StartDate: 2022-12-06 19:11:11+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 415333da516869c20929506a8b59497667febb82 CommitTime: 2022-12-06 19:29:40 +0100 CommitAuthor: Frederick Stein CommitSubject: Improve communication for RPA gradients (#2435) Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=415333da516869c20929506a8b59497667febb82 Sending build context to Docker daemon 366.6MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu e96e057aae67: Already exists Digest: sha256:4b1d0c4a2d2aaf63b37111f34eb9fa89fa1bf53dd6e4ca954d47caebca4005c2 Status: Downloaded newer image for ubuntu:22.04 ---> a8780b506fa4 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 456d88508063 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 196acfd778fb Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 1c5721a94525 Step 5/42 : RUN mkdir scripts ---> Using cache ---> aa1c7bdf0e90 Step 6/42 : COPY ./tools/toolchain/scripts/VERSION ./tools/toolchain/scripts/parse_if.py ./tools/toolchain/scripts/tool_kit.sh ./tools/toolchain/scripts/common_vars.sh ./tools/toolchain/scripts/signal_trap.sh ./tools/toolchain/scripts/get_openblas_arch.sh ./scripts/ ---> Using cache ---> 8641bd388b4f Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> ae0fdf87c16d Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 6a351dfd8131 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 4d5dfef407b9 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 0e445bb4268b Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> a9380f2de82b Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> d6337908126d Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 8a1db76fade1 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 1e7ce9efd5c2 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 83f292e73484 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 39a0f5a647c5 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 181871d0a5f8 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> dcbac3fbc0b5 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 00cdb4f44852 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> df5af5310ca0 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> f9cd14892187 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> de3a037bfc84 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> f43c92f11ce1 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 9a64e4b9c97c Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> b661a51bf637 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> bd92300963b7 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 7d2f843f50ba Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 6522bb55e463 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 2f2ed82af43a Step 30/42 : COPY ./Makefile . ---> Using cache ---> 0abb6b8b65e7 Step 31/42 : COPY ./src ./src ---> Using cache ---> 2b645bd3039d Step 32/42 : COPY ./exts ./exts ---> Using cache ---> d04f3d8453a5 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> e4078dfc4381 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 aeef85a8baf2 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container aeef85a8baf2 ---> 9b915fe6d6e2 Step 35/42 : COPY ./data ./data ---> f40c420ded0d Step 36/42 : COPY ./tests ./tests ---> e42e89881a7b Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 178102171fb9 Step 38/42 : COPY ./benchmarks ./benchmarks ---> d4da93d42726 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> d7bc32c120e0 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 1e35db2b175e ========== 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 0.027 0.027 85.531 85.531 qs_mol_dyn_low 1 2.0 0.003 0.003 84.929 84.929 qs_forces 11 3.9 0.001 0.001 84.890 84.890 qs_energies 11 4.9 0.001 0.001 79.013 79.013 scf_env_do_scf 11 5.9 0.001 0.001 68.266 68.266 velocity_verlet 10 3.0 0.002 0.002 55.783 55.783 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 51.964 51.964 rebuild_ks_matrix 119 8.3 0.001 0.001 19.560 19.560 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 19.559 19.559 dbcsr_multiply_generic 2286 12.5 0.175 0.175 19.123 19.123 qs_rho_update_rho_low 119 7.7 0.000 0.000 18.961 18.961 calculate_rho_elec 119 8.7 0.950 0.950 18.961 18.961 qs_scf_new_mos 108 7.5 0.001 0.001 18.734 18.734 qs_scf_loop_do_ot 108 8.5 0.001 0.001 18.733 18.733 qs_ks_update_qs_env 119 7.6 0.001 0.001 17.931 17.931 ot_scf_mini 108 9.5 0.002 0.002 17.426 17.426 init_scf_loop 11 6.9 0.000 0.000 16.128 16.128 grid_collocate_task_list 119 9.7 14.691 14.691 14.691 14.691 prepare_preconditioner 11 7.9 0.000 0.000 13.705 13.705 make_preconditioner 11 8.9 0.000 0.000 13.705 13.705 sum_up_and_integrate 119 10.3 0.500 0.500 12.698 12.698 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.541 12.541 integrate_v_rspace 119 11.3 0.088 0.088 12.198 12.198 ot_mini 108 10.5 0.001 0.001 11.322 11.322 make_m2s 4572 13.5 0.044 0.044 10.825 10.825 grid_integrate_task_list 119 12.3 10.332 10.332 10.332 10.332 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.073 6.073 qs_ot_get_derivative 108 11.5 0.001 0.001 5.862 5.862 pw_transfer 1439 11.6 0.063 0.063 5.735 5.735 dbcsr_make_dense_low 5837 15.5 0.064 0.064 5.690 5.690 make_dense_data 5837 16.5 5.034 5.034 5.612 5.612 make_images 4572 14.5 2.208 2.208 5.575 5.575 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.548 5.548 ot_diis_step 108 11.5 0.004 0.004 5.457 5.457 dbcsr_make_images_dense 3978 14.8 0.017 0.017 4.973 4.973 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 4.954 4.954 apply_single 119 13.6 0.000 0.000 4.954 4.954 fft_wrap_pw1pw2_140 487 13.2 0.418 0.418 4.730 4.730 multiply_cannon 2286 13.5 0.170 0.170 4.606 4.606 cp_fm_cholesky_decompose 22 10.9 4.266 4.266 4.266 4.266 cp_fm_cholesky_invert 11 10.9 4.222 4.222 4.222 4.222 multiply_cannon_loop 2286 14.5 0.044 0.044 4.162 4.162 multiply_cannon_multrec 2286 15.5 4.069 4.069 4.116 4.116 init_scf_run 11 5.9 0.002 0.002 4.064 4.064 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.063 4.063 dbcsr_complete_redistribute 329 12.2 1.883 1.883 3.661 3.661 wfi_extrapolate 11 7.9 0.001 0.001 3.523 3.523 dbcsr_copy 2102 12.0 0.225 0.225 3.481 3.481 density_rs2pw 119 9.7 0.005 0.005 3.320 3.320 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.305 3.305 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.251 3.251 dbcsr_copy_into_existing 22 7.9 3.196 3.196 3.196 3.196 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.955 2.955 qs_ot_get_p 119 10.4 0.001 0.001 2.891 2.891 qs_create_task_list 11 7.9 0.000 0.000 2.884 2.884 generate_qs_task_list 11 8.9 1.959 1.959 2.884 2.884 fft3d_s 1202 14.6 2.769 2.769 2.776 2.776 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.570 2.570 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.403 2.403 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.289 2.289 dbcsr_data_release 279534 16.0 2.042 2.042 2.042 2.042 pw_poisson_solve 119 10.3 0.325 0.325 1.945 1.945 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.901 1.901 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.871 