StartDate: 2022-12-21 11:05:50+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 219e4046ece0941c566644462ddbee8fb2b94c92 CommitTime: 2022-12-21 11:02:53 +0100 CommitAuthor: Dr. Mathieu Taillefumier CommitSubject: Updating SIRIUS to latest version Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=219e4046ece0941c566644462ddbee8fb2b94c92 Sending build context to Docker daemon 366.7MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 6e3729cf69e0: Already exists Digest: sha256:27cb6e6ccef575a4698b66f5de06c7ecd61589132d5a91d098f7f3f9285415a9 Status: Downloaded newer image for ubuntu:22.04 ---> 6b7dfa7e8fdb Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> e98199835f6f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> ccd07bf8588a Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 0aa7ad9d2809 Step 5/42 : RUN mkdir scripts ---> Using cache ---> e9459f85bb88 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 ---> 47c0caf3dab5 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 19088ac45e1f Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 92805a05cd8b Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> f79915edd4c8 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 772a9d69903e Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> c5eaee8dccc0 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 5b71e8004021 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 3e1c7ddbc73d Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 7ae95cc24b0b Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> e8f67edf91da Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 4eee74a8c872 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 5390ddc9be55 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> ae1ade2dccf8 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> cc11c0aadd10 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 2095a1bc093b Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> b379c6349643 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 7b01d219c96c Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 9c8219606e8b Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 8f190ee94a76 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 1124eb2cf2ae Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 3dd7ca9afd06 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 5b7fe05b22eb Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 8593079993b3 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> c4e3c82156a3 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 9c4844c40523 Step 31/42 : COPY ./src ./src ---> Using cache ---> c1106981c0bd Step 32/42 : COPY ./exts ./exts ---> Using cache ---> e0feb3f108bc Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> e2340122fd4d 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 4a0dd0f2c9fb './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 4a0dd0f2c9fb ---> 83f88df2ae36 Step 35/42 : COPY ./data ./data ---> 266e3e0944f2 Step 36/42 : COPY ./tests ./tests ---> 12e7c102d093 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> dc4e78f82ba9 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 40fbd6b0267f Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> a9cd58c4132c Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 5dbb0a5d6b6f ========== 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 0.031 0.031 85.670 85.670 qs_mol_dyn_low 1 2.0 0.003 0.003 85.077 85.077 qs_forces 11 3.9 0.001 0.001 85.037 85.037 qs_energies 11 4.9 0.001 0.001 79.156 79.156 scf_env_do_scf 11 5.9 0.001 0.001 68.760 68.760 velocity_verlet 10 3.0 0.002 0.002 55.514 55.514 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 52.725 52.725 rebuild_ks_matrix 119 8.3 0.001 0.001 19.727 19.727 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 19.727 19.727 qs_scf_new_mos 108 7.5 0.001 0.001 19.516 19.516 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.515 19.515 dbcsr_multiply_generic 2286 12.5 0.157 0.157 19.286 19.286 qs_rho_update_rho_low 119 7.7 0.001 0.001 18.768 18.768 calculate_rho_elec 119 8.7 0.945 0.945 18.767 18.767 ot_scf_mini 108 9.5 0.002 0.002 18.182 18.182 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.099 18.099 init_scf_loop 11 6.9 0.000 0.000 15.887 15.887 grid_collocate_task_list 119 9.7 14.384 14.384 14.384 14.384 prepare_preconditioner 11 7.9 0.000 0.000 13.486 13.486 make_preconditioner 11 8.9 0.000 0.000 13.486 13.486 sum_up_and_integrate 119 10.3 0.502 0.502 12.676 12.676 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.377 12.377 integrate_v_rspace 119 11.3 0.085 0.085 12.173 12.173 ot_mini 108 10.5 0.001 0.001 12.021 12.021 make_m2s 4572 13.5 0.044 0.044 10.777 10.777 grid_integrate_task_list 119 12.3 10.296 10.296 10.296 10.296 qs_ot_get_derivative 108 11.5 0.001 0.001 6.481 6.481 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.080 6.080 pw_transfer 1439 11.6 0.060 0.060 5.959 5.959 dbcsr_make_dense_low 5837 15.5 0.084 0.084 5.949 5.949 make_dense_data 5837 16.5 5.273 5.273 5.851 5.851 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.746 5.746 ot_diis_step 108 11.5 0.004 0.004 5.537 5.537 make_images 4572 14.5 2.124 2.124 5.306 5.306 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.191 5.191 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.031 5.031 apply_single 119 13.6 0.000 0.000 5.031 5.031 fft_wrap_pw1pw2_140 487 13.2 0.430 0.430 4.929 4.929 multiply_cannon 2286 13.5 0.170 0.170 4.653 4.653 cp_fm_cholesky_decompose 22 10.9 4.295 4.295 4.295 4.295 multiply_cannon_loop 2286 14.5 0.062 0.062 4.208 4.208 multiply_cannon_multrec 2286 15.5 4.089 4.089 4.145 4.145 cp_fm_cholesky_invert 11 10.9 4.008 4.008 4.008 4.008 init_scf_run 11 5.9 0.002 0.002 3.709 3.709 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.707 3.707 dbcsr_complete_redistribute 329 12.2 1.891 1.891 3.687 3.687 dbcsr_copy 2102 12.0 0.235 0.235 3.512 3.512 density_rs2pw 119 9.7 0.004 0.004 3.439 3.439 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.314 3.314 dbcsr_copy_into_existing 22 7.9 3.243 3.243 3.243 3.243 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.234 3.234 wfi_extrapolate 11 7.9 0.001 0.001 3.191 3.191 copy_dbcsr_to_fm 153 11.3 0.002 0.002 3.002 3.002 fft3d_s 1202 14.6 2.886 2.886 2.890 2.890 qs_create_task_list 11 7.9 0.000 0.000 2.875 2.875 generate_qs_task_list 11 8.9 1.962 1.962 2.875 2.875 qs_ot_get_p 119 10.4 0.001 0.001 2.808 2.808 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.565 2.565 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.439 2.439 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.286 2.286 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 2.239 2.239 dbcsr_data_release 279534 16.0 2.152 2.152 2.152 2.152 pw_poisson_solve 119 10.3 0.330 0.330 1.993 1.993 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.895 1.895 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.839 1.839 potential_pw2rs 119 12.3 0.045 0.045 1.793 1.793 cp_fm_upper_to_full 72 14.2 1.740 1.740 1.740 1.740 dbcsr_finalize 5186 13.8 0.109 0.109 1.733 1.733 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.021 42.559 42.568 qs_mol_dyn_low 1 2.0 0.003 0.004 