.364 1.399 multiply_cannon_metrocomm1 18288 15.5 0.022 0.024 0.626 1.399 mp_alltoall_d11v 2130 13.8 1.005 1.390 1.005 1.390 mp_sum_l 11218 13.2 0.851 1.276 0.851 1.276 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.227 1.252 mp_sum_d 4135 12.0 0.761 1.249 0.761 1.249 hybrid_alltoall_any 4725 16.4 0.074 0.229 1.137 1.243 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.133 1.201 rs_pw_transfer_PW2RS_50 119 14.3 0.337 0.372 0.989 1.192 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.045 1.101 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.001 1.010 1.100 ------------------------------------------------------------------------------- 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=52.22899999999999, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=17.082, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=11.648, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.483, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.325, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=5.179, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=19.986999999999995, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=10.785, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=9.632, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.463, 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="mp_waitany", label="mp_waitany", y=1.929, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.565, 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 0.030 0.030 116.950 116.950 qs_mol_dyn_low 1 2.0 0.003 0.003 116.260 116.260 qs_forces 11 3.9 0.001 0.001 116.216 116.216 qs_energies 11 4.9 0.001 0.001 108.185 108.185 scf_env_do_scf 11 5.9 0.001 0.001 95.207 95.207 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 76.695 76.695 velocity_verlet 10 3.0 0.002 0.002 74.873 74.873 rebuild_ks_matrix 107 8.3 0.001 0.001 35.532 35.532 qs_ks_build_kohn_sham_matrix 107 9.3 0.012 0.012 35.532 35.532 qs_rho_update_rho_low 107 7.7 0.001 0.001 33.690 33.690 calculate_rho_elec 107 8.7 0.870 0.870 33.689 33.689 qs_ks_update_qs_env 107 7.6 0.001 0.001 31.910 31.910 grid_collocate_task_list 107 9.7 29.374 29.374 29.374 29.374 sum_up_and_integrate 107 10.3 0.734 0.734 28.591 28.591 integrate_v_rspace 107 11.3 0.119 0.119 27.857 27.857 grid_integrate_task_list 107 12.3 25.976 25.976 25.976 25.976 dbcsr_multiply_generic 1966 12.4 0.143 0.143 18.977 18.977 init_scf_loop 11 6.9 0.000 0.000 18.322 18.322 qs_scf_new_mos 96 7.5 0.001 0.001 18.315 18.315 qs_scf_loop_do_ot 96 8.5 0.001 0.001 18.315 18.315 ot_scf_mini 96 9.5 0.002 0.002 17.017 17.017 prepare_preconditioner 11 7.9 0.000 0.000 14.145 14.145 make_preconditioner 11 8.9 0.000 0.000 14.145 14.145 make_full_inverse_cholesky 11 9.9 0.031 0.031 12.951 12.951 ot_mini 96 10.5 0.001 0.001 11.026 11.026 make_m2s 3932 13.4 0.040 0.040 10.241 10.241 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.797 6.797 pw_transfer 1295 11.6 0.064 0.064 5.865 5.865 qs_ot_get_derivative 96 11.5 0.001 0.001 5.857 5.857 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.660 5.660 init_scf_run 11 5.9 0.002 0.002 5.583 5.583 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.581 5.581 make_images 3932 14.4 2.027 2.027 5.353 5.353 dbcsr_make_dense_low 4961 15.5 0.068 0.068 5.342 5.342 make_dense_data 4961 16.5 4.735 4.735 5.262 5.262 ot_diis_step 96 11.5 0.003 0.003 5.166 5.166 multiply_cannon 1966 13.4 0.164 0.164 5.138 5.138 wfi_extrapolate 11 7.9 0.001 0.001 4.940 4.940 fft_wrap_pw1pw2_140 439 13.2 0.417 0.417 4.907 4.907 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.856 4.856 apply_single 107 13.6 0.000 0.000 4.856 4.856 multiply_cannon_loop 1966 14.4 0.037 0.037 4.694 4.694 multiply_cannon_multrec 1966 15.4 4.613 4.613 4.656 4.656 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.618 4.618 cp_fm_cholesky_decompose 22 10.9 4.582 4.582 4.582 4.582 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.505 4.505 cp_fm_cholesky_invert 11 10.9 4.238 4.238 4.238 4.238 dbcsr_copy 1855 11.9 0.233 0.233 3.739 3.739 dbcsr_complete_redistribute 317 12.2 1.950 1.950 3.730 3.730 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.730 3.730 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.524 3.524 dbcsr_copy_into_existing 22 7.9 3.450 3.450 3.450 3.450 density_rs2pw 107 9.7 0.005 0.005 3.445 3.445 qs_create_task_list 11 7.9 0.000 0.000 3.339 3.339 generate_qs_task_list 11 8.9 2.393 2.393 3.339 3.339 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.113 3.113 fft3d_s 1082 14.6 2.797 2.797 2.806 2.806 qs_ot_get_p 107 10.4 0.001 0.001 2.647 2.647 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.633 2.633 ------------------------------------------------------------------------------- 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 0.009 0.031 75.704 75.715 qs_mol_dyn_low 1 2.0 0.004 0.005 75.571 75.576 qs_forces 11 3.9 0.002 0.002 75.528 75.529 qs_energies 11 4.9 0.001 0.001 70.503 70.505 scf_env_do_scf 11 5.9 0.000 0.002 65.321 65.322 scf_env_do_scf_inner_loop 96 6.5 0.003 0.022 60.542 60.542 velocity_verlet 10 3.0 0.002 0.004 44.133 44.134 rebuild_ks_matrix 107 8.3 0.000 0.001 32.708 32.787 qs_ks_build_kohn_sham_matrix 107 9.3 0.015 0.018 32.708 32.787 qs_ks_update_qs_env 107 7.6 0.001 0.001 28.842 28.916 sum_up_and_integrate 107 10.3 0.035 0.039 28.668 28.693 integrate_v_rspace 107 11.3 0.004 0.005 28.633 28.659 qs_rho_update_rho_low 107 7.7 0.001 0.001 28.169 28.177 calculate_rho_elec 107 8.7 0.028 0.029 28.169 28.176 grid_integrate_task_list 107 12.3 24.346 24.791 24.346 24.791 grid_collocate_task_list 107 9.7 23.623 24.070 23.623 24.070 dbcsr_multiply_generic 1966 12.4 0.070 0.076 12.266 12.375 qs_scf_new_mos 96 7.5 0.001 0.001 9.578 9.663 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.577 9.663 multiply_cannon 1966 13.4 0.141 0.150 9.019 9.260 ot_scf_mini 96 9.5 0.002 