1.871 dbcsr_finalize 5186 13.8 0.099 0.099 1.801 1.801 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.797 1.797 potential_pw2rs 119 12.3 0.044 0.044 1.778 1.778 ------------------------------------------------------------------------------- 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 43.578 43.587 qs_mol_dyn_low 1 2.0 0.003 0.004 43.467 43.472 qs_forces 11 3.9 0.001 0.001 43.426 43.427 qs_energies 11 4.9 0.001 0.001 40.611 40.613 scf_env_do_scf 11 5.9 0.000 0.002 37.261 37.265 scf_env_do_scf_inner_loop 108 6.5 0.003 0.019 34.429 34.429 velocity_verlet 10 3.0 0.002 0.003 25.807 25.808 rebuild_ks_matrix 119 8.3 0.000 0.001 15.680 15.810 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.016 15.680 15.810 qs_ks_update_qs_env 119 7.6 0.001 0.001 13.962 14.077 dbcsr_multiply_generic 2286 12.5 0.071 0.078 12.981 13.220 qs_rho_update_rho_low 119 7.7 0.001 0.001 12.773 12.785 calculate_rho_elec 119 8.7 0.030 0.032 12.772 12.784 sum_up_and_integrate 119 10.3 0.031 0.034 11.652 11.667 integrate_v_rspace 119 11.3 0.004 0.005 11.621 11.638 qs_scf_new_mos 108 7.5 0.001 0.001 10.275 10.431 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.275 10.431 multiply_cannon 2286 13.5 0.140 0.155 9.633 10.175 ot_scf_mini 108 9.5 0.002 0.002 9.642 9.801 multiply_cannon_loop 2286 14.5 0.093 0.102 9.113 9.639 grid_collocate_task_list 119 9.7 8.927 9.294 8.927 9.294 mp_waitall_1 169478 16.3 8.205 8.871 8.205 8.871 grid_integrate_task_list 119 12.3 8.014 8.154 8.014 8.154 multiply_cannon_metrocomm3 18288 15.5 0.036 0.039 5.399 6.156 ot_mini 108 10.5 0.001 0.001 5.617 5.780 rs_pw_transfer 974 11.9 0.010 0.012 4.243 4.636 density_rs2pw 119 9.7 0.005 0.007 3.519 3.904 pw_transfer 1439 11.6 0.100 0.112 3.268 3.333 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.102 3.171 potential_pw2rs 119 12.3 0.006 0.007 3.120 3.128 multiply_cannon_multrec 18288 15.5 2.877 3.062 2.887 3.072 qs_ot_get_derivative 108 11.5 0.001 0.001 2.850 2.997 init_scf_loop 11 6.9 0.000 0.000 2.819 2.819 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.634 2.772 apply_single 119 13.6 0.000 0.000 2.634 2.772 fft_wrap_pw1pw2_140 487 13.2 0.270 0.289 2.670 2.740 ot_diis_step 108 11.5 0.003 0.003 2.738 2.738 init_scf_run 11 5.9 0.000 0.004 2.371 2.371 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.371 2.371 fft3d_ps 1201 14.6 1.215 1.277 2.220 2.288 make_m2s 4572 13.5 0.045 0.052 2.211 2.272 wfi_extrapolate 11 7.9 0.001 0.001 2.144 2.144 make_images 4572 14.5 0.114 0.120 1.886 1.940 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.855 1.871 mp_waitany 9880 13.7 1.289 1.704 1.289 1.704 multiply_cannon_metrocomm1 18288 15.5 0.018 0.019 0.534 1.460 rs_pw_transfer_RS2PW_140 130 11.5 0.197 0.240 1.013 1.408 qs_ot_get_p 119 10.4 0.001 0.001 1.234 1.399 rs_pw_transfer_PW2RS_140 130 13.9 0.370 0.396 1.154 1.197 mp_sum_l 11218 13.2 0.706 1.155 0.706 1.155 make_images_data 4572 15.5 0.035 0.041 1.038 1.132 prepare_preconditioner 11 7.9 0.000 0.000 1.095 1.117 make_preconditioner 11 8.9 0.000 0.000 1.095 1.117 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.951 1.037 hybrid_alltoall_any 4725 16.4 0.063 0.197 0.923 1.019 make_full_inverse_cholesky 11 9.9 0.000 0.000 0.994 1.014 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.885 0.947 mp_alltoall_d11v 2130 13.8 0.675 0.944 0.675 0.944 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.855 0.936 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.907 0.908 ------------------------------------------------------------------------------- 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=42.917, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.691, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.332, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.034, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.266, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.222, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.069, 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=14.266000000000005, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.927, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.014, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.877, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.289, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.205, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.028 0.028 108.691 108.691 qs_mol_dyn_low 1 2.0 0.002 0.002 108.046 108.046 qs_forces 11 3.9 0.001 0.001 108.007 108.007 qs_energies 11 4.9 0.001 0.001 100.539 100.539 scf_env_do_scf 11 5.9 0.001 0.001 88.378 88.378 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 71.013 71.013 velocity_verlet 10 3.0 0.002 0.002 69.397 69.397 rebuild_ks_matrix 107 8.3 0.001 0.001 32.751 32.751 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 32.751 32.751 qs_rho_update_rho_low 107 7.7 0.000 0.000 31.192 31.192 calculate_rho_elec 107 8.7 0.852 0.852 31.191 31.191 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.528 29.528 grid_collocate_task_list 107 9.7 27.118 27.118 27.118 27.118 sum_up_and_integrate 107 10.3 0.445 0.445 26.574 26.574 integrate_v_rspace 107 11.3 0.077 0.077 26.129 26.129 grid_integrate_task_list 107 12.3 24.430 24.430 24.430 24.430 dbcsr_multiply_generic 1966 12.4 0.153 0.153 17.252 17.252 init_scf_loop 11 6.9 0.000 0.000 17.233 17.233 qs_scf_new_mos 96 7.5 0.000 0.000 16.948 16.948 qs_scf_loop_do_ot 96 8.5 0.001 0.001 16.948 16.948 ot_scf_mini 96 9.5 0.002 0.002 15.790 15.790 prepare_preconditioner 11 7.9 0.000 0.000 13.364 13.364 make_preconditioner 11 8.9 0.000 0.000 13.364 13.364 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.196 12.196 ot_mini 96 10.5 0.001 0.001 10.392 10.392 make_m2s 3932 13.4 0.039 0.039 9.678 9.678 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.481 6.481 qs_ot_get_derivative 96 11.5 0.001 0.001 5.558 5.558 pw_transfer 1295 11.6 0.056 0.056 5.479 5.479 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.306 5.306 dbcsr_make_dense_low 4961 15.5 0.068 0.068 5.153 5.153 init_scf_run 11 5.9 0.002 0.002 5.104 5.104 scf_env_initial_rho_setup 11 6.9 0.000 0.000 5.102 5.102 make_dense_data 4961 16.5 4.525 4.525 5.073 5.073 make_images 3932 14.4 1.930 1.930 4.893 4.893 ot_diis_step 96 11.5 0.003 0.003 4.832 4.832 fft_wrap_pw1pw2_140 439 13.2 0.358 0.358 4.593 4.593 wfi_extrapolate 11 7.9 0.001 0.001 4.531 4.531 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.484 4.484 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.479 4.479 apply_single 107 13.6 0.000 0.000 4.479 4.479 multiply_cannon 1966 13.4 0.151 0.151 4.277 4.277 cp_fm_cholesky_decompose 22 10.9 4.162 4.162 4.162 4.162 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.077 4.077 cp_fm_cholesky_invert 11 10.9 3.986 3.986 3.986 3.986 multiply_cannon_loop 1966 14.4 0.041 0.041 3.882 3.882 multiply_cannon_multrec 1966 15.4 3.794 3.794 3.839 3.839 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.668 3.668 dbcsr_complete_redistribute 317 12.2 1.878 1.878 3.511 3.511 dbcsr_copy 1855 11.9 0.202 