42.455 42.459 qs_forces 11 3.9 0.001 0.001 42.415 42.416 qs_energies 11 4.9 0.001 0.001 39.635 39.637 scf_env_do_scf 11 5.9 0.000 0.002 36.348 36.348 scf_env_do_scf_inner_loop 108 6.5 0.003 0.017 33.534 33.534 velocity_verlet 10 3.0 0.001 0.003 25.455 25.457 rebuild_ks_matrix 119 8.3 0.000 0.001 15.379 15.459 qs_ks_build_kohn_sham_matrix 119 9.3 0.014 0.017 15.378 15.458 qs_ks_update_qs_env 119 7.6 0.001 0.001 13.678 13.751 dbcsr_multiply_generic 2286 12.5 0.069 0.075 12.680 12.842 qs_rho_update_rho_low 119 7.7 0.000 0.001 12.479 12.486 calculate_rho_elec 119 8.7 0.029 0.031 12.479 12.486 sum_up_and_integrate 119 10.3 0.027 0.031 11.402 11.434 integrate_v_rspace 119 11.3 0.004 0.005 11.375 11.408 qs_scf_new_mos 108 7.5 0.001 0.001 9.926 10.013 qs_scf_loop_do_ot 108 8.5 0.001 0.001 9.925 10.012 multiply_cannon 2286 13.5 0.146 0.167 9.466 9.810 ot_scf_mini 108 9.5 0.002 0.002 9.312 9.407 multiply_cannon_loop 2286 14.5 0.090 0.105 8.980 9.326 grid_collocate_task_list 119 9.7 8.802 9.106 8.802 9.106 grid_integrate_task_list 119 12.3 7.929 8.131 7.929 8.131 mp_waitall_1 158411 16.6 7.399 8.025 7.399 8.025 multiply_cannon_metrocomm3 18288 15.5 0.036 0.040 5.336 6.037 ot_mini 108 10.5 0.001 0.001 5.402 5.509 rs_pw_transfer 974 11.9 0.010 0.012 4.014 4.384 density_rs2pw 119 9.7 0.005 0.006 3.348 3.702 pw_transfer 1439 11.6 0.095 0.116 3.102 3.166 multiply_cannon_multrec 18288 15.5 2.838 3.052 2.847 3.062 fft_wrap_pw1pw2 1201 12.6 0.008 0.010 2.942 2.991 potential_pw2rs 119 12.3 0.006 0.007 2.945 2.966 qs_ot_get_derivative 108 11.5 0.001 0.001 2.764 2.861 init_scf_loop 11 6.9 0.000 0.000 2.802 2.802 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.566 2.657 apply_single 119 13.6 0.000 0.000 2.566 2.657 ot_diis_step 108 11.5 0.003 0.003 2.617 2.617 fft_wrap_pw1pw2_140 487 13.2 0.245 0.293 2.495 2.601 init_scf_run 11 5.9 0.000 0.004 2.328 2.328 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.328 2.328 make_m2s 4572 13.5 0.044 0.050 2.167 2.236 fft3d_ps 1201 14.6 1.133 1.240 2.099 2.188 wfi_extrapolate 11 7.9 0.001 0.001 2.099 2.099 make_images 4572 14.5 0.113 0.117 1.858 1.925 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.830 1.838 mp_waitany 9880 13.7 1.288 1.797 1.288 1.797 rs_pw_transfer_RS2PW_140 130 11.5 0.203 0.259 0.981 1.351 qs_ot_get_p 119 10.4 0.001 0.001 1.166 1.272 make_images_data 4572 15.5 0.034 0.041 1.059 1.198 rs_pw_transfer_PW2RS_140 130 13.9 0.331 0.421 1.140 1.173 prepare_preconditioner 11 7.9 0.000 0.000 1.091 1.106 make_preconditioner 11 8.9 0.000 0.000 1.091 1.106 multiply_cannon_metrocomm1 18288 15.5 0.018 0.021 0.511 1.060 hybrid_alltoall_any 4725 16.4 0.056 0.192 0.932 1.036 make_full_inverse_cholesky 11 9.9 0.000 0.000 0.988 1.005 mp_alltoall_z22v 1201 16.6 0.725 0.980 0.725 0.980 mp_alltoall_d11v 2130 13.8 0.690 0.971 0.690 0.971 mp_sum_l 11218 13.2 0.629 0.960 0.629 0.960 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.889 0.948 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.850 0.929 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.877 0.916 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.883 0.884 ------------------------------------------------------------------------------- Plot: name="H2O-64_timings_32omp", title="Timings of H2O-64 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32omp", name="rest", label="rest", y=47.333000000000006, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.384, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.296, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.273, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.295, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.089, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=14.302999999999994, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.802, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=7.929, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.838, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.288, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.399, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.027 0.027 108.942 108.942 qs_mol_dyn_low 1 2.0 0.002 0.002 108.317 108.317 qs_forces 11 3.9 0.001 0.001 108.279 108.279 qs_energies 11 4.9 0.001 0.001 100.738 100.738 scf_env_do_scf 11 5.9 0.001 0.001 88.163 88.163 scf_env_do_scf_inner_loop 96 6.5 0.009 0.009 70.303 70.303 velocity_verlet 10 3.0 0.002 0.002 69.978 69.978 rebuild_ks_matrix 107 8.3 0.001 0.001 32.977 32.977 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 32.976 32.976 qs_rho_update_rho_low 107 7.7 0.000 0.000 30.861 30.861 calculate_rho_elec 107 8.7 0.862 0.862 30.861 30.861 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.604 29.604 grid_collocate_task_list 107 9.7 26.811 26.811 26.811 26.811 sum_up_and_integrate 107 10.3 0.451 0.451 26.526 26.526 integrate_v_rspace 107 11.3 0.080 0.080 26.075 26.075 grid_integrate_task_list 107 12.3 24.315 24.315 24.315 24.315 init_scf_loop 11 6.9 0.000 0.000 17.725 17.725 dbcsr_multiply_generic 1966 12.4 0.135 0.135 17.016 17.016 qs_scf_new_mos 96 7.5 0.000 0.000 16.534 16.534 qs_scf_loop_do_ot 96 8.5 0.001 0.001 16.534 16.534 ot_scf_mini 96 9.5 0.002 0.002 15.385 15.385 prepare_preconditioner 11 7.9 0.000 0.000 13.652 13.652 make_preconditioner 11 8.9 0.000 0.000 13.652 13.652 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.492 12.492 ot_mini 96 10.5 0.001 0.001 10.001 10.001 make_m2s 3932 13.4 0.039 0.039 9.544 9.544 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.604 6.604 pw_transfer 1295 11.6 0.056 0.056 5.625 5.625 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.454 5.454 init_scf_run 11 5.9 0.002 0.002 5.347 5.347 scf_env_initial_rho_setup 11 6.9 0.000 0.000 5.346 5.346 qs_ot_get_derivative 96 11.5 0.001 0.001 5.214 5.214 dbcsr_make_dense_low 4961 15.5 0.056 0.056 5.090 5.090 make_dense_data 4961 16.5 4.518 4.518 5.022 5.022 make_images 3932 14.4 1.904 1.904 4.798 4.798 ot_diis_step 96 11.5 0.003 0.003 4.785 4.785 wfi_extrapolate 11 7.9 0.001 0.001 4.756 4.756 fft_wrap_pw1pw2_140 439 13.2 0.487 0.487 4.724 4.724 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.486 4.486 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.444 4.444 apply_single 107 13.6 0.000 0.000 4.444 4.444 cp_fm_cholesky_decompose 22 10.9 4.288 4.288 4.288 4.288 multiply_cannon 1966 13.4 0.147 0.147 4.221 4.221 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.194 4.194 cp_fm_cholesky_invert 11 10.9 3.958 3.958 3.958 3.958 multiply_cannon_loop 1966 14.4 0.036 0.036 3.829 3.829 dbcsr_complete_redistribute 317 12.2 1.914 1.914 3.818 3.818 multiply_cannon_multrec 1966 15.4 3.738 3.738 3.792 3.792 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.730 3.730 dbcsr_copy 1855 11.9 0.205 0.205 3.502 3.502 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.345 3.345 qs_create_task_list 11 7.9 0.000 0.000 3.299 3.299 generate_qs_task_list 11 8.9 2.396 2.396 3.299 3.299 dbcsr_copy_into_existing 22 7.9 3.252 3.252 3.252 3.252 density_rs2pw 107 9.7 0.004 0.004 3.188 3.188 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.032 3.032 fft3d_s 1082 14.6 2.721 2.721 2.725 2.725 