0.002 8.971 9.045 multiply_cannon_loop 1966 14.4 0.085 0.093 8.515 8.751 mp_waitall_1 136719 16.5 6.893 7.446 6.893 7.446 multiply_cannon_metrocomm3 15728 15.4 0.034 0.036 4.808 5.372 ot_mini 96 10.5 0.001 0.001 5.211 5.290 rs_pw_transfer 878 11.9 0.011 0.013 4.415 5.132 init_scf_loop 11 6.9 0.000 0.000 4.766 4.766 density_rs2pw 107 9.7 0.005 0.005 3.937 4.646 init_scf_run 11 5.9 0.000 0.005 4.089 4.089 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.089 4.089 pw_transfer 1295 11.6 0.089 0.092 3.957 4.056 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.998 4.005 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 3.801 3.891 wfi_extrapolate 11 7.9 0.001 0.001 3.704 3.705 fft_wrap_pw1pw2_140 439 13.2 0.657 0.779 3.232 3.376 potential_pw2rs 107 12.3 0.006 0.007 3.345 3.363 multiply_cannon_multrec 15728 15.4 2.944 3.071 2.953 3.082 qs_ot_get_derivative 96 11.5 0.001 0.001 2.679 2.753 fft3d_ps 1081 14.6 1.237 1.410 2.408 2.555 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.489 2.532 apply_single 107 13.6 0.000 0.000 2.489 2.532 ot_diis_step 96 11.5 0.003 0.004 2.511 2.512 mp_waitany 8968 13.7 1.611 2.326 1.611 2.326 make_m2s 3932 13.4 0.042 0.047 2.199 2.249 make_images 3932 14.4 0.108 0.113 1.896 1.950 mp_alltoall_d11v 1998 13.7 1.122 1.939 1.122 1.939 rs_pw_transfer_RS2PW_140 118 11.5 0.162 0.178 1.209 1.929 rs_gather_matrices 107 12.3 0.092 0.101 0.877 1.660 ------------------------------------------------------------------------------- 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=47.670000000000016, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=29.374, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.976, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.735, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.613, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.582, 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=16.286999999999992, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=23.623, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.346, 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=2.944, 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="mp_waitall_1", label="mp_waitall_1", y=6.893, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.611, 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 0.242 0.242 124.827 124.827 qs_energies 1 2.0 0.000 0.000 123.890 123.890 scf_env_do_scf 1 3.0 0.000 0.000 122.596 122.596 qs_ks_update_qs_env 8 5.0 0.000 0.000 116.483 116.483 rebuild_ks_matrix 7 6.0 0.000 0.000 116.424 116.424 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 116.424 116.424 hfx_ks_matrix 7 8.0 0.000 0.000 105.978 105.978 integrate_four_center 7 9.0 1.910 1.910 105.933 105.933 integrate_four_center_main 7 10.0 0.956 0.956 96.876 96.876 integrate_four_center_bin 450 11.0 95.920 95.920 95.920 95.920 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 67.007 67.007 init_scf_loop 1 4.0 0.000 0.000 55.574 55.574 integrate_four_center_load 7 10.0 0.013 0.013 6.850 6.850 hfx_load_balance 1 11.0 0.007 0.007 6.836 6.836 qs_vxc_create 14 8.0 0.000 0.000 3.687 3.687 xc_vxc_pw_create 14 9.0 0.141 0.141 3.687 3.687 hfx_load_balance_bin 1 12.0 3.421 3.421 3.421 3.421 hfx_load_balance_count 1 12.0 3.391 3.391 3.391 3.391 prepare_preconditioner 1 5.0 0.000 0.000 2.900 2.900 make_preconditioner 1 6.0 0.000 0.000 2.900 2.900 calculate_rho_elec 15 7.4 0.123 0.123 2.878 2.878 xc_rho_set_and_dset_create 14 10.0 0.121 0.121 2.712 2.712 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.675 2.675 ------------------------------------------------------------------------------- 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 0.286 0.321 108.666 108.679 qs_energies 1 2.0 0.000 0.000 108.151 108.158 scf_env_do_scf 1 3.0 0.000 0.000 107.763 107.764 qs_ks_update_qs_env 8 5.0 0.000 0.000 105.460 105.461 rebuild_ks_matrix 7 6.0 0.000 0.000 105.451 105.452 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 105.451 105.452 hfx_ks_matrix 7 8.0 0.000 0.001 99.283 99.284 integrate_four_center 7 9.0 0.061 0.370 99.273 99.275 integrate_four_center_main 7 10.0 0.004 0.004 90.527 92.172 integrate_four_center_bin 448 11.0 90.523 92.169 90.523 92.169 scf_env_do_scf_inner_loop 7 4.0 0.000 0.002 60.208 60.208 init_scf_loop 1 4.0 0.000 0.000 47.554 47.555 integrate_four_center_load 7 10.0 0.000 0.000 6.254 6.256 hfx_load_balance 1 11.0 0.001 0.001 6.254 6.256 mp_sync 56 11.2 1.736 3.321 1.736 3.321 hfx_load_balance_bin 1 12.0 3.054 3.125 3.054 3.125 hfx_load_balance_count 1 12.0 3.050 3.113 3.050 3.113 qs_vxc_create 14 8.0 0.000 0.000 2.699 2.699 xc_vxc_pw_create 14 9.0 0.009 0.009 2.699 2.699 xc_rho_set_and_dset_create 14 10.0 0.012 0.014 2.105 2.219 ------------------------------------------------------------------------------- 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=18.98699999999998, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=95.92, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=3.421, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=3.391, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.91, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.956, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.242, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="H2O-hyb_timings_32mpi", title="Timings of H2O-hyb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32mpi", name="rest", label="rest", y=9.951999999999984, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=90.523, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=3.054, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=3.05, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.061, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.004, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.286, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=1.736, 