0.202 3.405 3.405 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.389 3.389 qs_create_task_list 11 7.9 0.000 0.000 3.300 3.300 generate_qs_task_list 11 8.9 2.397 2.397 3.300 3.300 density_rs2pw 107 9.7 0.004 0.004 3.221 3.221 dbcsr_copy_into_existing 22 7.9 3.173 3.173 3.173 3.173 copy_dbcsr_to_fm 147 11.2 0.002 0.002 2.920 2.920 fft3d_s 1082 14.6 2.711 2.711 2.716 2.716 qs_ot_get_p 107 10.4 0.001 0.001 2.455 2.455 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.400 2.400 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.246 2.246 ------------------------------------------------------------------------------- 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 69.566 69.576 qs_mol_dyn_low 1 2.0 0.003 0.003 69.470 69.474 qs_forces 11 3.9 0.001 0.001 69.430 69.430 qs_energies 11 4.9 0.001 0.001 64.777 64.779 scf_env_do_scf 11 5.9 0.000 0.002 60.000 60.000 scf_env_do_scf_inner_loop 96 6.5 0.002 0.016 55.393 55.394 velocity_verlet 10 3.0 0.002 0.003 41.327 41.328 rebuild_ks_matrix 107 8.3 0.000 0.001 30.235 30.306 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.022 30.234 30.306 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.656 26.723 sum_up_and_integrate 107 10.3 0.032 0.036 26.576 26.590 integrate_v_rspace 107 11.3 0.004 0.005 26.543 26.562 qs_rho_update_rho_low 107 7.7 0.000 0.001 25.292 25.299 calculate_rho_elec 107 8.7 0.027 0.028 25.291 25.298 grid_integrate_task_list 107 12.3 22.718 23.140 22.718 23.140 grid_collocate_task_list 107 9.7 21.755 22.137 21.755 22.137 dbcsr_multiply_generic 1966 12.4 0.064 0.069 11.681 11.764 qs_scf_new_mos 96 7.5 0.000 0.001 9.081 9.155 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.080 9.155 multiply_cannon 1966 13.4 0.128 0.138 8.743 9.045 ot_scf_mini 96 9.5 0.002 0.002 8.522 8.586 multiply_cannon_loop 1966 14.4 0.088 0.094 8.269 8.541 mp_waitall_1 146670 16.2 7.269 7.598 7.269 7.598 multiply_cannon_metrocomm3 15728 15.4 0.033 0.035 4.859 5.288 ot_mini 96 10.5 0.001 0.001 5.003 5.071 rs_pw_transfer 878 11.9 0.010 0.011 3.940 4.621 init_scf_loop 11 6.9 0.000 0.000 4.594 4.594 density_rs2pw 107 9.7 0.005 0.006 3.243 3.928 init_scf_run 11 5.9 0.000 0.004 3.775 3.775 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.774 3.775 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.696 3.704 wfi_extrapolate 11 7.9 0.001 0.001 3.433 3.433 pw_transfer 1295 11.6 0.090 0.101 2.950 2.976 potential_pw2rs 107 12.3 0.006 0.007 2.833 2.850 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 2.800 2.831 multiply_cannon_multrec 15728 15.4 2.682 2.754 2.691 2.764 qs_ot_get_derivative 96 11.5 0.001 0.001 2.537 2.601 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.404 2.501 apply_single 107 13.6 0.000 0.000 2.403 2.501 ot_diis_step 96 11.5 0.003 0.003 2.446 2.446 fft_wrap_pw1pw2_140 439 13.2 0.245 0.260 2.406 2.441 make_m2s 3932 13.4 0.040 0.044 2.006 2.067 fft3d_ps 1081 14.6 1.090 1.133 1.990 2.037 mp_waitany 8968 13.7 1.309 2.021 1.309 2.021 mp_alltoall_d11v 1998 13.7 1.165 1.857 1.165 1.857 make_images 3932 14.4 0.102 0.106 1.719 1.773 rs_pw_transfer_RS2PW_140 118 11.5 0.194 0.243 1.041 1.730 rs_gather_matrices 107 12.3 0.072 0.082 0.956 1.614 ------------------------------------------------------------------------------- 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=40.676, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.118, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.43, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.525, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.162, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=3.986, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.794, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 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=13.833000000000006, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.755, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.718, 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=2.682, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.309, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.269, 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 0.182 104.262 104.262 qs_energies 1 2.0 0.000 0.000 103.457 103.457 scf_env_do_scf 1 3.0 0.000 0.000 102.358 102.358 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.210 97.210 rebuild_ks_matrix 7 6.0 0.000 0.000 97.154 97.154 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.154 97.154 hfx_ks_matrix 7 8.0 0.000 0.000 87.977 87.977 integrate_four_center 7 9.0 1.525 1.525 87.903 87.903 integrate_four_center_main 7 10.0 0.667 0.667 80.354 80.354 integrate_four_center_bin 448 11.0 79.687 79.687 79.687 79.687 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.294 56.294 init_scf_loop 1 4.0 0.000 0.000 46.052 46.052 integrate_four_center_load 7 10.0 0.000 0.000 5.776 5.776 hfx_load_balance 1 11.0 0.001 0.001 5.775 5.775 qs_vxc_create 14 8.0 0.000 0.000 3.198 3.198 xc_vxc_pw_create 14 9.0 0.169 0.169 3.198 3.198 hfx_load_balance_bin 1 12.0 2.880 2.880 2.880 2.880 hfx_load_balance_count 1 12.0 2.878 2.878 2.878 2.878 calculate_rho_elec 15 7.4 0.118 0.118 2.440 2.440 xc_rho_set_and_dset_create 14 10.0 0.102 0.102 2.392 2.392 prepare_preconditioner 1 5.0 0.000 0.000 2.373 2.373 make_preconditioner 1 6.0 0.000 0.000 2.373 2.373 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.319 2.319 ------------------------------------------------------------------------------- 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 0.219 0.244 96.280 96.290 qs_energies 1 2.0 0.000 0.000 95.915 95.922 scf_env_do_scf 1 3.0 0.000 0.000 95.575 95.576 qs_ks_update_qs_env 8 5.0 0.000 0.000 93.713 93.714 rebuild_ks_matrix 7 6.0 0.000 0.000 93.705 93.706 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 93.705 93.706 hfx_ks_matrix 7 8.0 0.000 0.000 88.498 88.500 integrate_four_center 7 9.0 0.054 0.333 88.489 88.490 integrate_four_center_main 7 10.0 0.003 0.003 78.376 80.450 integrate_four_center_bin 448 11.0 78.373 80.448 78.373 80.448 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 52.576 52.577 init_scf_loop 1 4.0 0.000 0.000 42.998 43.001 integrate_four_center_load 7 10.0 0.000 0.000 5.702 5.703 hfx_load_balance 1 11.0 0.001 0.001 5.702 5.703 mp_sync 70 11.3 3.757 4.710 3.757 4.710 hfx_load_balance_count 1 12.0 2.773 2.852 2.773 2.852 hfx_load_balance_bin 1 12.0 2.768 2.845 2.768 2.845 qs_vxc_create 14 8.0 0.000 0.000 2.349 2.349 xc_vxc_pw_create 14 9.0 0.007 0.008 2.349 2.349 xc_rho_set_and_dset_create 14 10.0 0.009 0.010 1.895 2.007 ------------------------------------------------------------------------------- Plot: name="H2O-hyb_timings_32omp", title="Timings of H2O-hyb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32omp", name="rest", label="rest", y=16.442999999999998, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=79.687, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.88, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.878, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.525, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.667, 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=8.332999999999998, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.373, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.768, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.773, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.054, 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=0.219, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=3.757, yerr=0.0 Running GW_PBE_4benzene.inp with 1 threads and 32 ranks... done. Running GW_PBE_4benzene.