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.460 2.460 qs_ot_get_p 107 10.4 0.001 0.001 2.452 2.452 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.325 2.325 ------------------------------------------------------------------------------- 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 0.024 68.824 68.834 qs_mol_dyn_low 1 2.0 0.003 0.003 68.726 68.730 qs_forces 11 3.9 0.001 0.001 68.687 68.687 qs_energies 11 4.9 0.001 0.001 64.039 64.041 scf_env_do_scf 11 5.9 0.000 0.002 59.290 59.290 scf_env_do_scf_inner_loop 96 6.5 0.002 0.016 54.853 54.853 velocity_verlet 10 3.0 0.001 0.003 41.157 41.158 rebuild_ks_matrix 107 8.3 0.000 0.001 29.848 29.911 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.015 29.848 29.910 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.270 26.327 sum_up_and_integrate 107 10.3 0.030 0.036 26.225 26.249 integrate_v_rspace 107 11.3 0.004 0.005 26.195 26.222 qs_rho_update_rho_low 107 7.7 0.000 0.000 25.135 25.141 calculate_rho_elec 107 8.7 0.026 0.027 25.134 25.140 grid_integrate_task_list 107 12.3 22.633 23.032 22.633 23.032 grid_collocate_task_list 107 9.7 21.659 22.006 21.659 22.006 dbcsr_multiply_generic 1966 12.4 0.062 0.066 11.655 11.794 multiply_cannon 1966 13.4 0.128 0.140 8.718 9.124 qs_scf_new_mos 96 7.5 0.000 0.001 8.984 9.080 qs_scf_loop_do_ot 96 8.5 0.001 0.001 8.983 9.079 multiply_cannon_loop 1966 14.4 0.084 0.100 8.274 8.559 ot_scf_mini 96 9.5 0.002 0.002 8.439 8.540 mp_waitall_1 136719 16.5 6.833 7.386 6.833 7.386 multiply_cannon_metrocomm3 15728 15.4 0.034 0.043 4.904 5.494 ot_mini 96 10.5 0.001 0.001 4.944 5.051 rs_pw_transfer 878 11.9 0.009 0.011 3.903 4.516 init_scf_loop 11 6.9 0.000 0.000 4.423 4.424 density_rs2pw 107 9.7 0.004 0.005 3.181 3.791 init_scf_run 11 5.9 0.000 0.004 3.763 3.763 scf_env_initial_rho_setup 11 6.9 0.000 0.004 3.762 3.763 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.694 3.701 wfi_extrapolate 11 7.9 0.001 0.001 3.424 3.424 multiply_cannon_multrec 15728 15.4 2.630 2.903 2.639 2.914 pw_transfer 1295 11.6 0.086 0.103 2.809 2.869 potential_pw2rs 107 12.3 0.006 0.007 2.757 2.780 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 2.666 2.716 qs_ot_get_derivative 96 11.5 0.001 0.001 2.533 2.631 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.381 2.455 apply_single 107 13.6 0.000 0.000 2.380 2.455 ot_diis_step 96 11.5 0.003 0.003 2.395 2.395 fft_wrap_pw1pw2_140 439 13.2 0.220 0.261 2.286 2.380 make_m2s 3932 13.4 0.039 0.042 1.998 2.049 mp_waitany 8968 13.7 1.382 2.003 1.382 2.003 fft3d_ps 1081 14.6 1.019 1.151 1.893 1.960 make_images 3932 14.4 0.101 0.105 1.721 1.768 rs_pw_transfer_RS2PW_140 118 11.5 0.154 0.170 1.039 1.666 mp_alltoall_d11v 1998 13.7 0.977 1.632 0.977 1.632 rs_gather_matrices 107 12.3 0.065 0.071 0.770 1.416 ------------------------------------------------------------------------------- Plot: name="H2O-64_nonortho_timings_32omp", title="Timings of H2O-64_nonortho with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="rest", label="rest", y=41.31399999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=26.811, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.315, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.518, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.288, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=3.958, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.738, 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=13.686999999999998, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.659, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.633, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.63, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=6.833, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.382, 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 0.182 0.182 104.498 104.498 qs_energies 1 2.0 0.000 0.000 103.699 103.699 scf_env_do_scf 1 3.0 0.000 0.000 102.528 102.528 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.792 97.792 rebuild_ks_matrix 7 6.0 0.000 0.000 97.736 97.736 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.736 97.736 hfx_ks_matrix 7 8.0 0.000 0.000 89.004 89.004 integrate_four_center 7 9.0 2.218 2.218 88.967 88.967 integrate_four_center_main 7 10.0 0.759 0.759 80.610 80.610 integrate_four_center_bin 447 11.0 79.851 79.851 79.851 79.851 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.183 56.183 init_scf_loop 1 4.0 0.000 0.000 46.335 46.335 integrate_four_center_load 7 10.0 0.000 0.000 5.866 5.866 hfx_load_balance 1 11.0 0.001 0.001 5.866 5.866 qs_vxc_create 14 8.0 0.000 0.000 3.060 3.060 xc_vxc_pw_create 14 9.0 0.116 0.116 3.060 3.060 hfx_load_balance_count 1 12.0 2.926 2.926 2.926 2.926 hfx_load_balance_bin 1 12.0 2.923 2.923 2.923 2.923 calculate_rho_elec 15 7.4 0.118 0.118 2.395 2.395 xc_rho_set_and_dset_create 14 10.0 0.091 0.091 2.332 2.332 prepare_preconditioner 1 5.0 0.000 0.000 2.206 2.206 make_preconditioner 1 6.0 0.000 0.000 2.206 2.206 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.190 2.190 ------------------------------------------------------------------------------- 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 0.224 0.246 94.338 94.349 qs_energies 1 2.0 0.000 0.000 93.985 93.992 scf_env_do_scf 1 3.0 0.000 0.000 93.589 93.591 qs_ks_update_qs_env 8 5.0 0.000 0.000 91.566 91.566 rebuild_ks_matrix 7 6.0 0.000 0.000 91.558 91.558 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 91.558 91.558 hfx_ks_matrix 7 8.0 0.000 0.000 86.468 86.469 integrate_four_center 7 9.0 0.052 0.335 86.460 86.461 integrate_four_center_main 7 10.0 0.003 0.003 78.435 80.072 integrate_four_center_bin 448 11.0 78.432 80.070 78.432 80.070 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 52.396 52.396 init_scf_loop 1 4.0 0.000 0.000 41.192 41.194 integrate_four_center_load 7 10.0 0.000 0.000 5.634 5.636 hfx_load_balance 1 11.0 0.001 0.001 5.634 5.636 mp_sync 70 11.3 1.726 3.228 1.726 3.228 hfx_load_balance_bin 1 12.0 2.756 2.818 2.756 2.818 hfx_load_balance_count 1 12.0 2.757 2.808 2.757 2.808 qs_vxc_create 14 8.0 0.000 0.000 2.296 2.296 xc_vxc_pw_create 14 9.0 0.007 0.007 2.296 2.296 xc_rho_set_and_dset_create 14 10.0 0.009 0.010 1.870 1.983 ------------------------------------------------------------------------------- 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=15.638999999999996, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=79.851, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.926, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.923, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=2.218, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.759, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.182, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="H2O-hyb_timings_32mpi", title="Timings of H2O-hyb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32mpi", name="rest", label="rest", y=8.387999999999977, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.432, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.757, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.756, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.052, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.224, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=1.726, yerr=0.0 Running GW_PBE_4benzene.inp with 1 threads and 32 ranks... done. Running GW_PBE_4benzene.