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 0.017 0.017 98.238 98.238 qs_energies 1 2.0 0.000 0.000 97.773 97.773 mp2_main 1 3.0 0.000 0.000 94.105 94.105 mp2_gpw_main 1 4.0 0.000 0.000 93.979 93.979 rpa_ri_compute_en 1 5.0 0.000 0.000 89.889 89.889 rpa_num_int 1 6.0 0.001 0.001 89.882 89.882 compute_mat_P_omega 1 7.0 0.004 0.004 76.837 76.837 compute_mat_P_omega_contract 10 8.0 13.101 13.101 76.569 76.569 dbt_total 2336 9.6 0.021 0.021 55.834 55.834 dbt_contract 787 11.0 0.052 0.052 47.285 47.285 dbt_tas_total 1149 12.2 0.267 0.267 45.653 45.653 dbt_tas_multiply 807 12.1 0.002 0.002 44.248 44.248 dbt_tas_dbm 807 14.1 0.004 0.004 36.604 36.604 dbm_multiply 807 16.1 36.593 36.593 36.593 36.593 dbt_tas_mm_1N 524 15.1 0.002 0.002 27.372 27.372 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 24.874 24.874 compute_mat_P_omega_calc_M_occ 250 9.0 13.075 13.075 23.072 23.072 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.585 8.585 dbt_tas_mm_2 251 15.0 0.002 0.002 7.410 7.410 dbt_copy 1103 10.7 0.079 0.079 7.118 7.118 compute_QP_energies 1 7.0 0.000 0.000 6.891 6.891 compute_self_energy_cubic_gw 1 8.0 0.101 0.101 6.890 6.890 contract_cubic_gw 21 9.0 0.000 0.000 5.382 5.382 dbt_tas_reserve_blocks_index 3261 14.3 0.530 0.530 4.462 4.462 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 4.082 4.082 dbm_reserve_blocks 3628 15.3 4.016 4.016 4.016 4.016 scf_env_do_scf 1 3.0 0.000 0.000 3.537 3.537 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 3.537 3.537 dbt_reserve_blocks_index 2280 13.1 0.080 0.080 3.423 3.423 dbt_reserve_blocks_index_array 2222 12.2 0.011 0.011 3.356 3.356 dbt_crop 1042 12.0 1.823 1.823 2.890 2.890 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.848 2.848 dbt_tas_copy 574 11.4 1.603 1.603 2.675 2.675 dbt_reshape 278 11.9 1.556 1.556 2.595 2.595 convert_to_new_pgrid 2421 14.1 0.105 0.105 2.499 2.499 dbm_copy 1614 15.1 2.394 2.394 2.394 2.394 compute_W_cubic_GW 10 7.0 0.012 0.012 2.349 2.349 dbt_tas_reshape 367 15.0 0.008 0.008 2.329 2.329 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 2.090 2.090 ------------------------------------------------------------------------------- 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 0.008 0.036 43.079 43.093 qs_energies 1 2.0 0.000 0.000 42.859 42.861 mp2_main 1 3.0 0.000 0.001 41.662 41.665 mp2_gpw_main 1 4.0 0.000 0.000 41.619 41.621 rpa_ri_compute_en 1 5.0 0.000 0.000 40.029 40.032 rpa_num_int 1 6.0 0.000 0.002 40.028 40.031 dbt_total 2336 9.6 0.022 0.025 35.565 35.570 compute_mat_P_omega 1 7.0 0.001 0.007 34.511 34.532 compute_mat_P_omega_contract 10 8.0 0.523 0.560 34.335 34.343 dbt_contract 787 11.0 0.052 0.059 25.679 25.685 dbt_tas_total 1149 12.2 0.099 0.120 22.635 22.637 dbt_tas_multiply 807 12.1 0.003 0.003 22.579 22.582 dbt_tas_dbm 807 14.1 0.004 0.005 16.870 16.886 dbm_multiply 807 16.1 13.391 14.366 13.391 14.366 compute_mat_P_omega_calc_M_occ 250 9.0 0.492 0.523 10.262 10.262 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 9.802 9.803 dbt_copy 1149 10.8 0.018 0.021 8.584 9.014 dbt_reshape 1136 11.8 3.456 3.679 8.210 8.641 dbt_tas_mm_2 251 15.0 0.002 0.002 8.028 8.033 mp_sync 8688 11.6 6.194 7.905 6.194 7.905 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 6.952 6.953 dbt_tas_mm_1N 524 15.1 0.002 0.002 6.051 6.686 dbt_communicate_buffer 1136 12.8 0.061 0.066 3.568 3.816 mp_waitall_2 3812 15.3 3.517 3.780 3.517 3.780 compute_QP_energies 1 7.0 0.000 0.000 3.466 3.467 compute_self_energy_cubic_gw 1 8.0 0.003 0.004 3.464 3.465 dbt_reserve_blocks_index 2887 13.1 0.083 0.099 2.468 2.940 dbt_reserve_blocks_index_array 2829 12.2 0.010 0.013 2.454 2.922 dbt_tas_reserve_blocks_index 3347 14.5 0.498 0.539 2.448 2.915 contract_cubic_gw 21 9.0 0.000 0.000 2.685 2.685 dbm_reserve_blocks 3752 15.4 2.071 2.525 2.071 2.525 dbt_crop 1042 12.0 1.131 1.250 1.883 2.133 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 1.588 1.588 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.002 1.505 1.508 dbt_tas_replicate 405 14.1 0.650 0.845 1.347 1.431 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.374 1.377 convert_to_new_pgrid 2421 14.1 0.030 0.034 1.077 1.295 dbm_copy 1608 15.1 1.040 1.257 1.040 1.257 parallel_gemm_fm 105 8.4 0.000 0.000 1.210 1.218 parallel_gemm_fm_cosma 105 9.4 1.209 1.218 1.209 1.218 scf_env_do_scf 1 3.0 0.000 0.000 1.148 1.148 scf_env_do_scf_inner_loop 17 4.0 0.001 0.003 1.148 1.148 mp_max_i 2002 9.8 0.791 1.064 0.791 1.064 compute_W_cubic_GW 10 7.0 0.001 0.001 0.927 0.940 ------------------------------------------------------------------------------- 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=27.502999999999986, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=36.593, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=13.101, 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=13.075, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=4.016, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.394, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.556, 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=12.395000000000003, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=13.391, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.523, 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=0.492, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.071, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=1.04, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.456, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=6.194, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.517, 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 0.024 0.024 338.482 338.482 qs_forces 1 2.0 0.000 0.000 337.805 337.805 rebuild_ks_matrix 7 6.6 0.000 0.000 335.800 335.800 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 335.800 335.800 hfx_ks_matrix 7 8.6 0.000 0.000 333.380 333.380 hfx_ri_update_ks 7 9.6 