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.013 0.013 80.524 80.524 qs_energies 1 2.0 0.000 0.000 80.151 80.151 mp2_main 1 3.0 0.000 0.000 77.297 77.297 mp2_gpw_main 1 4.0 0.000 0.000 77.194 77.194 rpa_ri_compute_en 1 5.0 0.000 0.000 73.568 73.568 rpa_num_int 1 6.0 0.001 0.001 73.562 73.562 compute_mat_P_omega 1 7.0 0.003 0.003 63.705 63.705 compute_mat_P_omega_contract 10 8.0 8.699 8.699 63.510 63.510 dbt_total 2336 9.6 0.011 0.011 50.395 50.395 dbt_contract 787 11.0 0.033 0.033 43.674 43.674 dbt_tas_total 1149 12.2 0.214 0.214 42.789 42.789 dbt_tas_multiply 807 12.1 0.003 0.003 41.426 41.426 dbt_tas_dbm 807 14.1 0.003 0.003 34.840 34.840 dbm_multiply 807 16.1 34.832 34.832 34.832 34.832 dbt_tas_mm_1N 524 15.1 0.001 0.001 27.759 27.759 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 26.325 26.325 compute_mat_P_omega_calc_M_occ 250 9.0 8.730 8.730 16.609 16.609 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.503 6.503 dbt_tas_mm_2 251 15.0 0.001 0.001 5.585 5.585 dbt_copy 1103 10.7 0.061 0.061 5.340 5.340 compute_QP_energies 1 7.0 0.000 0.000 5.207 5.207 compute_self_energy_cubic_gw 1 8.0 0.053 0.053 5.206 5.206 contract_cubic_gw 21 9.0 0.000 0.000 4.272 4.272 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.618 3.618 dbt_tas_reserve_blocks_index 3261 14.3 0.139 0.139 3.315 3.315 dbm_reserve_blocks 3628 15.3 3.248 3.248 3.248 3.248 scf_env_do_scf 1 3.0 0.000 0.000 2.721 2.721 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.721 2.721 dbt_reserve_blocks_index 2280 13.1 0.049 0.049 2.520 2.520 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.474 2.474 convert_to_new_pgrid 2421 14.1 0.092 0.092 2.242 2.242 dbt_tas_copy 574 11.4 1.331 1.331 2.199 2.199 dbt_tas_reshape 367 15.0 0.020 0.020 2.159 2.159 dbm_copy 1614 15.1 2.150 2.150 2.150 2.150 dbt_crop 1042 12.0 1.369 1.369 2.149 2.149 compute_W_cubic_GW 10 7.0 0.004 0.004 1.911 1.911 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.896 1.896 get_2c_integrals 1 6.0 0.000 0.000 1.738 1.738 dbt_reshape 278 11.9 0.907 0.907 1.726 1.726 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.025 30.241 30.251 qs_energies 1 2.0 0.000 0.000 30.112 30.113 mp2_main 1 3.0 0.000 0.000 29.195 29.196 mp2_gpw_main 1 4.0 0.000 0.000 29.159 29.160 rpa_ri_compute_en 1 5.0 0.000 0.000 27.922 27.923 rpa_num_int 1 6.0 0.000 0.002 27.921 27.923 dbt_total 2336 9.6 0.011 0.012 24.782 24.787 compute_mat_P_omega 1 7.0 0.001 0.005 23.595 23.620 compute_mat_P_omega_contract 10 8.0 0.398 0.417 23.493 23.496 dbt_contract 787 11.0 0.025 0.026 18.671 18.674 dbt_tas_total 1149 12.2 0.050 0.056 16.753 16.753 dbt_tas_multiply 807 12.1 0.002 0.002 16.700 16.702 dbt_tas_dbm 807 14.1 0.002 0.003 12.593 12.595 dbm_multiply 807 16.1 9.765 10.688 9.765 10.688 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.047 7.048 compute_mat_P_omega_calc_M_occ 250 9.0 0.384 0.407 6.859 6.859 dbt_tas_mm_2 251 15.0 0.001 0.001 5.918 5.919 dbt_copy 1111 10.7 0.011 0.011 5.395 5.547 mp_sync 8706 11.6 4.364 5.364 4.364 5.364 dbt_reshape 1098 11.7 2.071 2.204 5.131 5.281 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.015 5.016 dbt_tas_mm_1N 524 15.1 0.001 0.001 4.513 4.927 compute_QP_energies 1 7.0 0.000 0.000 2.770 2.771 compute_self_energy_cubic_gw 1 8.0 0.002 0.004 2.769 2.770 mp_waitall_2 3776 15.3 2.378 2.582 2.378 2.582 dbt_communicate_buffer 1098 12.7 0.052 0.057 2.421 2.522 contract_cubic_gw 21 9.0 0.000 0.000 2.209 2.209 dbt_reserve_blocks_index 2849 13.1 0.062 0.066 1.520 1.647 dbt_reserve_blocks_index_array 2791 12.2 0.010 0.011 1.513 1.638 dbt_tas_reserve_blocks_index 3300 14.5 0.111 0.121 1.492 1.616 dbm_reserve_blocks 3696 15.4 1.470 1.596 1.470 1.596 dbt_crop 1042 12.0 0.888 0.984 1.361 1.491 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.236 1.236 dbt_tas_replicate 396 14.1 0.526 0.683 1.060 1.115 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.940 0.946 parallel_gemm_fm 105 8.4 0.000 0.000 0.928 0.935 parallel_gemm_fm_cosma 105 9.4 0.928 0.935 0.928 0.935 scf_env_do_scf 1 3.0 0.000 0.000 0.879 0.879 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.879 0.879 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.871 0.873 convert_to_new_pgrid 2421 14.1 0.024 0.029 0.770 0.867 dbm_copy 1608 15.1 0.741 0.837 0.741 0.837 compute_W_cubic_GW 10 7.0 0.001 0.001 0.708 0.711 mp_max_i 1994 9.8 0.495 0.645 0.495 0.645 dbm_add 807 14.1 0.573 0.615 0.573 0.615 ------------------------------------------------------------------------------- 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=21.958000000000013, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=34.832, 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=8.73, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.699, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.248, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.15, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.907, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=8.669999999999998, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.765, 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=0.384, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.398, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.47, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.741, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.071, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.378, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.364, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.018 0.018 372.048 372.048 qs_forces 1 2.0 0.000 0.000 371.497 371.497 rebuild_ks_matrix 7 6.6 0.000 0.000 370.075 370.075 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 370.075 370.075 hfx_ks_matrix 7 8.6 0.000 0.000 368.065 368.065 hfx_ri_update_ks 7 9.6 0.000 0.000 330.261 330.261 hfx_ri_update_ks_Pmat 7 10.6 30.759 30.759 330.244 330.244 dbt_total 841 11.0 0.005 0.005 314.912 314.912 dbt_contract 207 12.4 0.033 0.033 296.689 296.689 dbt_tas_total 375 13.4 1.421 1.421 296.229 296.229 dbt_tas_multiply 216 13.5 0.001 0.001 291.703 291.703 qs_energies 1 3.0 0.000 0.000 289.923 289.923 scf_env_do_scf 1 4.0 0.000 0.000 289.641 289.641 qs_ks_update_qs_env 8 6.0 0.000 0.000 288.552 288.552 dbt_tas_dbm 216 15.5 0.001 0.001 280.348 280.348 dbm_multiply 216 17.5 280.345 280.345 280.345 280.345 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 275.833 275.833 dbt_tas_mm_2 91 16.5 0.001 0.001 266.871 266.871 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 186.387 