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.012 0.012 78.860 78.860 qs_energies 1 2.0 0.000 0.000 78.494 78.494 mp2_main 1 3.0 0.000 0.000 75.829 75.829 mp2_gpw_main 1 4.0 0.000 0.000 75.729 75.729 rpa_ri_compute_en 1 5.0 0.000 0.000 72.090 72.090 rpa_num_int 1 6.0 0.001 0.001 72.085 72.085 compute_mat_P_omega 1 7.0 0.003 0.003 62.115 62.115 compute_mat_P_omega_contract 10 8.0 8.729 8.729 61.921 61.921 dbt_total 2336 9.6 0.011 0.011 48.478 48.478 dbt_contract 787 11.0 0.032 0.032 41.788 41.788 dbt_tas_total 1149 12.2 0.179 0.179 40.935 40.935 dbt_tas_multiply 807 12.1 0.003 0.003 39.613 39.613 dbt_tas_dbm 807 14.1 0.003 0.003 33.314 33.314 dbm_multiply 807 16.1 33.306 33.306 33.306 33.306 dbt_tas_mm_1N 524 15.1 0.001 0.001 26.024 26.024 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 24.812 24.812 compute_mat_P_omega_calc_M_occ 250 9.0 8.753 8.753 16.371 16.371 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.667 6.667 dbt_tas_mm_2 251 15.0 0.001 0.001 5.788 5.788 dbt_copy 1103 10.7 0.067 0.067 5.351 5.351 compute_QP_energies 1 7.0 0.000 0.000 4.952 4.952 compute_self_energy_cubic_gw 1 8.0 0.053 0.053 4.951 4.951 contract_cubic_gw 21 9.0 0.000 0.000 3.918 3.918 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.631 3.631 dbt_tas_reserve_blocks_index 3261 14.3 0.144 0.144 3.275 3.275 dbm_reserve_blocks 3628 15.3 3.200 3.200 3.200 3.200 scf_env_do_scf 1 3.0 0.000 0.000 2.549 2.549 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.549 2.549 dbt_reserve_blocks_index 2280 13.1 0.049 0.049 2.504 2.504 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.463 2.463 convert_to_new_pgrid 2421 14.1 0.132 0.132 2.271 2.271 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.161 2.161 dbm_copy 1614 15.1 2.139 2.139 2.139 2.139 dbt_crop 1042 12.0 1.339 1.339 2.098 2.098 dbt_tas_copy 574 11.4 1.267 1.267 2.079 2.079 dbt_tas_reshape 367 15.0 0.006 0.006 2.027 2.027 compute_W_cubic_GW 10 7.0 0.004 0.004 1.958 1.958 dbt_reshape 278 11.9 0.950 0.950 1.797 1.797 get_2c_integrals 1 6.0 0.000 0.000 1.709 1.709 ------------------------------------------------------------------------------- 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 0.007 0.026 29.737 29.752 qs_energies 1 2.0 0.000 0.000 29.661 29.663 mp2_main 1 3.0 0.000 0.000 28.787 28.789 mp2_gpw_main 1 4.0 0.000 0.000 28.754 28.756 rpa_ri_compute_en 1 5.0 0.000 0.000 27.405 27.406 rpa_num_int 1 6.0 0.000 0.002 27.404 27.406 dbt_total 2336 9.6 0.011 0.012 24.366 24.371 compute_mat_P_omega 1 7.0 0.001 0.005 23.239 23.253 compute_mat_P_omega_contract 10 8.0 0.380 0.401 23.129 23.133 dbt_contract 787 11.0 0.024 0.026 18.345 18.350 dbt_tas_total 1149 12.2 0.047 0.055 16.488 16.489 dbt_tas_multiply 807 12.1 0.002 0.002 16.434 16.436 dbt_tas_dbm 807 14.1 0.002 0.003 12.385 12.389 dbm_multiply 807 16.1 9.567 10.527 9.567 10.527 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.962 6.963 compute_mat_P_omega_calc_M_occ 250 9.0 0.369 0.389 6.784 6.785 mp_sync 8706 11.6 4.535 6.062 4.535 6.062 dbt_tas_mm_2 251 15.0 0.001 0.001 5.812 5.814 dbt_copy 1111 10.7 0.010 0.011 5.209 5.534 dbt_reshape 1098 11.7 1.970 2.200 4.936 5.256 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 4.936 4.937 dbt_tas_mm_1N 524 15.1 0.001 0.001 4.388 4.880 compute_QP_energies 1 7.0 0.000 0.000 2.630 2.631 compute_self_energy_cubic_gw 1 8.0 0.002 0.004 2.629 2.630 mp_waitall_2 3776 15.3 2.337 2.528 2.337 2.528 dbt_communicate_buffer 1098 12.7 0.052 0.059 2.380 2.524 contract_cubic_gw 21 9.0 0.000 0.000 2.093 2.093 dbt_reserve_blocks_index 2849 13.1 0.060 0.067 1.426 1.693 dbt_reserve_blocks_index_array 2791 12.2 0.008 0.011 1.418 1.687 dbt_tas_reserve_blocks_index 3300 14.5 0.111 0.120 1.398 1.662 dbm_reserve_blocks 3696 15.4 1.375 1.640 1.375 1.640 dbt_crop 1042 12.0 0.844 0.952 1.289 1.466 mp2_ri_gpw_compute_in 1 5.0 0.000 0.002 1.348 1.348 dbt_tas_replicate 396 14.1 0.522 0.691 1.048 1.113 parallel_gemm_fm 105 8.4 0.000 0.000 0.946 0.957 parallel_gemm_fm_cosma 105 9.4 0.946 0.957 0.946 0.957 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.906 0.908 convert_to_new_pgrid 2421 14.1 0.022 0.027 0.720 0.859 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.846 0.847 scf_env_do_scf 1 3.0 0.000 0.000 0.838 0.838 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.838 0.838 dbm_copy 1608 15.1 0.692 0.833 0.692 0.833 mp_max_i 1994 9.8 0.510 0.730 0.510 0.730 compute_W_cubic_GW 10 7.0 0.001 0.001 0.706 0.713 mp_bcast_im 6 9.7 0.586 0.607 0.586 0.607 dbm_add 807 14.1 0.527 0.605 0.527 0.605 ------------------------------------------------------------------------------- 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=21.782999999999994, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=33.306, 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=8.753, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.729, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.2, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.139, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.95, 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=8.511999999999997, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.567, 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=0.369, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.38, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.375, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.692, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=1.97, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.535, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.337, 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 0.017 0.017 312.592 312.592 qs_forces 1 2.0 0.000 0.000 312.054 312.054 rebuild_ks_matrix 7 6.6 0.000 0.000 310.664 310.664 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 310.664 310.664 hfx_ks_matrix 7 8.6 0.000 0.000 308.818 308.818 hfx_ri_update_ks 7 9.6 0.000 0.000 268.765 268.765 hfx_ri_update_ks_Pmat 7 10.6 30.666 30.666 268.761 268.761 dbt_total 841 11.0 0.005 0.005 255.831 255.831 dbt_contract 207 12.4 0.036 0.036 237.092 237.092 dbt_tas_total 375 13.4 1.499 1.499 236.386 236.386 qs_energies 1 3.0 0.000 0.000 236.223 236.223 scf_env_do_scf 1 4.0 0.000 0.000 235.938 235.938 qs_ks_update_qs_env 8 6.0 0.000 0.000 234.882 234.882 dbt_tas_multiply 216 13.5 0.001 0.001 232.045 232.045 dbt_tas_dbm 216 15.5 0.001 0.001 219.355 219.355 dbm_multiply 216 17.5 219.352 219.352 219.352 219.352 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 214.526 214.526 dbt_tas_mm_2 91 16.5 0.001 0.001 206.308 206.308 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 151.314 151.314 init_scf_loop 2 5.0 0.000 0.000 84.622 84.622 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 75.785 75.785 hfx_ri_update_forces 1 7.0 1.562 1.562 40.049 40.049 hfx_ri_forces_Pmat_3c 1 8.0 4.652 4.652 23.427 23.427 dbt_copy 409 11.7 0.038 0.038 14.390 14.390 precalc_derivatives 1 8.0 2.154 2.154 12.741 12.741 dbt_reshape 