0.000 0.000 289.372 289.372 hfx_ri_update_ks_Pmat 7 10.6 38.682 38.682 289.359 289.359 dbt_total 783 11.1 0.008 0.008 268.985 268.985 qs_energies 1 3.0 0.000 0.000 255.197 255.197 scf_env_do_scf 1 4.0 0.000 0.000 254.820 254.820 qs_ks_update_qs_env 8 6.0 0.000 0.000 253.263 253.263 dbt_contract 207 12.4 0.073 0.073 245.471 245.471 dbt_tas_total 317 14.0 2.326 2.326 242.183 242.183 dbt_tas_multiply 216 13.5 0.001 0.001 238.412 238.412 dbt_tas_dbm 216 15.5 0.001 0.001 226.877 226.877 dbm_multiply 216 17.5 226.873 226.873 226.873 226.873 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 219.841 219.841 dbt_tas_mm_2 91 16.5 0.001 0.001 209.097 209.097 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 160.887 160.887 init_scf_loop 2 5.0 0.000 0.000 93.930 93.930 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 82.543 82.543 hfx_ri_update_forces 1 7.0 1.705 1.705 44.003 44.003 hfx_ri_forces_Pmat_3c 1 8.0 4.981 4.981 23.974 23.974 dbt_copy 409 11.7 0.077 0.077 19.731 19.731 precalc_derivatives 1 8.0 2.310 2.310 15.301 15.301 dbt_reshape 132 13.2 8.808 8.808 13.788 13.788 dbt_tas_mm_3T 77 17.1 0.000 0.000 12.502 12.502 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 11.334 11.334 dbt_tas_reserve_blocks_index 1229 15.4 1.139 1.139 9.697 9.697 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 9.071 9.071 build_3c_derivatives 3 9.0 2.893 2.893 8.819 8.819 dbm_reserve_blocks 1345 16.4 8.714 8.714 8.714 8.714 dbt_reserve_blocks_index 818 14.4 0.152 0.152 7.691 7.691 dbt_reserve_blocks_index_array 795 13.4 0.009 0.009 7.570 7.570 ------------------------------------------------------------------------------- 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 0.009 0.031 59.877 59.888 qs_forces 1 2.0 0.000 0.000 59.682 59.682 rebuild_ks_matrix 7 6.6 0.000 0.000 58.813 58.814 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 58.813 58.814 hfx_ks_matrix 7 8.6 0.000 0.000 57.457 57.464 dbt_total 783 11.1 0.008 0.008 51.038 51.044 dbt_contract 207 12.4 0.030 0.032 39.178 39.192 hfx_ri_update_ks 7 9.6 0.000 0.000 34.824 34.824 hfx_ri_update_ks_Pmat 7 10.6 1.739 1.850 34.822 34.823 dbt_tas_total 317 14.0 0.052 0.067 34.423 34.424 dbt_tas_multiply 216 13.5 0.001 0.001 34.308 34.309 qs_energies 1 3.0 0.000 0.000 32.756 32.756 scf_env_do_scf 1 4.0 0.000 0.001 32.570 32.570 qs_ks_update_qs_env 8 6.0 0.000 0.000 31.902 31.903 dbt_tas_dbm 216 15.5 0.001 0.002 28.943 28.946 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 26.912 26.913 dbm_multiply 216 17.5 25.889 26.717 25.889 26.717 hfx_ri_update_forces 1 7.0 0.073 0.077 22.632 22.639 scf_env_do_scf_inner_loop 6 5.0 0.000 0.002 18.309 18.309 hfx_ri_forces_Pmat_3c 1 8.0 0.214 0.232 16.361 16.361 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 15.574 15.575 init_scf_loop 2 5.0 0.000 0.000 14.259 14.260 dbt_tas_mm_2 91 16.5 0.001 0.001 13.346 13.347 dbt_copy 497 12.3 0.015 0.018 11.068 11.561 dbt_reshape 365 13.6 4.705 4.873 8.562 8.884 dbt_tas_mm_3T 77 17.1 0.000 0.000 7.774 8.525 mp_sync 2665 13.0 5.736 8.132 5.736 8.132 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.330 6.330 dbt_tas_mm_3N 37 15.4 0.000 0.000 5.522 5.724 precalc_derivatives 1 8.0 0.097 0.103 4.801 4.801 dbt_tas_reserve_blocks_index 1356 15.8 1.028 1.096 3.965 4.527 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 4.385 4.385 dbt_reserve_blocks_index 1051 14.7 0.155 0.164 3.316 3.746 dbt_reserve_blocks_index_array 1028 13.8 0.006 0.006 3.281 3.703 dbm_reserve_blocks 1481 16.7 3.024 3.561 3.024 3.561 dbt_crop 372 13.7 2.345 2.417 3.312 3.487 mp_waitall_2 1138 16.4 2.739 2.846 2.739 2.846 build_3c_derivatives 3 9.0 0.270 0.291 2.731 2.741 dbt_communicate_buffer 365 14.6 0.013 0.014 2.435 2.545 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 2.373 2.380 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 2.209 2.210 convert_to_new_pgrid 648 15.5 0.050 0.103 1.696 1.868 dbt_tas_copy 132 12.5 0.830 0.889 1.583 1.785 dbm_copy 452 16.3 1.453 1.623 1.453 1.623 ------------------------------------------------------------------------------- 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=50.424000000000035, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=226.873, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=38.682, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=8.808, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=8.714, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.981, 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=15.83100000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=25.889, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.739, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=4.705, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.024, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.214, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=5.736, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.739, 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 0.019 0.019 200.130 200.130 qs_energies 1 2.0 0.000 0.000 199.916 199.916 mp2_main 1 3.0 0.000 0.000 194.198 194.198 mp2_gpw_main 1 4.0 0.001 0.001 193.712 193.712 mp2_ri_gpw_compute_in 1 5.0 0.429 0.429 141.275 141.275 mp2_ri_gpw_compute_in_loop 1 6.0 0.019 0.019 131.224 131.224 mp2_eri_3c_integrate_gpw 2656 7.0 0.022 0.022 93.892 93.892 integrate_v_rspace 2666 8.0 0.860 0.860 79.519 79.519 grid_integrate_task_list 2666 9.0 76.401 76.401 76.401 76.401 mp2_ri_gpw_compute_en 1 5.0 0.095 0.095 52.407 52.407 mp2_ri_gpw_compute_en_RI_loop 1 6.0 10.532 10.532 50.407 50.407 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.982 2.982 30.883 30.883 local_gemm 2080 8.0 27.901 27.901 27.901 27.901 dbcsr_multiply_generic 5322 8.0 0.253 0.253 25.590 25.590 ao_to_mo_and_store_B_mult_1 2656 7.0 0.015 0.015 25.571 25.571 multiply_cannon 5322 9.0 0.632 0.632 13.199 13.199 calculate_wavefunction 