186.387 init_scf_loop 2 5.0 0.000 0.000 103.252 103.252 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 81.526 81.526 hfx_ri_update_forces 1 7.0 1.638 1.638 37.801 37.801 hfx_ri_forces_Pmat_3c 1 8.0 4.615 4.615 21.136 21.136 dbt_copy 409 11.7 0.038 0.038 13.689 13.689 precalc_derivatives 1 8.0 2.132 2.132 12.910 12.910 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.415 9.415 dbt_reshape 132 13.2 5.518 5.518 9.386 9.386 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.107 9.107 ------------------------------------------------------------------------------- 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 0.007 0.024 42.931 42.940 qs_forces 1 2.0 0.000 0.000 42.810 42.810 rebuild_ks_matrix 7 6.6 0.000 0.000 42.170 42.170 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 42.170 42.170 hfx_ks_matrix 7 8.6 0.000 0.001 41.248 41.257 dbt_total 841 11.0 0.005 0.005 36.647 36.649 dbt_contract 207 12.4 0.020 0.021 28.968 28.980 dbt_tas_total 375 13.4 0.055 0.179 26.957 26.957 dbt_tas_multiply 216 13.5 0.001 0.001 26.010 26.010 hfx_ri_update_ks 7 9.6 0.000 0.000 24.164 24.164 hfx_ri_update_ks_Pmat 7 10.6 1.191 1.261 24.163 24.164 qs_energies 1 3.0 0.000 0.000 22.703 22.703 scf_env_do_scf 1 4.0 0.000 0.001 22.570 22.570 qs_ks_update_qs_env 8 6.0 0.000 0.000 22.073 22.074 dbt_tas_dbm 216 15.5 0.001 0.001 20.898 20.899 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 20.097 20.097 dbm_multiply 216 17.5 18.491 19.560 18.491 19.560 hfx_ri_update_forces 1 7.0 0.055 0.058 17.083 17.091 hfx_ri_forces_Pmat_3c 1 8.0 0.165 0.177 12.752 12.767 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 12.661 12.661 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 11.466 11.466 init_scf_loop 2 5.0 0.000 0.000 9.908 9.908 dbt_tas_mm_2 91 16.5 0.001 0.001 9.715 9.716 mp_sync 2909 12.8 4.363 6.640 4.363 6.640 dbt_copy 421 11.8 0.009 0.011 6.322 6.518 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.655 6.125 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.897 4.897 dbt_reshape 252 12.8 2.200 2.275 4.313 4.413 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.906 4.061 precalc_derivatives 1 8.0 0.078 0.084 3.319 3.319 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.040 3.041 dbm_reserve_blocks 1477 16.3 2.487 2.689 2.487 2.689 dbt_tas_reserve_blocks_index 1302 15.5 0.214 0.228 2.477 2.645 dbt_crop 372 13.7 1.686 1.765 2.304 2.454 mp_waitall_2 1204 16.3 2.116 2.234 2.116 2.234 dbt_reserve_blocks_index 938 14.4 0.090 0.096 1.951 2.107 dbt_reserve_blocks_index_array 915 13.4 0.005 0.009 1.930 2.084 build_3c_derivatives 3 9.0 0.222 0.241 1.873 1.880 dbt_tas_replicate 175 15.2 0.656 0.688 1.619 1.674 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.609 1.612 dbt_communicate_buffer 252 13.8 0.011 0.012 1.419 1.493 dbt_tas_copy 169 12.8 0.787 0.823 1.383 1.484 convert_to_new_pgrid 648 15.5 0.032 0.068 1.251 1.436 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.336 1.337 dbm_copy 452 16.3 1.088 1.277 1.088 1.277 dbt_tas_communicate_buffer 352 16.4 0.013 0.014 0.922 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=48.678999999999974, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=280.345, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=30.759, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=5.518, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.615, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="precalc_derivatives", label="precalc_derivatives", y=2.132, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 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=11.840000000000003, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=18.491, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.191, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.2, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.165, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="precalc_derivatives", label="precalc_derivatives", y=0.078, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.487, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.363, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.116, 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 0.014 206.548 206.548 qs_energies 1 2.0 0.000 0.000 206.366 206.366 mp2_main 1 3.0 0.000 0.000 201.630 201.630 mp2_gpw_main 1 4.0 0.001 0.001 201.237 201.237 mp2_ri_gpw_compute_in 1 5.0 0.381 0.381 155.054 155.054 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 143.791 143.791 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 115.070 115.070 integrate_v_rspace 2666 8.0 0.632 0.632 102.146 102.146 grid_integrate_task_list 2666 9.0 99.515 99.515 99.515 99.515 mp2_ri_gpw_compute_en 1 5.0 0.086 0.086 46.159 46.159 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.229 9.229 44.339 44.339 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.095 2.095 28.108 28.108 local_gemm 2080 8.0 26.013 26.013 26.013 26.013 dbcsr_multiply_generic 5322 8.0 0.179 0.179 20.206 20.206 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.186 20.186 pw_transfer 63872 10.6 1.014 1.014 11.674 11.674 calculate_wavefunction 2656 8.0 8.191 8.191 11.617 11.617 get_2c_integrals 1 6.0 0.000 0.000 10.881 10.881 fft_wrap_pw1pw2 53228 11.4 0.107 0.107 10.452 10.452 multiply_cannon 5322 9.0 0.416 0.416 10.222 10.222 compute_2c_integrals 1 7.0 0.006 0.006 10.078 10.078 compute_2c_integrals_loop_lm 1 8.0 0.007 0.007 10.055 10.055 mp2_eri_2c_integrate_gpw 1 9.0 3.350 3.350 10.048 10.048 multiply_cannon_loop 5322 10.0 0.114 0.114 8.895 8.895 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.187 2.187 8.428 8.428 make_m2s 10644 9.0 0.059 0.059 7.796 7.796 fft_wrap_pw1pw2_20 21271 12.4 0.467 0.467 7.562 7.562 make_images 10644 10.0 3.155 3.155 7.509 7.509 multiply_cannon_multrec 5322 11.0 7.417 7.417 7.456 7.456 copy_dbcsr_to_fm 2679 8.0 0.028 0.028 6.790 6.790 fft3d_s 53229 13.4 6.468 6.468 6.502 6.502 dbcsr_complete_redistribute 2689 9.0 1.058 1.058 5.324 5.324 mp2_ri_gpw_compute_en_ener 2080 7.0 5.210 5.210 5.210 5.210 dbcsr_finalize 10708 9.5 0.153 0.153 4.763 4.763 scf_env_do_scf 1 3.0 0.000 0.000 4.321 4.321 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.321 4.321 dbcsr_merge_all 8011 10.3 3.222 3.222 4.170 4.170 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.024 34.262 34.272 qs_energies 1 2.0 0.000 0.001 34.169 34.169 mp2_main 1 3.0 0.000 0.000 32.111 32.111 mp2_gpw_main 1 4.0 0.001 0.001 31.900 31.901 mp2_ri_gpw_compute_in 1 5.0 0.049 0.049 16.962 17.242 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.780 16.062 mp2_ri_gpw_compute_en 1 5.0 0.176 0.189 14.847 15.244 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.723 13.895 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.831 0.886 13.870 13.875 integrate_v_rspace 93 8.1 0.100 0.110 13.583 13.760 grid_integrate_task_list 93 9.1 13.295 13.475 13.295 13.475 mp2_ri_gpw_compute_en_expansio 65 7.0 0.108 0.124 10.458 10.708 local_gemm 65 8.0 10.351 10.611 10.351 10.611 mp2_ri_gpw_compute_en_comm 17 7.0 0.069 0.076 2.213 2.410 