132 13.2 6.118 6.118 10.045 10.045 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.473 9.473 dbt_tas_mm_3T 77 17.1 0.000 0.000 8.939 8.939 build_3c_derivatives 3 9.0 2.393 2.393 7.164 7.164 dbt_tas_reserve_blocks_index 1287 15.4 0.279 0.279 7.056 7.056 dbm_reserve_blocks 1461 16.2 7.005 7.005 7.005 7.005 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.686 6.686 ------------------------------------------------------------------------------- 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 0.019 42.171 42.180 qs_forces 1 2.0 0.000 0.000 42.070 42.070 rebuild_ks_matrix 7 6.6 0.000 0.000 41.426 41.427 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 41.426 41.427 hfx_ks_matrix 7 8.6 0.000 0.000 40.530 40.536 dbt_total 841 11.0 0.005 0.005 36.012 36.014 dbt_contract 207 12.4 0.020 0.022 28.441 28.497 dbt_tas_total 375 13.4 0.048 0.156 26.425 26.425 dbt_tas_multiply 216 13.5 0.001 0.001 25.510 25.510 hfx_ri_update_ks 7 9.6 0.000 0.000 23.661 23.661 hfx_ri_update_ks_Pmat 7 10.6 1.159 1.231 23.653 23.660 qs_energies 1 3.0 0.000 0.000 22.264 22.264 scf_env_do_scf 1 4.0 0.000 0.001 22.132 22.132 qs_ks_update_qs_env 8 6.0 0.000 0.000 21.630 21.631 dbt_tas_dbm 216 15.5 0.001 0.001 20.302 20.312 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 19.796 19.797 dbm_multiply 216 17.5 17.848 18.994 17.848 18.994 hfx_ri_update_forces 1 7.0 0.054 0.058 16.868 16.874 hfx_ri_forces_Pmat_3c 1 8.0 0.158 0.171 12.637 12.650 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 12.394 12.394 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 11.367 11.367 init_scf_loop 2 5.0 0.000 0.000 9.738 9.738 dbt_tas_mm_2 91 16.5 0.001 0.001 9.492 9.493 mp_sync 2909 12.8 4.605 7.242 4.605 7.242 dbt_copy 421 11.8 0.009 0.011 6.148 6.474 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.190 5.806 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.620 4.620 dbt_reshape 252 12.8 2.146 2.264 4.216 4.383 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.910 4.060 precalc_derivatives 1 8.0 0.076 0.081 3.232 3.232 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 2.993 2.994 dbm_reserve_blocks 1477 16.3 2.353 2.725 2.353 2.725 dbt_tas_reserve_blocks_index 1302 15.5 0.219 0.230 2.357 2.715 dbt_crop 372 13.7 1.656 1.739 2.232 2.404 mp_waitall_2 1204 16.3 2.091 2.177 2.091 2.177 dbt_reserve_blocks_index 938 14.4 0.089 0.096 1.857 2.107 dbt_reserve_blocks_index_array 915 13.4 0.005 0.005 1.835 2.083 build_3c_derivatives 3 9.0 0.218 0.237 1.830 1.837 dbt_tas_replicate 175 15.2 0.641 0.680 1.582 1.671 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.569 1.572 convert_to_new_pgrid 648 15.5 0.034 0.074 1.246 1.519 dbt_tas_copy 169 12.8 0.753 0.807 1.325 1.499 dbt_communicate_buffer 252 13.8 0.011 0.013 1.395 1.451 dbm_copy 452 16.3 1.085 1.358 1.085 1.358 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.306 1.306 dbt_tas_communicate_buffer 352 16.4 0.012 0.015 0.910 0.968 ------------------------------------------------------------------------------- Plot: name="RI-HFX_H2O-32_timings_32omp", title="Timings of RI-HFX_H2O-32 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="rest", label="rest", y=44.79899999999998, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=219.352, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=30.666, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.005, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.118, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.652, 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=11.810999999999996, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=17.848, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.159, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.353, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.146, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.158, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.605, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.091, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.014 0.014 182.865 182.865 qs_energies 1 2.0 0.000 0.000 182.685 182.685 mp2_main 1 3.0 0.000 0.000 178.155 178.155 mp2_gpw_main 1 4.0 0.001 0.001 177.764 177.764 mp2_ri_gpw_compute_in 1 5.0 0.376 0.376 128.342 128.342 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 116.882 116.882 mp2_eri_3c_integrate_gpw 2656 7.0 0.012 0.012 87.991 87.991 integrate_v_rspace 2666 8.0 0.587 0.587 75.091 75.091 grid_integrate_task_list 2666 9.0 72.542 72.542 72.542 72.542 mp2_ri_gpw_compute_en 1 5.0 0.086 0.086 49.398 49.398 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.339 9.339 47.600 47.600 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.161 2.161 30.929 30.929 local_gemm 2080 8.0 28.767 28.767 28.767 28.767 dbcsr_multiply_generic 5322 8.0 0.171 0.171 19.991 19.991 ao_to_mo_and_store_B_mult_1 2656 7.0 0.008 0.008 19.971 19.971 pw_transfer 63872 10.6 1.024 1.024 11.771 11.771 calculate_wavefunction 2656 8.0 8.065 8.065 11.589 11.589 get_2c_integrals 1 6.0 0.000 0.000 11.083 11.083 fft_wrap_pw1pw2 53228 11.4 0.114 0.114 10.534 10.534 compute_2c_integrals 1 7.0 0.006 0.006 10.222 10.222 compute_2c_integrals_loop_lm 1 8.0 0.006 0.006 10.197 10.197 mp2_eri_2c_integrate_gpw 1 9.0 3.370 3.370 10.191 10.191 multiply_cannon 5322 9.0 0.418 0.418 10.156 10.156 multiply_cannon_loop 5322 10.0 0.114 0.114 8.838 8.838 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.169 2.169 8.812 8.812 make_m2s 10644 9.0 0.062 0.062 7.850 7.850 make_images 10644 10.0 3.165 3.165 7.551 7.551 multiply_cannon_multrec 5322 11.0 7.404 7.404 7.442 7.442 fft_wrap_pw1pw2_20 21271 12.4 0.424 0.424 7.429 7.429 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 7.158 7.158 fft3d_s 53229 13.4 6.454 6.454 6.489 6.489 dbcsr_complete_redistribute 2689 9.0 1.109 1.109 5.628 5.628 mp2_ri_gpw_compute_en_ener 2080 7.0 5.414 5.414 5.414 5.414 dbcsr_finalize 10708 9.5 0.160 0.160 5.083 5.083 dbcsr_merge_all 8011 10.3 3.472 3.472 4.471 4.471 scf_env_do_scf 1 3.0 0.000 0.000 4.136 4.136 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.136 4.136 potential_pw2rs 5322 10.0 0.145 0.145 3.901 3.901 ------------------------------------------------------------------------------- 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 0.019 33.718 33.728 qs_energies 1 2.0 0.000 0.000 33.652 33.653 mp2_main 1 3.0 0.000 0.001 31.706 31.707 mp2_gpw_main 1 4.0 0.001 0.002 31.602 31.603 mp2_ri_gpw_compute_in 1 5.0 0.052 0.052 16.787 17.086 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.617 15.921 mp2_ri_gpw_compute_en 1 5.0 0.160 0.167 14.727 14.981 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.680 13.861 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.730 0.863 13.778 13.786 integrate_v_rspace 93 8.1 0.096 0.107 13.551 13.732 grid_integrate_task_list 93 9.1 13.267 13.446 13.267 13.446 mp2_ri_gpw_compute_en_expansio 65 7.0 0.092 0.115 10.325 10.496 local_gemm 65 8.0 10.234 10.384 10.234 10.384 mp2_ri_gpw_compute_en_comm 17 7.0 0.058 0.079 2.399 2.915 mp_sendrecv_dm3 1054 8.0 1.926 2.553 1.926 2.553 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.663 1.849 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.647 