2656 8.0 8.942 8.942 12.885 12.885 pw_transfer 63872 10.6 1.163 1.163 12.720 12.720 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 3.140 3.140 11.634 11.634 multiply_cannon_loop 5322 10.0 0.167 0.167 11.448 11.448 fft_wrap_pw1pw2 53228 11.4 0.130 0.130 11.304 11.304 multiply_cannon_multrec 5322 11.0 9.746 9.746 9.799 9.799 make_m2s 10644 9.0 0.080 0.080 9.650 9.650 get_2c_integrals 1 6.0 0.000 0.000 9.620 9.620 make_images 10644 10.0 3.643 3.643 9.190 9.190 copy_dbcsr_to_fm 2679 8.0 0.037 0.037 9.112 9.112 compute_2c_integrals 1 7.0 0.006 0.006 8.556 8.556 compute_2c_integrals_loop_lm 1 8.0 0.014 0.014 8.543 8.543 mp2_eri_2c_integrate_gpw 1 9.0 1.006 1.006 8.529 8.529 fft_wrap_pw1pw2_20 21271 12.4 0.537 0.537 7.908 7.908 dbcsr_complete_redistribute 2689 9.0 1.534 1.534 7.074 7.074 fft3d_s 53229 13.4 6.790 6.790 6.837 6.837 mp2_ri_gpw_compute_en_ener 2080 7.0 6.691 6.691 6.691 6.691 dbcsr_finalize 10708 9.5 0.181 0.181 6.187 6.187 dbcsr_merge_all 8011 10.3 3.793 3.793 5.448 5.448 scf_env_do_scf 1 3.0 0.000 0.000 5.268 5.268 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 5.268 5.268 potential_pw2rs 5322 10.0 0.191 0.191 4.455 4.455 ------------------------------------------------------------------------------- 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 0.008 0.033 42.886 42.896 qs_energies 1 2.0 0.000 0.000 42.734 42.735 mp2_main 1 3.0 0.000 0.001 40.486 40.487 mp2_gpw_main 1 4.0 0.001 0.002 40.376 40.376 mp2_ri_gpw_compute_in 1 5.0 0.058 0.059 20.833 21.120 mp2_ri_gpw_compute_en 1 5.0 0.200 0.213 19.442 19.661 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 19.350 19.639 mp2_ri_gpw_compute_en_RI_loop 1 6.0 1.868 2.143 18.311 18.332 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 16.824 17.026 integrate_v_rspace 93 8.1 0.122 0.137 16.667 16.874 grid_integrate_task_list 93 9.1 16.305 16.518 16.305 16.518 mp2_ri_gpw_compute_en_expansio 65 7.0 0.134 0.165 12.700 12.902 local_gemm 65 8.0 12.566 12.799 12.566 12.799 mp2_ri_gpw_compute_en_comm 20 7.0 0.090 0.111 3.292 3.943 mp_sendrecv_dm3 1240 8.0 2.622 3.432 2.622 3.432 dbcsr_multiply_generic 176 8.0 0.009 0.010 2.168 2.319 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 2.148 2.302 scf_env_do_scf 1 3.0 0.000 0.000 2.102 2.103 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 2.102 2.102 get_2c_integrals 1 6.0 0.004 0.012 1.405 1.430 multiply_cannon 176 9.0 0.020 0.023 1.265 1.308 multiply_cannon_loop 176 10.0 0.002 0.003 1.195 1.234 multiply_cannon_multrec 246 11.0 1.020 1.050 1.027 1.057 compute_2c_integrals 1 7.0 0.003 0.004 1.039 1.055 make_m2s 352 9.0 0.003 0.004 0.857 0.974 make_images 352 10.0 0.062 0.063 0.842 0.959 qs_scf_new_mos 10 5.0 0.000 0.000 0.948 0.955 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.909 0.950 mp2_eri_2c_integrate_gpw 1 9.0 0.241 0.260 0.907 0.949 pw_transfer 2120 10.5 0.055 0.060 0.913 0.927 eigensolver 11 5.8 0.001 0.001 0.890 0.892 ------------------------------------------------------------------------------- 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=66.608, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=76.401, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=27.901, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=10.532, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=9.746, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.942, 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=8.505000000000003, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=16.305, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=12.566, 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=1.868, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=1.02, 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="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=2.622, 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 0.099 0.099 132.220 132.220 qs_energies 1 2.0 0.000 0.000 130.660 130.660 scf_env_do_scf 1 3.0 0.000 0.000 122.860 122.860 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 122.860 122.860 qs_ks_update_qs_env 15 5.0 0.000 0.000 52.420 52.420 rebuild_ks_matrix 15 6.0 0.000 0.000 52.208 52.208 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 52.208 52.208 qs_scf_new_mos 15 5.0 0.000 0.000 44.185 44.185 eigensolver 15 6.0 0.002 0.002 36.365 36.365 qs_vxc_create 15 8.0 0.025 0.025 35.835 35.835 calculate_dispersion_nonloc 15 9.0 6.927 6.927 31.161 31.161 pw_transfer 1191 10.0 0.063 0.063 25.333 25.333 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 25.149 25.149 qs_rho_update_rho_low 16 5.0 0.000 0.000 23.513 23.513 calculate_rho_elec 16 6.0 0.216 0.216 23.512 23.512 cp_fm_diag_elpa 15 7.0 0.000 0.000 23.076 23.076 cp_fm_diag_elpa_base 15 8.0 20.511 20.511 23.075 23.075 grid_collocate_task_list 16 7.0 22.061 22.061 22.061 22.061 fft_wrap_pw1pw2_150 765 12.0 3.828 3.828 18.353 18.353 sum_up_and_integrate 15 8.0 0.158 0.158 15.084 15.084 integrate_v_rspace 15 9.0 0.018 0.018 14.926 14.926 grid_integrate_task_list 15 10.0 14.377 14.377 14.377 14.377 fft3d_s 1087 13.0 11.269 11.269 11.278 11.278 cp_fm_cholesky_restore 45 7.0 10.994 10.994 10.994 10.994 pw_scatter_s 585 13.1 7.794 7.794 7.794 7.794 fft_wrap_pw1pw2_200 197 12.3 0.867 0.867 6.606 6.606 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.620 5.620 dbcsr_complete_redistribute 46 8.3 2.250 2.250 5.558 5.558 cp_fm_upper_to_full 30 8.0 4.858 4.858 4.858 4.858 xc_vxc_pw_create 15 9.0 0.218 0.218 4.649 4.649 vdW_energy 15 10.0 4.485 4.485 4.485 4.485 gspace_mixing 14 5.0 0.171 0.171 4.246 4.246 init_scf_run 1 3.0 0.000 0.000 3.753 3.753 broyden_mixing 14 6.0 3.579 3.579 3.579 3.579 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.515 3.515 xc_pw_derive 90 11.0 0.001 0.001 3.115 3.115 ------------------------------------------------------------------------------- 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 