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.766 2.009 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.749 1.989 scf_env_do_scf 1 3.0 0.000 0.000 1.946 1.947 scf_env_do_scf_inner_loop 10 4.0 0.000 0.003 1.946 1.946 mp_sendrecv_dm3 1054 8.0 1.675 1.898 1.675 1.898 get_2c_integrals 1 6.0 0.000 0.000 1.118 1.139 multiply_cannon 176 9.0 0.015 0.016 1.033 1.111 multiply_cannon_loop 176 10.0 0.002 0.002 0.976 1.052 qs_scf_new_mos 10 5.0 0.000 0.000 1.015 1.020 eigensolver 11 5.8 0.001 0.001 1.001 1.003 multiply_cannon_multrec 246 11.0 0.834 0.875 0.839 0.880 make_m2s 352 9.0 0.003 0.003 0.697 0.858 make_images 352 10.0 0.051 0.052 0.685 0.845 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.836 0.837 compute_2c_integrals 1 7.0 0.003 0.003 0.823 0.836 cp_fm_redistribute_end 11 7.8 0.312 0.825 0.324 0.830 cp_fm_diag_elpa_base 11 7.8 0.491 0.791 0.502 0.806 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.738 0.759 mp2_eri_2c_integrate_gpw 1 9.0 0.199 0.217 0.736 0.758 pw_transfer 2120 10.5 0.043 0.045 0.737 0.745 mp_min_d 2 7.0 0.294 0.696 0.294 0.696 fft_wrap_pw1pw2 1768 11.4 0.004 0.005 0.680 0.687 ------------------------------------------------------------------------------- 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=56.18299999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=99.515, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=26.013, 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=9.229, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.191, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.417, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 Plot: name="RI-MP2_ammonia_timings_32mpi", title="Timings of RI-MP2_ammonia with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="rest", label="rest", y=7.276, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.295, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.351, 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=0.831, 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=0.834, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.675, 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 0.090 0.090 123.888 123.888 qs_energies 1 2.0 0.000 0.000 122.514 122.514 scf_env_do_scf 1 3.0 0.000 0.000 115.950 115.950 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 115.950 115.950 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.026 48.026 rebuild_ks_matrix 15 6.0 0.000 0.000 47.819 47.819 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 47.819 47.819 qs_scf_new_mos 15 5.0 0.000 0.000 43.180 43.180 eigensolver 15 6.0 0.001 0.001 35.440 35.440 qs_vxc_create 15 8.0 0.033 0.033 32.815 32.815 calculate_dispersion_nonloc 15 9.0 6.621 6.621 28.582 28.582 cp_fm_diag_elpa 15 7.0 0.000 0.000 23.330 23.330 cp_fm_diag_elpa_base 15 8.0 20.829 20.829 23.329 23.329 pw_transfer 1191 10.0 0.056 0.056 22.390 22.390 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 22.218 22.218 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.968 21.968 calculate_rho_elec 16 6.0 0.216 0.216 21.968 21.968 grid_collocate_task_list 16 7.0 20.666 20.666 20.666 20.666 fft_wrap_pw1pw2_150 765 12.0 3.497 3.497 16.184 16.184 sum_up_and_integrate 15 8.0 0.090 0.090 13.888 13.888 integrate_v_rspace 15 9.0 0.020 0.020 13.798 13.798 grid_integrate_task_list 15 10.0 13.280 13.280 13.280 13.280 fft3d_s 1087 13.0 9.928 9.928 9.935 9.935 cp_fm_cholesky_restore 45 7.0 9.918 9.918 9.918 9.918 pw_scatter_s 585 13.1 6.973 6.973 6.973 6.973 fft_wrap_pw1pw2_200 197 12.3 0.692 0.692 5.847 5.847 dbcsr_complete_redistribute 46 8.3 2.249 2.249 5.557 5.557 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.543 5.543 cp_fm_upper_to_full 30 8.0 4.691 4.691 4.691 4.691 vdW_energy 15 10.0 4.264 4.264 4.264 4.264 xc_vxc_pw_create 15 9.0 0.222 0.222 4.199 4.199 gspace_mixing 14 5.0 0.171 0.171 3.977 3.977 broyden_mixing 14 6.0 3.384 3.384 3.385 3.385 init_scf_run 1 3.0 0.000 0.000 3.095 3.095 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.003 3.003 xc_pw_derive 90 11.0 0.001 0.001 2.733 2.733 calculate_dm_sparse 15 6.0 0.017 0.017 2.549 2.549 ------------------------------------------------------------------------------- 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 0.030 58.928 58.938 qs_energies 1 2.0 0.000 0.000 58.657 58.662 scf_env_do_scf 1 3.0 0.000 0.001 54.632 54.633 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 54.632 54.633 qs_ks_update_qs_env 15 5.0 0.000 0.000 22.760 22.770 rebuild_ks_matrix 15 6.0 0.000 0.000 22.727 22.738 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 22.727 22.738 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.289 20.291 calculate_rho_elec 16 6.0 0.007 0.007 20.289 20.291 grid_collocate_task_list 16 7.0 19.177 19.456 19.177 19.456 sum_up_and_integrate 15 8.0 0.012 0.016 13.455 13.491 integrate_v_rspace 15 9.0 0.001 0.001 13.444 13.483 grid_integrate_task_list 15 10.0 12.773 12.892 12.773 12.892 qs_scf_new_mos 15 5.0 0.000 0.000 12.272 12.306 eigensolver 15 6.0 0.001 0.002 11.322 11.337 qs_vxc_create 15 8.0 0.001 0.001 8.983 8.998 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.198 8.199 cp_fm_diag_elpa_base 15 8.0 8.049 8.076 8.195 8.195 calculate_dispersion_nonloc 15 9.0 0.909 1.014 7.240 7.262 pw_transfer 1191 10.0 0.094 0.101 6.712 6.773 fft_wrap_pw1pw2 1086 11.0 0.013 0.014 6.531 6.596 fft3d_ps 1086 13.0 2.507 2.647 4.821 4.923 fft_wrap_pw1pw2_150 765 12.0 0.306 0.328 4.245 4.275 cp_fm_cholesky_restore 45 7.0 2.980 3.033 2.980 3.033 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.430 2.430 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.147 2.333 fft_wrap_pw1pw2_200 197 12.3 0.186 0.206 2.174 2.243 mp_alltoall_z22v 1086 15.0 1.687 1.977 1.687 1.977 xc_vxc_pw_create 15 9.0 0.016 0.022 1.742 1.764 init_scf_run 1 3.0 0.000 0.001 1.372 1.373 build_core_ppnl 1 5.0 1.252 1.365 1.252 1.365 vdW_energy 15 10.0 1.278 1.327 1.278 1.327 yz_to_x 501 13.9 0.255 0.303 1.142 1.312 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.288 1.288 rs_pw_transfer 158 9.4 0.001 0.002 0.994 1.246 x_to_yz 585 14.1 0.346 0.366 1.146 1.244 xc_pw_derive 90 11.0 0.001 0.002 1.147 1.223 ------------------------------------------------------------------------------- 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=49.266999999999996, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.829, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.666, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.28, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=9.928, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=9.918, 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=13.442000000000007, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.049, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.177, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.773, 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=2.98, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.507, 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 0.081 0.081 345.274 345.274 qs_energies 