1.836 scf_env_do_scf 1 3.0 0.000 0.000 1.833 1.834 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.833 1.834 get_2c_integrals 1 6.0 0.000 0.000 1.090 1.125 multiply_cannon 176 9.0 0.015 0.016 0.998 1.064 multiply_cannon_loop 176 10.0 0.002 0.002 0.944 1.008 qs_scf_new_mos 10 5.0 0.000 0.000 0.915 0.923 eigensolver 11 5.8 0.001 0.001 0.892 0.894 multiply_cannon_multrec 246 11.0 0.820 0.853 0.824 0.858 compute_2c_integrals 1 7.0 0.002 0.003 0.815 0.836 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 0.721 0.752 mp2_eri_2c_integrate_gpw 1 9.0 0.197 0.203 0.720 0.751 make_m2s 352 9.0 0.003 0.003 0.630 0.748 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.738 0.738 pw_transfer 2120 10.5 0.043 0.049 0.727 0.738 make_images 352 10.0 0.050 0.051 0.618 0.736 cp_fm_redistribute_end 11 7.8 0.275 0.727 0.289 0.732 cp_fm_diag_elpa_base 11 7.8 0.429 0.690 0.440 0.705 fft_wrap_pw1pw2 1768 11.4 0.004 0.004 0.672 0.679 ------------------------------------------------------------------------------- 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=56.74800000000002, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=72.542, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=28.767, 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=9.339, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.065, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.404, 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=6.741000000000007, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.267, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.234, 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=0.73, 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=0.82, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.926, 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 0.076 0.076 120.947 120.947 qs_energies 1 2.0 0.000 0.000 119.640 119.640 scf_env_do_scf 1 3.0 0.000 0.000 113.158 113.158 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 113.158 113.158 qs_ks_update_qs_env 15 5.0 0.000 0.000 47.782 47.782 rebuild_ks_matrix 15 6.0 0.000 0.000 47.576 47.576 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 47.576 47.576 qs_scf_new_mos 15 5.0 0.000 0.000 40.955 40.955 eigensolver 15 6.0 0.001 0.001 33.287 33.287 qs_vxc_create 15 8.0 0.037 0.037 32.753 32.753 calculate_dispersion_nonloc 15 9.0 6.795 6.795 28.710 28.710 pw_transfer 1191 10.0 0.056 0.056 22.149 22.149 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 21.984 21.984 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.646 21.646 calculate_rho_elec 16 6.0 0.217 0.217 21.646 21.646 cp_fm_diag_elpa 15 7.0 0.000 0.000 21.084 21.084 cp_fm_diag_elpa_base 15 8.0 18.575 18.575 21.084 21.084 grid_collocate_task_list 16 7.0 20.347 20.347 20.347 20.347 fft_wrap_pw1pw2_150 765 12.0 3.542 3.542 16.181 16.181 sum_up_and_integrate 15 8.0 0.084 0.084 13.764 13.764 integrate_v_rspace 15 9.0 0.018 0.018 13.681 13.681 grid_integrate_task_list 15 10.0 13.177 13.177 13.177 13.177 cp_fm_cholesky_restore 45 7.0 9.976 9.976 9.976 9.976 fft3d_s 1087 13.0 9.808 9.808 9.823 9.823 pw_scatter_s 585 13.1 6.881 6.881 6.881 6.881 fft_wrap_pw1pw2_200 197 12.3 0.650 0.650 5.616 5.616 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.545 5.545 dbcsr_complete_redistribute 46 8.3 2.249 2.249 5.494 5.494 cp_fm_upper_to_full 30 8.0 4.734 4.734 4.734 4.734 vdW_energy 15 10.0 4.236 4.236 4.236 4.236 xc_vxc_pw_create 15 9.0 0.228 0.228 4.006 4.006 gspace_mixing 14 5.0 0.171 0.171 3.979 3.979 broyden_mixing 14 6.0 3.402 3.402 3.402 3.402 init_scf_run 1 3.0 0.000 0.000 3.067 3.067 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.961 2.961 xc_pw_derive 90 11.0 0.001 0.001 2.600 2.600 calculate_dm_sparse 15 6.0 0.018 0.018 2.474 2.474 ------------------------------------------------------------------------------- From /workspace/artifacts/diag_cu144_broy_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.014 0.026 57.969 57.980 qs_energies 1 2.0 0.000 0.000 57.721 57.726 scf_env_do_scf 1 3.0 0.000 0.001 53.597 53.598 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 53.597 53.598 qs_ks_update_qs_env 15 5.0 0.000 0.000 22.130 22.138 rebuild_ks_matrix 15 6.0 0.000 0.000 22.098 22.106 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 22.097 22.106 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.272 20.276 calculate_rho_elec 16 6.0 0.007 0.007 20.272 20.276 grid_collocate_task_list 16 7.0 19.108 19.305 19.108 19.305 sum_up_and_integrate 15 8.0 0.010 0.015 13.380 13.430 integrate_v_rspace 15 9.0 0.000 0.001 13.370 13.425 grid_integrate_task_list 15 10.0 12.712 12.806 12.712 12.806 qs_scf_new_mos 15 5.0 0.000 0.000 11.936 11.969 eigensolver 15 6.0 0.001 0.002 11.025 11.059 qs_vxc_create 15 8.0 0.001 0.001 8.448 8.459 cp_fm_diag_elpa 15 7.0 0.000 0.000 7.816 7.819 cp_fm_diag_elpa_base 15 8.0 7.676 7.704 7.813 7.813 calculate_dispersion_nonloc 15 9.0 0.898 0.910 6.766 6.799 pw_transfer 1191 10.0 0.081 0.097 6.198 6.296 fft_wrap_pw1pw2 1086 11.0 0.011 0.013 6.039 6.177 fft3d_ps 1086 13.0 2.272 2.614 4.488 4.805 fft_wrap_pw1pw2_150 765 12.0 0.236 0.292 3.853 3.908 cp_fm_cholesky_restore 45 7.0 3.061 3.094 3.061 3.094 mp_alltoall_z22v 1086 15.0 1.700 2.522 1.700 2.522 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.452 2.452 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.132 2.355 fft_wrap_pw1pw2_200 197 12.3 0.164 0.199 2.081 2.149 xc_vxc_pw_create 15 9.0 0.014 0.019 1.681 1.714 x_to_yz 585 14.1 0.304 0.339 1.158 1.485 init_scf_run 1 3.0 0.000 0.001 1.449 1.450 yz_to_x 501 13.9 0.189 0.248 1.035 1.438 rs_pw_transfer 158 9.4 0.001 0.002 1.092 1.397 build_core_ppnl 1 5.0 1.245 1.384 1.245 1.384 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.364 1.365 vdW_energy 15 10.0 1.235 1.304 1.235 1.304 density_rs2pw 16 7.0 0.001 0.001 1.050 1.244 xc_pw_derive 90 11.0 0.001 0.002 1.101 1.174 ------------------------------------------------------------------------------- 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=49.06400000000001, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.347, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=18.575, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.177, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=9.976, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=9.808, 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=13.140000000000008, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.108, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=7.676, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.712, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.061, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.272, 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 0.071 0.071 329.120 329.120 qs_energies 1 2.0 0.000 0.000 328.989 328.989 ls_scf 1 3.0 0.000 0.000 327.804 327.804 ls_scf_main 1 4.0 0.002 0.002 318.725 318.725 density_matrix_trs4 11 5.0 0.012 0.012 227.276 227.276 arnoldi_extremal 12 6.1 0.000 0.000 143.639 143.639 arnoldi_normal_ev 12 7.1 0.014 0.014 143.639 143.639 build_subspace 23 8.1 0.079 0.079 140.995 140.995 