0.018 0.036 72.917 72.927 qs_energies 1 2.0 0.000 0.000 72.548 72.554 scf_env_do_scf 1 3.0 0.000 0.001 67.639 67.639 scf_env_do_scf_inner_loop 15 4.0 0.001 0.004 67.638 67.639 qs_ks_update_qs_env 15 5.0 0.000 0.000 29.814 29.822 rebuild_ks_matrix 15 6.0 0.000 0.000 29.774 29.784 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 29.774 29.783 qs_rho_update_rho_low 16 5.0 0.000 0.000 24.780 24.793 calculate_rho_elec 16 6.0 0.008 0.010 24.780 24.793 grid_collocate_task_list 16 7.0 23.304 23.481 23.304 23.481 sum_up_and_integrate 15 8.0 0.019 0.023 16.644 16.712 integrate_v_rspace 15 9.0 0.001 0.001 16.626 16.700 grid_integrate_task_list 15 10.0 15.638 15.773 15.638 15.773 qs_scf_new_mos 15 5.0 0.000 0.001 13.793 13.832 qs_vxc_create 15 8.0 0.001 0.001 12.716 12.728 eigensolver 15 6.0 0.002 0.002 12.651 12.711 pw_transfer 1191 10.0 0.104 0.116 10.251 10.387 fft_wrap_pw1pw2 1086 11.0 0.014 0.016 10.039 10.194 calculate_dispersion_nonloc 15 9.0 1.058 1.088 10.151 10.179 cp_fm_diag_elpa 15 7.0 0.000 0.001 8.927 8.930 cp_fm_diag_elpa_base 15 8.0 8.755 8.786 8.923 8.926 fft3d_ps 1086 13.0 3.357 3.684 6.745 7.389 fft_wrap_pw1pw2_150 765 12.0 0.907 1.055 6.508 6.552 mp_alltoall_z22v 1086 15.0 2.670 3.832 2.670 3.832 cp_fm_cholesky_restore 45 7.0 3.528 3.582 3.528 3.582 fft_wrap_pw1pw2_200 197 12.3 0.616 0.769 3.398 3.478 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.931 2.931 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.586 2.810 xc_vxc_pw_create 15 9.0 0.019 0.029 2.565 2.616 x_to_yz 585 14.1 0.417 0.442 1.745 2.269 yz_to_x 501 13.9 0.270 0.321 1.612 2.223 xc_pw_derive 90 11.0 0.001 0.001 1.790 1.887 init_scf_run 1 3.0 0.000 0.001 1.716 1.718 build_core_ppnl 1 5.0 1.524 1.662 1.524 1.662 vdW_energy 15 10.0 1.542 1.614 1.542 1.614 scf_env_initial_rho_setup 1 4.0 0.000 0.002 1.599 1.600 ------------------------------------------------------------------------------- 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=53.007999999999996, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.061, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.511, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.377, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=11.269, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.994, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=18.335000000000008, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=23.304, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.755, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=15.638, 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=3.528, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=3.357, 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 0.074 0.074 294.563 294.563 qs_energies 1 2.0 0.000 0.000 294.427 294.427 ls_scf 1 3.0 0.000 0.000 293.180 293.180 ls_scf_main 1 4.0 0.002 0.002 283.816 283.816 density_matrix_trs4 11 5.0 0.013 0.013 180.395 180.395 ls_scf_dm_to_ks 11 5.0 0.000 0.000 97.317 97.317 matrix_ls_to_qs 11 6.0 0.000 0.000 93.767 93.767 dbcsr_multiply_generic 185 6.1 0.958 0.958 82.311 82.311 arnoldi_extremal 12 6.1 0.000 0.000 81.592 81.592 arnoldi_normal_ev 12 7.1 0.053 0.053 81.591 81.591 build_subspace 23 8.1 0.086 0.086 80.111 80.111 dbcsr_matrix_vector_mult 652 9.0 0.282 0.282 79.692 79.692 dbcsr_matrix_vector_mult_local 652 10.0 78.031 78.031 78.041 78.041 dbcsr_copy_into_existing 11 7.0 49.222 49.222 49.222 49.222 dbcsr_complete_redistribute 23 7.5 34.904 34.904 48.826 48.826 multiply_cannon 185 7.1 0.422 0.422 47.144 47.144 matrix_decluster 11 7.0 0.000 0.000 44.543 44.543 multiply_cannon_loop 185 8.1 0.254 0.254 33.980 33.980 make_m2s 370 7.1 0.040 0.040 29.828 29.828 make_images 370 8.1 13.220 13.220 27.274 27.274 multiply_cannon_multrec 185 9.1 24.172 24.172 24.220 24.220 dbcsr_finalize 646 7.5 0.256 0.256 18.273 18.273 dbcsr_merge_all 597 8.5 2.885 2.885 16.970 16.970 setup_rec_index_2d 370 8.1 12.632 12.632 12.632 12.632 tree_to_linear_d 110 9.4 12.479 12.479 12.479 12.479 dbcsr_sort_indices 1103 9.9 11.948 11.948 11.948 11.948 quick_finalize 395 10.0 0.461 0.461 10.365 10.365 dbcsr_special_finalize 370 9.1 0.002 0.002 9.596 9.596 calculate_norms 370 9.1 9.506 9.506 9.506 9.506 ls_scf_init_scf 1 4.0 0.000 0.000 8.651 8.651 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.319 8.319 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.661 7.661 dbcsr_dot_sd 144 6.3 7.514 7.514 7.515 7.515 matrix_qs_to_ls 12 5.1 0.000 0.000 6.274 6.274 matrix_cluster 12 6.1 0.000 0.000 6.274 6.274 dbcsr_frobenius_norm 142 6.1 6.088 6.088 6.090 6.090 ------------------------------------------------------------------------------- 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 0.008 0.021 65.439 65.449 qs_energies 1 2.0 0.000 0.000 65.319 65.319 ls_scf 1 3.0 0.000 0.000 65.267 65.268 ls_scf_main 1 4.0 0.000 0.007 62.617 62.618 density_matrix_trs4 11 5.0 0.006 0.018 60.193 60.244 dbcsr_multiply_generic 185 6.1 0.057 0.075 57.031 57.239 multiply_cannon 185 7.1 0.033 0.036 47.431 47.851 multiply_cannon_loop 185 8.1 0.107 0.131 45.057 45.362 multiply_cannon_multrec 1480 9.1 27.646 30.437 27.901 30.708 mp_waitall_1 11936 10.3 15.060 19.164 15.060 19.164 multiply_cannon_metrocomm3 1480 9.1 0.012 0.015 8.648 15.084 multiply_cannon_metrocomm1 1480 9.1 0.007 0.010 3.680 7.339 make_m2s 370 7.1 0.034 0.037 6.687 6.798 make_images 370 8.1 0.626 0.658 6.556 6.667 calculate_norms 2960 9.1 4.659 5.537 4.659 5.537 make_images_data 370 9.1 0.008 0.010 2.964 3.241 hybrid_alltoall_any 393 9.9 0.183 0.845 2.573 2.894 mp_sum_l 1119 5.6 1.909 2.569 1.909 2.569 arnoldi_extremal 12 6.1 0.000 0.000 2.438 2.452 arnoldi_normal_ev 12 7.1 0.001 0.007 2.437 2.452 build_subspace 23 8.1 0.019 0.023 2.330 2.332 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.094 2.195 dbcsr_matrix_vector_mult 652 9.0 0.013 0.048 