1 2.0 0.000 0.000 345.129 345.129 ls_scf 1 3.0 0.000 0.000 343.893 343.893 ls_scf_main 1 4.0 0.002 0.002 335.101 335.101 density_matrix_trs4 11 5.0 0.012 0.012 244.315 244.315 arnoldi_extremal 12 6.1 0.000 0.000 160.876 160.876 arnoldi_normal_ev 12 7.1 0.014 0.014 160.876 160.876 dbcsr_matrix_vector_mult 652 9.0 0.173 0.173 158.254 158.254 build_subspace 23 8.1 0.076 0.076 158.042 158.042 dbcsr_matrix_vector_mult_local 652 10.0 156.779 156.779 156.789 156.789 ls_scf_dm_to_ks 11 5.0 0.000 0.000 85.561 85.561 matrix_ls_to_qs 11 6.0 0.000 0.000 82.333 82.333 dbcsr_multiply_generic 185 6.1 0.822 0.822 72.718 72.718 multiply_cannon 185 7.1 0.277 0.277 44.045 44.045 dbcsr_copy_into_existing 11 7.0 43.654 43.654 43.654 43.654 dbcsr_complete_redistribute 23 7.5 31.293 31.293 42.415 42.415 matrix_decluster 11 7.0 0.000 0.000 38.677 38.677 multiply_cannon_loop 185 8.1 0.233 0.233 31.601 31.601 make_m2s 370 7.1 0.037 0.037 24.281 24.281 make_images 370 8.1 10.529 10.529 22.766 22.766 multiply_cannon_multrec 185 9.1 22.148 22.148 22.174 22.174 dbcsr_finalize 646 7.5 0.161 0.161 14.535 14.535 dbcsr_merge_all 597 8.5 2.209 2.209 13.494 13.494 setup_rec_index_2d 370 8.1 12.080 12.080 12.080 12.080 tree_to_linear_d 110 9.4 10.059 10.059 10.059 10.059 dbcsr_sort_indices 1103 9.9 10.040 10.040 10.040 10.040 calculate_norms 370 9.1 9.194 9.194 9.194 9.194 quick_finalize 395 10.0 0.356 0.356 8.695 8.695 ls_scf_init_scf 1 4.0 0.000 0.000 8.111 8.111 dbcsr_special_finalize 370 9.1 0.002 0.002 8.039 8.039 ls_scf_init_matrix_S 1 5.0 0.000 0.000 7.779 7.779 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.136 7.136 ------------------------------------------------------------------------------- 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 64.929 64.938 qs_energies 1 2.0 0.000 0.000 64.838 64.838 ls_scf 1 3.0 0.000 0.000 64.787 64.788 ls_scf_main 1 4.0 0.001 0.009 62.317 62.319 density_matrix_trs4 11 5.0 0.006 0.017 59.834 59.916 dbcsr_multiply_generic 185 6.1 0.058 0.069 56.555 56.745 multiply_cannon 185 7.1 0.035 0.039 47.374 47.848 multiply_cannon_loop 185 8.1 0.119 0.136 44.983 45.787 multiply_cannon_multrec 1480 9.1 27.688 30.032 27.961 30.327 mp_waitall_1 11936 10.3 14.514 16.340 14.514 16.340 multiply_cannon_metrocomm3 1480 9.1 0.014 0.017 8.647 12.333 make_m2s 370 7.1 0.034 0.037 6.422 6.487 make_images 370 8.1 0.620 0.652 6.296 6.360 calculate_norms 2960 9.1 4.889 5.995 4.889 5.995 multiply_cannon_metrocomm1 1480 9.1 0.008 0.010 3.308 5.994 make_images_data 370 9.1 0.009 0.011 2.800 3.016 hybrid_alltoall_any 393 9.9 0.186 1.003 2.467 2.645 mp_sum_l 1119 5.6 1.681 2.535 1.681 2.535 arnoldi_extremal 12 6.1 0.000 0.000 2.406 2.419 arnoldi_normal_ev 12 7.1 0.001 0.004 2.405 2.418 build_subspace 23 8.1 0.020 0.026 2.315 2.316 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.152 2.206 dbcsr_matrix_vector_mult 652 9.0 0.009 0.043 1.990 2.054 dbcsr_complete_redistribute 23 7.5 1.190 1.283 1.924 2.000 matrix_ls_to_qs 11 6.0 0.000 0.000 1.875 1.953 ls_scf_init_scf 1 4.0 0.000 0.000 1.902 1.903 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.877 1.884 matrix_decluster 11 7.0 0.000 0.000 1.735 1.811 make_images_pack 370 9.1 1.617 1.757 1.621 1.762 dbcsr_matrix_vector_mult_local 652 10.0 1.690 1.758 1.692 1.760 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.717 1.718 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 0.859 1.585 dbcsr_finalize 646 7.5 0.008 0.008 1.426 1.543 buffer_matrices_ensure_size 370 8.1 1.320 1.415 1.320 1.415 ------------------------------------------------------------------------------- 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=70.12599999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=156.779, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=43.654, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=31.293, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.148, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=12.08, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.194, 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 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=13.277000000000001, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.69, 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=1.19, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=27.688, 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=4.889, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.514, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.681, 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 69.047 69.047 lib_test 1 2.0 0.000 0.000 69.039 69.039 dbcsr_run_tests 3 3.0 0.002 0.002 69.039 69.039 test_multiplies_multiproc 3 4.0 0.001 0.001 53.162 53.162 dbcsr_redistribute 9 5.0 34.519 34.519 36.067 36.067 dbcsr_make_random_matrix 9 4.0 12.755 12.755 15.771 15.771 dbcsr_multiply_generic 9 5.0 0.002 0.002 15.744 15.744 multiply_cannon 9 6.0 0.002 0.002 11.073 11.073 multiply_cannon_loop 9 7.0 0.011 0.011 10.714 10.714 multiply_cannon_multrec 9 8.0 10.703 10.703 10.703 10.703 dbcsr_finalize 27 5.7 0.009 0.009 5.533 5.533 dbcsr_merge_all 18 6.5 1.956 1.956 4.800 4.800 dbcsr_data_release 975 7.6 2.786 2.786 2.786 2.786 tree_to_linear_d 9 7.0 1.853 1.853 1.853 1.853 make_m2s 18 6.0 0.001 0.001 1.578 1.578 make_images 18 7.0 0.543 0.543 1.531 1.531 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.003 0.013 17.142 17.146 lib_test 1 2.0 0.000 0.000 17.115 17.133 dbcsr_run_tests 3 3.0 0.000 0.001 17.111 17.129 test_multiplies_multiproc 3 4.0 0.000 0.002 16.278 16.321 dbcsr_multiply_generic 9 5.0 0.001 0.001 14.955 15.047 multiply_cannon 9 6.0 0.001 0.002 13.280 13.548 multiply_cannon_loop 9 7.0 0.002 0.002 12.990 13.261 multiply_cannon_multrec 72 8.0 10.883 11.182 10.884 11.182 mp_waitall_1 576 9.2 2.407 2.982 2.407 2.982 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.876 2.436 dbcsr_data_release 444 7.6 0.770 0.904 0.770 0.904 dbcsr_make_random_matrix 9 4.0 0.661 0.670 0.807 0.827 dbcsr_finalize 27 5.7 0.000 0.000 0.696 0.786 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.223 0.781 mp_sum_l 390 2.5 0.370 0.771 0.370 0.771 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.363 0.765 dbcsr_destroy 111 5.9 0.000 0.000 0.613 0.700 make_m2s 18 6.0 0.001 0.001 0.643 0.678 make_images 18 7.0 0.021 0.021 0.640 0.675 dbcsr_merge_all 18 6.5 0.099 0.125 0.537 0.613 dbcsr_redistribute 9 5.0 0.233 0.268 0.398 0.421 make_images_data 18 8.0 0.000 0.001 0.339 0.392 dbcsr_data_copy_aa2 18 7.5 0.320 0.383 0.320 0.383 hybrid_alltoall_any 18 9.0 0.027 0.128 0.300 0.350 ------------------------------------------------------------------------------- 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=6.327999999999989, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=34.519, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.755, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.703, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.786, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.956, 