dbcsr_matrix_vector_mult 652 9.0 0.190 0.190 140.771 140.771 dbcsr_matrix_vector_mult_local 652 10.0 139.100 139.100 139.109 139.109 ls_scf_dm_to_ks 11 5.0 0.000 0.000 86.260 86.260 matrix_ls_to_qs 11 6.0 0.000 0.000 82.991 82.991 dbcsr_multiply_generic 185 6.1 0.840 0.840 72.896 72.896 dbcsr_copy_into_existing 11 7.0 45.650 45.650 45.650 45.650 multiply_cannon 185 7.1 0.277 0.277 44.333 44.333 dbcsr_complete_redistribute 23 7.5 29.974 29.974 41.022 41.022 matrix_decluster 11 7.0 0.000 0.000 37.340 37.340 multiply_cannon_loop 185 8.1 0.251 0.251 32.104 32.104 make_m2s 370 7.1 0.038 0.038 24.235 24.235 make_images 370 8.1 10.537 10.537 22.718 22.718 multiply_cannon_multrec 185 9.1 22.030 22.030 22.055 22.055 dbcsr_finalize 646 7.5 0.161 0.161 14.585 14.585 dbcsr_merge_all 597 8.5 2.284 2.284 13.367 13.367 setup_rec_index_2d 370 8.1 11.867 11.867 11.867 11.867 dbcsr_sort_indices 1103 9.9 10.123 10.123 10.123 10.123 tree_to_linear_d 110 9.4 9.898 9.898 9.898 9.898 calculate_norms 370 9.1 9.798 9.798 9.798 9.798 quick_finalize 395 10.0 0.364 0.364 8.765 8.765 ls_scf_init_scf 1 4.0 0.000 0.000 8.389 8.389 dbcsr_special_finalize 370 9.1 0.002 0.002 8.116 8.116 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.057 8.057 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.407 7.407 ------------------------------------------------------------------------------- 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 0.023 63.296 63.306 qs_energies 1 2.0 0.000 0.000 63.212 63.212 ls_scf 1 3.0 0.000 0.000 63.163 63.164 ls_scf_main 1 4.0 0.000 0.009 60.699 60.700 density_matrix_trs4 11 5.0 0.006 0.018 58.309 58.364 dbcsr_multiply_generic 185 6.1 0.059 0.084 55.275 55.587 multiply_cannon 185 7.1 0.032 0.037 46.037 46.728 multiply_cannon_loop 185 8.1 0.106 0.132 43.743 44.686 multiply_cannon_multrec 1480 9.1 26.744 30.221 26.991 30.477 mp_waitall_1 11936 10.3 14.681 19.395 14.681 19.395 multiply_cannon_metrocomm3 1480 9.1 0.012 0.017 8.708 15.919 multiply_cannon_metrocomm1 1480 9.1 0.007 0.010 3.418 7.628 make_m2s 370 7.1 0.034 0.037 6.349 6.412 make_images 370 8.1 0.616 0.646 6.225 6.287 calculate_norms 2960 9.1 4.468 5.689 4.468 5.689 make_images_data 370 9.1 0.009 0.013 2.773 3.005 mp_sum_l 1119 5.6 1.912 2.923 1.912 2.923 hybrid_alltoall_any 393 9.9 0.167 0.840 2.410 2.585 arnoldi_extremal 12 6.1 0.000 0.000 2.240 2.259 arnoldi_normal_ev 12 7.1 0.001 0.003 2.239 2.258 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.067 2.236 build_subspace 23 8.1 0.018 0.025 2.152 2.153 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.070 2.014 dbcsr_complete_redistribute 23 7.5 1.159 1.238 1.867 1.958 dbcsr_matrix_vector_mult 652 9.0 0.009 0.043 1.867 1.922 matrix_ls_to_qs 11 6.0 0.000 0.000 1.816 1.908 ls_scf_init_scf 1 4.0 0.000 0.000 1.890 1.891 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.867 1.873 matrix_decluster 11 7.0 0.000 0.000 1.676 1.769 make_images_pack 370 9.1 1.580 1.739 1.584 1.743 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.705 1.706 dbcsr_matrix_vector_mult_local 652 10.0 1.575 1.647 1.577 1.649 dbcsr_finalize 646 7.5 0.007 0.008 1.307 1.504 buffer_matrices_ensure_size 370 8.1 1.239 1.449 1.239 1.449 ------------------------------------------------------------------------------- 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=70.70100000000002, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=139.1, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=45.65, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=29.974, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.03, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.867, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.798, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=11.177000000000007, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.575, 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=1.159, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=26.744, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="setup_rec_index_2d", label="setup_rec_index_2d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.468, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.681, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.912, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.58, yerr=0.0 Running dbcsr.inp with 1 threads and 32 ranks... done. Running dbcsr.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/dbcsr_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.007 69.370 69.370 lib_test 1 2.0 0.000 0.000 69.362 69.362 dbcsr_run_tests 3 3.0 0.002 0.002 69.362 69.362 test_multiplies_multiproc 3 4.0 0.001 0.001 53.789 53.789 dbcsr_redistribute 9 5.0 35.302 35.302 36.856 36.856 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.611 15.611 dbcsr_make_random_matrix 9 4.0 12.412 12.412 15.466 15.466 multiply_cannon 9 6.0 0.001 0.001 10.950 10.950 multiply_cannon_loop 9 7.0 0.014 0.014 10.592 10.592 multiply_cannon_multrec 9 8.0 10.578 10.578 10.578 10.578 dbcsr_finalize 27 5.7 0.009 0.009 5.542 5.542 dbcsr_merge_all 18 6.5 1.941 1.941 4.821 4.821 dbcsr_data_release 975 7.6 2.779 2.779 2.779 2.779 tree_to_linear_d 9 7.0 1.839 1.839 1.839 1.839 make_m2s 18 6.0 0.001 0.001 1.619 1.619 make_images 18 7.0 0.567 0.567 1.573 1.573 ------------------------------------------------------------------------------- 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 17.102 17.107 lib_test 1 2.0 0.000 0.000 17.073 17.093 dbcsr_run_tests 3 3.0 0.000 0.001 17.070 17.089 test_multiplies_multiproc 3 4.0 0.000 0.002 16.238 16.304 dbcsr_multiply_generic 9 5.0 0.001 0.001 14.900 15.008 multiply_cannon 9 6.0 0.001 0.002 13.143 13.463 multiply_cannon_loop 9 7.0 0.002 0.002 12.873 13.174 multiply_cannon_multrec 72 8.0 10.710 11.210 10.710 11.211 mp_waitall_1 576 9.2 2.468 3.122 2.468 3.122 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.926 2.472 dbcsr_data_release 444 7.6 0.787 0.909 0.787 0.909 dbcsr_make_random_matrix 9 4.0 0.660 0.678 0.799 0.824 dbcsr_finalize 27 5.7 0.000 0.000 0.672 0.779 mp_sum_l 390 2.5 0.432 0.774 0.432 0.774 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.426 0.770 dbcsr_destroy 111 5.9 0.000 0.000 0.633 0.732 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.230 0.695 make_m2s 18 6.0 0.001 0.001 0.655 0.688 make_images 18 7.0 0.021 0.022 0.652 0.684 dbcsr_merge_all 18 6.5 0.095 0.118 0.517 0.608 dbcsr_redistribute 9 5.0 0.231 0.269 0.384 0.413 make_images_data 18 8.0 0.000 0.001 0.341 0.392 dbcsr_data_copy_aa2 18 7.5 0.310 0.363 0.310 0.363 hybrid_alltoall_any 18 9.0 0.026 0.122 0.300 0.344 ------------------------------------------------------------------------------- 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=6.358000000000004, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.302, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.412, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.578, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.779, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.941, 