1.985 2.082 ls_scf_init_scf 1 4.0 0.000 0.000 2.055 2.056 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.031 2.036 dbcsr_complete_redistribute 23 7.5 1.166 1.207 1.879 1.956 matrix_ls_to_qs 11 6.0 0.000 0.000 1.829 1.913 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.868 1.870 make_images_pack 370 9.1 1.616 1.863 1.619 1.867 matrix_decluster 11 7.0 0.000 0.000 1.689 1.771 dbcsr_matrix_vector_mult_local 652 10.0 1.629 1.709 1.631 1.710 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.039 1.589 buffer_matrices_ensure_size 370 8.1 1.259 1.504 1.259 1.504 dbcsr_finalize 646 7.5 0.007 0.009 1.316 1.473 ------------------------------------------------------------------------------- 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=85.50799999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=78.031, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=49.222, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=34.904, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=24.172, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images", label="make_images", y=13.22, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.506, 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=12.743999999999986, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.629, 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=1.166, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=27.646, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images", label="make_images", y=0.626, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.659, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.909, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=15.06, 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 0.008 0.008 74.568 74.568 lib_test 1 2.0 0.000 0.000 74.560 74.560 dbcsr_run_tests 3 3.0 0.002 0.002 74.560 74.560 test_multiplies_multiproc 3 4.0 0.001 0.001 58.339 58.339 dbcsr_redistribute 9 5.0 38.385 38.385 40.023 40.023 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.931 16.931 dbcsr_make_random_matrix 9 4.0 13.065 13.065 16.107 16.107 multiply_cannon 9 6.0 0.002 0.002 12.052 12.052 multiply_cannon_loop 9 7.0 0.031 0.031 11.692 11.692 multiply_cannon_multrec 9 8.0 11.661 11.661 11.662 11.662 dbcsr_finalize 27 5.7 0.018 0.018 5.645 5.645 dbcsr_merge_all 18 6.5 2.054 2.054 4.893 4.893 dbcsr_data_release 975 7.6 2.899 2.899 2.899 2.899 tree_to_linear_d 9 7.0 1.967 1.967 1.967 1.967 make_m2s 18 6.0 0.001 0.001 1.691 1.691 make_images 18 7.0 0.581 0.581 1.637 1.637 ------------------------------------------------------------------------------- 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 0.011 18.170 18.174 lib_test 1 2.0 0.000 0.000 18.142 18.161 dbcsr_run_tests 3 3.0 0.000 0.001 18.141 18.160 test_multiplies_multiproc 3 4.0 0.000 0.002 17.293 17.355 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.937 16.032 multiply_cannon 9 6.0 0.001 0.002 14.139 14.451 multiply_cannon_loop 9 7.0 0.002 0.002 13.836 14.177 multiply_cannon_multrec 72 8.0 11.585 12.144 11.585 12.145 mp_waitall_1 576 9.2 2.582 3.302 2.582 3.302 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.994 2.775 mp_sum_l 390 2.5 0.393 0.954 0.393 0.954 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.390 0.950 dbcsr_data_release 444 7.6 0.758 0.865 0.758 0.865 dbcsr_finalize 27 5.7 0.000 0.000 0.716 0.859 dbcsr_make_random_matrix 9 4.0 0.668 0.676 0.815 0.855 make_m2s 18 6.0 0.001 0.001 0.713 0.755 make_images 18 7.0 0.021 0.023 0.709 0.752 dbcsr_destroy 111 5.9 0.000 0.000 0.602 0.745 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.249 0.664 dbcsr_merge_all 18 6.5 0.106 0.129 0.559 0.645 dbcsr_redistribute 9 5.0 0.242 0.284 0.419 0.450 make_images_data 18 8.0 0.000 0.001 0.373 0.416 dbcsr_data_copy_aa2 18 7.5 0.332 0.397 0.332 0.397 hybrid_alltoall_any 18 9.0 0.031 0.136 0.328 0.372 ------------------------------------------------------------------------------- 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=6.504000000000005, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=38.385, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.065, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.661, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.899, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.054, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=1.836000000000002, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.242, 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=11.585, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.758, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.106, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.393, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.582, 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 0.061 0.061 142.083 142.083 qs_mol_dyn_low 1 2.0 0.004 0.004 140.600 140.600 velocity_verlet 5 3.0 0.004 0.004 115.137 115.137 qmmm_el_coupling 6 3.8 0.000 0.000 88.481 88.481 qmmm_elec_with_gaussian 6 4.8 0.031 0.031 88.477 88.477 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.522 87.522 qmmm_elec_gaussian_low_G 6 6.8 86.619 86.619 86.619 86.619 qs_forces 6 3.8 0.001 0.001 42.780 42.780 qs_energies 6 4.8 0.000 0.000 37.849 37.849 scf_env_do_scf 6 5.8 0.001 0.001 35.338 35.338 rebuild_ks_matrix 45 8.4 0.000 0.000 30.996 30.996 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 30.996 30.996 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 30.849 30.849 qs_ks_update_qs_env 45 7.8 0.000 0.000 26.540 26.540 pw_transfer 966 12.3 0.055 0.055 18.463 18.463 fft_wrap_pw1pw2 801 13.6 0.006 0.006 18.217 18.217 fft_wrap_pw1pw2_150 507 15.2 2.668 2.668 17.837 17.837 qs_vxc_create 45 10.4 0.001 0.001 15.475 15.475 xc_vxc_pw_create 45 11.4 0.748 0.748 15.475 15.475 xc_pw_derive 270 13.4 0.002 0.002 10.139 10.139 xc_rho_set_and_dset_create 45 12.4 1.252 1.252 