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=1.7190000000000012, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.233, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.661, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.883, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.77, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.099, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.37, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.407, 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 0.053 0.053 130.848 130.848 qs_mol_dyn_low 1 2.0 0.003 0.003 129.489 129.489 velocity_verlet 5 3.0 0.003 0.003 105.678 105.678 qmmm_el_coupling 6 3.8 0.000 0.000 87.244 87.244 qmmm_elec_with_gaussian 6 4.8 0.011 0.011 87.241 87.241 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 86.631 86.631 qmmm_elec_gaussian_low_G 6 6.8 85.729 85.729 85.729 85.729 qs_forces 6 3.8 0.000 0.000 33.900 33.900 qs_energies 6 4.8 0.000 0.000 30.086 30.086 scf_env_do_scf 6 5.8 0.001 0.001 27.888 27.888 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.349 24.349 rebuild_ks_matrix 45 8.4 0.000 0.000 23.376 23.376 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.376 23.376 qs_ks_update_qs_env 45 7.8 0.000 0.000 19.999 19.999 pw_transfer 966 12.3 0.052 0.052 16.880 16.880 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.690 16.690 fft_wrap_pw1pw2_150 507 15.2 2.219 2.219 16.286 16.286 qs_vxc_create 45 10.4 0.001 0.001 12.912 12.912 xc_vxc_pw_create 45 11.4 0.630 0.630 12.911 12.911 xc_pw_derive 270 13.4 0.002 0.002 9.162 9.162 fft3d_s 802 15.6 7.601 7.601 7.609 7.609 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.022 7.022 calculate_rho_elec 45 8.9 0.563 0.563 7.022 7.022 xc_rho_set_and_dset_create 45 12.4 0.537 0.537 6.645 6.645 pw_scatter_s 429 15.8 5.622 5.622 5.622 5.622 xc_pw_divergence 45 12.4 0.001 0.001 5.587 5.587 qmmm_forces 6 3.8 0.001 0.001 5.191 5.191 qmmm_forces_with_gaussian 6 4.8 0.016 0.016 4.854 4.854 pw_integral_ab 2539 7.4 4.416 4.416 4.416 4.416 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.144 4.144 qs_ks_ddapc 45 10.4 0.001 0.001 4.085 4.085 init_scf_loop 6 6.8 0.000 0.000 3.528 3.528 qmmm_forces_gaussian_low_G 6 6.8 3.446 3.446 3.446 3.446 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 3.299 3.299 density_rs2pw 45 9.9 0.002 0.002 3.249 3.249 grid_collocate_task_list 45 9.9 3.211 3.211 3.211 3.211 integrate_v_rspace 45 11.4 0.007 0.007 2.975 2.975 ------------------------------------------------------------------------------- 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 0.057 52.424 52.434 qs_mol_dyn_low 1 2.0 0.002 0.004 51.387 51.473 qs_forces 6 3.8 0.000 0.001 37.151 37.152 qs_energies 6 4.8 0.000 0.001 35.446 35.446 scf_env_do_scf 6 5.8 0.000 0.001 34.563 34.563 scf_env_do_scf_inner_loop 113 6.2 0.002 0.016 33.171 33.172 rebuild_ks_matrix 119 8.1 0.000 0.000 24.477 24.486 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.016 24.477 24.486 qs_ks_update_qs_env 119 7.3 0.001 0.001 23.052 23.061 velocity_verlet 5 3.0 0.002 0.004 21.787 21.791 pw_transfer 2446 12.3 0.204 0.219 16.330 16.832 fft_wrap_pw1pw2 2059 13.4 0.025 0.027 15.874 16.356 fft_wrap_pw1pw2_150 1321 14.9 1.302 1.407 15.352 15.837 qs_vxc_create 119 10.1 0.002 0.003 12.952 12.955 xc_vxc_pw_create 119 11.1 0.153 0.224 12.950 12.953 fft3d_ps 2059 15.4 6.972 7.641 11.734 12.382 xc_pw_derive 714 13.1 0.011 0.013 9.693 9.975 qs_rho_update_rho_low 119 7.3 0.000 0.001 9.944 9.946 calculate_rho_elec 119 8.3 0.048 0.054 9.943 9.946 sum_up_and_integrate 119 10.1 0.084 0.091 8.399 8.413 integrate_v_rspace 119 11.1 0.003 0.003 8.315 8.329 qmmm_forces 6 3.8 0.002 0.002 7.184 7.184 qmmm_forces_with_gaussian 6 4.8 0.008 0.012 6.948 7.079 xc_pw_divergence 119 12.1 0.005 0.006 6.310 6.542 xc_rho_set_and_dset_create 119 12.1 0.363 0.442 6.306 6.457 qmmm_el_coupling 6 3.8 0.000 0.000 6.212 6.285 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 6.210 6.283 rs_pw_transfer 988 11.5 0.010 0.013 5.673 5.963 density_rs2pw 119 9.3 0.006 0.008 5.494 5.779 potential_pw2rs 119 12.1 0.005 0.006 4.736 4.748 grid_collocate_task_list 119 9.3 4.324 4.577 4.324 4.577 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.835 3.873 mp_alltoall_z22v 2059 17.4 3.267 3.783 3.267 3.783 grid_integrate_task_list 119 12.1 3.360 3.537 3.360 3.537 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.324 3.499 qmmm_forces_gaussian_low_G 6 6.8 3.147 3.186 3.147 3.186 qmmm_elec_gaussian_low_G 6 6.8 2.736 2.912 2.736 2.912 x_to_yz 1095 16.8 0.850 0.972 2.598 2.835 pw_restrict_s3 18 5.8 1.339 1.369 2.536 2.629 mp_waitany 4028 12.8 2.014 2.454 2.014 2.454 yz_to_x 964 16.0 0.579 0.839 2.098 2.429 rs_pw_transfer_PW2RS_150 125 13.9 0.754 0.820 2.154 2.210 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.114 2.186 pw_prolongate_s3 18 6.8 1.128 1.152 2.114 2.186 rs_pw_transfer_RS2PW_150 125 11.2 0.577 0.763 1.700 1.987 qs_ks_ddapc 119 10.1 0.002 0.002 1.860 1.951 qs_scf_new_mos 113 7.2 0.000 0.000 1.886 1.893 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.886 1.893 ot_scf_mini 113 9.2 0.001 0.001 1.807 1.811 mp_waitall_1 188862 16.2 1.568 1.759 1.568 1.759 dbcsr_multiply_generic 2588 12.3 0.056 0.057 1.703 1.747 pw_integral_ab 2761 7.7 1.286 1.339 1.455 1.560 pw_scatter_p 1095 15.8 1.526 1.557 1.526 1.557 pw_gather_p 964 15.0 1.257 1.503 1.257 1.503 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.434 1.434 init_scf_loop 6 6.8 0.000 0.000 1.389 1.389 mp_sum_dm3 33 5.7 1.246 1.301 1.246 1.301 ot_mini 113 10.2 0.000 0.000 1.118 1.125 ------------------------------------------------------------------------------- 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=20.82300000000002, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=85.729, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.601, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.622, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.416, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.446, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.211, 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=27.331999999999997, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.736, 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=1.286, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.147, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.324, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.36, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.267, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.972, yerr=0.0 Summary: Performance test took 35 minutes. Status: OK Removing intermediate container 1e35db2b175e ---> c2b1d3648dbf Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in dcd9cc39abee Removing intermediate container dcd9cc39abee ---> 58adc841455a Step 42/42 : ENTRYPOINT [] ---> Running in e747c59c90e5 Removing intermediate container e747c59c90e5 ---> e455ca879956 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built e455ca879956 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: 2022-12-06 19:58:46+00:00