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=1.7189999999999976, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.231, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.66, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.71, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.787, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.095, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.432, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.468, 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 0.052 0.052 126.860 126.860 qs_mol_dyn_low 1 2.0 0.003 0.003 125.544 125.544 velocity_verlet 5 3.0 0.003 0.003 102.468 102.468 qmmm_el_coupling 6 3.8 0.000 0.000 83.352 83.352 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 83.348 83.348 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 82.733 82.733 qmmm_elec_gaussian_low_G 6 6.8 81.836 81.836 81.836 81.836 qs_forces 6 3.8 0.000 0.000 33.981 33.981 qs_energies 6 4.8 0.000 0.000 30.188 30.188 scf_env_do_scf 6 5.8 0.001 0.001 27.984 27.984 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.403 24.403 rebuild_ks_matrix 45 8.4 0.000 0.000 23.536 23.536 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.536 23.536 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.160 20.160 pw_transfer 966 12.3 0.051 0.051 16.939 16.939 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.760 16.760 fft_wrap_pw1pw2_150 507 15.2 2.216 2.216 16.355 16.355 qs_vxc_create 45 10.4 0.001 0.001 13.059 13.059 xc_vxc_pw_create 45 11.4 0.646 0.646 13.058 13.058 xc_pw_derive 270 13.4 0.002 0.002 9.268 9.268 fft3d_s 802 15.6 7.649 7.649 7.657 7.657 qs_rho_update_rho_low 45 7.9 0.000 0.000 6.970 6.970 calculate_rho_elec 45 8.9 0.562 0.562 6.970 6.970 xc_rho_set_and_dset_create 45 12.4 0.573 0.573 6.731 6.731 pw_scatter_s 429 15.8 5.648 5.648 5.648 5.648 xc_pw_divergence 45 12.4 0.001 0.001 5.635 5.635 qmmm_forces 6 3.8 0.002 0.002 5.159 5.159 qmmm_forces_with_gaussian 6 4.8 0.016 0.016 4.840 4.840 pw_integral_ab 2539 7.4 4.494 4.494 4.494 4.494 qs_ks_ddapc 45 10.4 0.001 0.001 4.120 4.120 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.115 4.115 init_scf_loop 6 6.8 0.000 0.000 3.576 3.576 qmmm_forces_gaussian_low_G 6 6.8 3.416 3.416 3.416 3.416 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.384 3.384 sum_up_and_integrate 45 10.4 0.324 0.324 3.261 3.261 density_rs2pw 45 9.9 0.002 0.002 3.241 3.241 grid_collocate_task_list 45 9.9 3.167 3.167 3.167 3.167 integrate_v_rspace 45 11.4 0.006 0.006 2.937 2.937 cp_ddapc_apply_CD 45 11.4 0.004 0.004 2.541 2.541 ------------------------------------------------------------------------------- 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 0.038 0.054 51.088 51.098 qs_mol_dyn_low 1 2.0 0.002 0.003 50.117 50.173 qs_forces 6 3.8 0.000 0.001 36.251 36.251 qs_energies 6 4.8 0.000 0.000 34.579 34.579 scf_env_do_scf 6 5.8 0.000 0.001 33.705 33.705 scf_env_do_scf_inner_loop 113 6.2 0.002 0.018 32.348 32.348 rebuild_ks_matrix 119 8.1 0.000 0.000 23.680 23.691 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.015 23.680 23.691 qs_ks_update_qs_env 119 7.3 0.001 0.001 22.291 22.301 velocity_verlet 5 3.0 0.002 0.003 21.220 21.224 pw_transfer 2446 12.3 0.185 0.222 15.651 16.164 fft_wrap_pw1pw2 2059 13.4 0.022 0.026 15.260 15.875 fft_wrap_pw1pw2_150 1321 14.9 1.112 1.382 14.670 15.130 fft3d_ps 2059 15.4 6.229 7.271 11.461 12.733 qs_vxc_create 119 10.1 0.002 0.003 12.372 12.379 xc_vxc_pw_create 119 11.1 0.137 0.217 12.370 12.377 qs_rho_update_rho_low 119 7.3 0.000 0.000 9.783 9.786 calculate_rho_elec 119 8.3 0.048 0.057 9.782 9.786 xc_pw_derive 714 13.1 0.009 0.012 9.285 9.568 sum_up_and_integrate 119 10.1 0.074 0.093 8.303 8.329 integrate_v_rspace 119 11.1 0.003 0.003 8.229 8.263 qmmm_forces 6 3.8 0.002 0.002 7.031 7.032 qmmm_forces_with_gaussian 6 4.8 0.007 0.008 6.707 6.931 xc_rho_set_and_dset_create 119 12.1 0.337 0.428 6.041 6.248 xc_pw_divergence 119 12.1 0.004 0.006 5.985 6.236 mp_alltoall_z22v 2059 17.4 3.973 6.180 3.973 6.180 qmmm_el_coupling 6 3.8 0.000 0.000 5.961 6.119 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 5.960 6.118 rs_pw_transfer 988 11.5 0.010 0.013 5.699 5.954 density_rs2pw 119 9.3 0.005 0.007 5.379 5.657 potential_pw2rs 119 12.1 0.006 0.018 4.664 4.694 grid_collocate_task_list 119 9.3 4.232 4.404 4.232 4.404 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.833 3.886 yz_to_x 964 16.0 0.468 0.703 2.421 3.719 x_to_yz 1095 16.8 0.738 0.882 2.758 3.526 grid_integrate_task_list 119 12.1 3.330 3.503 3.330 3.503 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.293 3.322 qmmm_forces_gaussian_low_G 6 6.8 3.146 3.197 3.146 3.197 qmmm_elec_gaussian_low_G 6 6.8 2.706 2.735 2.706 2.735 mp_waitany 4028 12.8 2.174 2.673 2.174 2.673 pw_restrict_s3 18 5.8 1.293 1.350 2.284 2.478 rs_pw_transfer_PW2RS_150 125 13.9 0.648 0.819 2.142 2.218 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 1.973 2.127 pw_prolongate_s3 18 6.8 1.096 1.138 1.973 2.127 qs_scf_new_mos 113 7.2 0.000 0.000 1.944 1.950 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.944 1.950 rs_pw_transfer_RS2PW_150 125 11.2 0.539 0.705 1.706 1.947 ot_scf_mini 113 9.2 0.001 0.001 1.862 1.868 qs_ks_ddapc 119 10.1 0.002 0.002 1.717 1.819 dbcsr_multiply_generic 2588 12.3 0.056 0.059 1.760 1.809 pw_scatter_p 1095 15.8 1.496 1.530 1.496 1.530 pw_integral_ab 2761 7.7 1.056 1.232 1.365 1.455 pw_gather_p 964 15.0 1.142 1.454 1.142 1.454 mp_sum_d 5814 12.2 0.821 1.439 0.821 1.439 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.402 1.403 init_scf_loop 6 6.8 0.000 0.000 1.355 1.355 mp_waitall_1 177795 16.4 1.003 1.291 1.003 1.291 mp_sum_dm3 33 5.7 1.190 1.245 1.190 1.245 ot_mini 113 10.2 0.000 0.000 1.148 1.153 ------------------------------------------------------------------------------- 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=20.650000000000006, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=81.836, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.649, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.648, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.494, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.416, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.167, 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 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=26.416, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.706, 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=1.056, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.146, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.232, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.33, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.973, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.229, yerr=0.0 Summary: Performance test took 33 minutes. Status: OK Removing intermediate container 5dbb0a5d6b6f ---> a7ed3f8b399c Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 1bc80f76c94e Removing intermediate container 1bc80f76c94e ---> 5e66d700cc64 Step 42/42 : ENTRYPOINT [] ---> Running in c3adaa1ae3d5 Removing intermediate container c3adaa1ae3d5 ---> b618db3ec360 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built b618db3ec360 Successfully tagged us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2022-12-21 11:50:38+00:00