8.531 8.531 fft3d_s 802 15.6 7.974 7.974 7.982 7.982 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.773 7.773 calculate_rho_elec 45 8.9 0.654 0.654 7.773 7.773 pw_integral_ab 2539 7.4 7.565 7.565 7.565 7.565 qmmm_forces 6 3.8 0.003 0.003 6.202 6.202 pw_scatter_s 429 15.8 6.163 6.163 6.163 6.163 xc_pw_divergence 45 12.4 0.001 0.001 6.125 6.125 qmmm_forces_with_gaussian 6 4.8 0.044 0.044 5.798 5.798 qs_ks_ddapc 45 10.4 0.001 0.001 5.491 5.491 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.586 4.586 init_scf_loop 6 6.8 0.000 0.000 4.481 4.481 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 4.473 4.473 sum_up_and_integrate 45 10.4 0.956 0.956 4.251 4.251 pw_poisson_solve 51 9.9 0.953 0.953 3.871 3.871 qmmm_forces_gaussian_low_G 6 6.8 3.815 3.815 3.815 3.815 cp_ddapc_apply_CD 45 11.4 0.006 0.006 3.730 3.730 density_rs2pw 45 9.9 0.002 0.002 3.639 3.639 grid_collocate_task_list 45 9.9 3.480 3.480 3.480 3.480 integrate_v_rspace 45 11.4 0.006 0.006 3.295 3.295 ------------------------------------------------------------------------------- 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 0.043 0.062 59.510 59.524 qs_mol_dyn_low 1 2.0 0.003 0.004 58.396 58.456 qs_forces 6 3.8 0.001 0.001 42.799 42.799 qs_energies 6 4.8 0.000 0.001 40.867 40.867 scf_env_do_scf 6 5.8 0.000 0.001 39.874 39.875 scf_env_do_scf_inner_loop 113 6.2 0.003 0.020 38.288 38.289 rebuild_ks_matrix 119 8.1 0.000 0.000 28.533 28.541 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.017 28.532 28.541 qs_ks_update_qs_env 119 7.3 0.001 0.001 26.904 26.913 velocity_verlet 5 3.0 0.002 0.004 24.386 24.389 pw_transfer 2446 12.3 0.190 0.212 20.496 20.975 fft_wrap_pw1pw2 2059 13.4 0.022 0.027 20.086 20.597 fft_wrap_pw1pw2_150 1321 14.9 3.083 3.617 19.404 19.931 qs_vxc_create 119 10.1 0.002 0.003 15.508 15.510 xc_vxc_pw_create 119 11.1 0.147 0.197 15.505 15.508 fft3d_ps 2059 15.4 7.296 8.186 13.416 14.965 xc_pw_derive 714 13.1 0.009 0.011 11.964 12.220 qs_rho_update_rho_low 119 7.3 0.001 0.001 11.278 11.279 calculate_rho_elec 119 8.3 0.050 0.057 11.278 11.278 sum_up_and_integrate 119 10.1 0.073 0.085 9.500 9.518 integrate_v_rspace 119 11.1 0.003 0.004 9.428 9.448 xc_pw_divergence 119 12.1 0.004 0.005 7.736 7.972 qmmm_forces 6 3.8 0.002 0.002 7.877 7.878 qmmm_forces_with_gaussian 6 4.8 0.007 0.012 7.281 7.765 xc_rho_set_and_dset_create 119 12.1 0.325 0.400 7.384 7.553 qmmm_el_coupling 6 3.8 0.000 0.000 6.787 6.949 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 6.785 6.947 density_rs2pw 119 9.3 0.006 0.007 6.444 6.630 mp_alltoall_z22v 2059 17.4 4.781 6.611 4.781 6.611 rs_pw_transfer 988 11.5 0.011 0.013 6.267 6.497 potential_pw2rs 119 12.1 0.006 0.007 5.540 5.559 grid_collocate_task_list 119 9.3 4.621 4.862 4.621 4.862 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.136 4.464 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.564 4.029 x_to_yz 1095 16.8 0.770 0.852 3.321 4.020 yz_to_x 964 16.0 0.511 0.623 2.742 3.816 grid_integrate_task_list 119 12.1 3.611 3.815 3.611 3.815 qmmm_forces_gaussian_low_G 6 6.8 3.403 3.738 3.403 3.738 qmmm_elec_gaussian_low_G 6 6.8 2.966 3.429 2.966 3.429 mp_waitany 4028 12.8 2.374 2.763 2.374 2.763 pw_restrict_s3 18 5.8 1.411 1.475 2.503 2.724 rs_pw_transfer_PW2RS_150 125 13.9 0.691 0.826 2.337 2.389 pw_gather_p 964 15.0 1.969 2.354 1.969 2.354 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.092 2.253 pw_prolongate_s3 18 6.8 1.182 1.235 2.092 2.253 qs_ks_ddapc 119 10.1 0.002 0.003 2.137 2.232 qs_scf_new_mos 113 7.2 0.000 0.001 2.067 2.072 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.067 2.072 rs_pw_transfer_RS2PW_150 125 11.2 0.539 0.681 1.791 2.051 ot_scf_mini 113 9.2 0.001 0.001 1.983 1.987 dbcsr_multiply_generic 2588 12.3 0.058 0.066 1.855 1.905 mp_sum_dm3 33 5.7 1.669 1.741 1.669 1.741 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.638 1.638 pw_scatter_p 1095 15.8 1.550 1.629 1.550 1.629 init_scf_loop 6 6.8 0.000 0.000 1.584 1.584 pw_integral_ab 2761 7.7 1.106 1.257 1.455 1.568 mp_sum_d 5822 12.2 0.942 1.407 0.942 1.407 mp_waitall_1 177795 16.4 1.155 1.271 1.155 1.271 ot_mini 113 10.2 0.000 0.001 1.207 1.212 ------------------------------------------------------------------------------- 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=26.467, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.619, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.974, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=7.565, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=6.163, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.815, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.48, 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="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 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=31.726, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.966, 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_integral_ab", label="pw_integral_ab", y=1.106, 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="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.403, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.621, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.296, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.781, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.611, yerr=0.0 Summary: Performance test took 37 minutes. Status: OK #48 DONE 2770.7s #49 preparing layers for inline cache #49 DONE 7.8s #50 exporting to image #50 exporting layers done #50 writing image sha256:52b5b5a4f74e69ec0c0dd4e17ab1e2a966e888a99dbc3fb25dcc0495f682cb74 done #50 naming to us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master done #50 DONE 0.0s #51 pushing us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master with docker #51 DONE 118.0s #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2023-04-27 20:02:20+00:00