StartDate: 2023-08-15 19:39:00+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 8ce3b69bbf0a9b31bf3df725b357dfb78f348a44 CommitTime: 2023-08-15 17:17:57 +0200 CommitAuthor: Jan Wilhelm CommitSubject: Initial commit of scalable, low-memory periodic GW #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=8ce3b69bbf0a9b31bf3df725b357dfb78f348a44 Build-Cache: Yes Populating docker build cache... done. DEPRECATED: The legacy builder is deprecated and will be removed in a future release. BuildKit is currently disabled; enable it by removing the DOCKER_BUILDKIT=0 environment-variable. Sending build context to Docker daemon 383.6MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 3153aa388d02: Pulling fs layer 3153aa388d02: Verifying Checksum 3153aa388d02: Download complete 3153aa388d02: Pull complete Digest: sha256:0bced47fffa3361afa981854fcabcd4577cd43cebbb808cea2b1f33a3dd7f508 Status: Downloaded newer image for ubuntu:22.04 ---> 5a81c4b8502e Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 7aa07568c8cc Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 17e4a8d90f26 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 1e89266971ea Step 5/42 : RUN mkdir scripts ---> Using cache ---> 2d1625000b51 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 ---> c29ce2c49e10 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 06abfb02151d Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 71c06419ade2 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 3b86893d3eaf Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> fa2bc79a1e11 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> ac99b22dec4a Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 06a8e152e1b3 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> dcead00aa5c6 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 9190f4463755 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 9e91174f0e72 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> f90f70c8ad44 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 58e5c6d849e9 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> b950f76e18cb Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 819cef1f4fcd Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 93e58ec4bdc0 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 6a7ddf7a8f2e Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> b1934b8dd17d Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 1f0cff029c33 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> ce1a55103cbe Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 3ab50cc13830 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> a84cb97ea163 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> a226e5860498 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 10d74815af73 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 4e07195b4fe7 Step 30/42 : COPY ./Makefile . ---> Using cache ---> d9dbc33b5367 Step 31/42 : COPY ./src ./src ---> Using cache ---> f98e2fcce902 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 07a87b82c52f Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 2ede25f75342 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 ) && rm -rf lib obj && ( [ ! -f ./exe/local/cp2k.psmp ] || ldd ./exe/local/cp2k.psmp | grep -q libmpi )" ---> Running in bdf125b7dc5a './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container bdf125b7dc5a ---> e8e26496f639 Step 35/42 : COPY ./data ./data ---> b0808fda1061 Step 36/42 : COPY ./tests ./tests ---> a1d3b9b77195 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> b65a9252deb3 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 40e1c74529b0 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> fbc95655332f Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in c213f675eccc ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 70 input files and 0 errors. ========== Running Performance Test ========== Running H2O-64.inp with 1 threads and 32 ranks... done. Running H2O-64.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.035 0.035 92.089 92.089 qs_mol_dyn_low 1 2.0 0.003 0.003 91.466 91.466 qs_forces 11 3.9 0.001 0.001 91.421 91.421 qs_energies 11 4.9 0.001 0.001 85.116 85.116 scf_env_do_scf 11 5.9 0.002 0.002 74.037 74.037 velocity_verlet 10 3.0 0.002 0.002 60.480 60.480 scf_env_do_scf_inner_loop 108 6.5 0.013 0.013 56.528 56.528 rebuild_ks_matrix 119 8.3 0.001 0.001 21.484 21.484 qs_ks_build_kohn_sham_matrix 119 9.3 0.013 0.013 21.483 21.483 qs_scf_new_mos 108 7.5 0.001 0.001 21.456 21.456 qs_scf_loop_do_ot 108 8.5 0.001 0.001 21.455 21.455 dbcsr_multiply_generic 2286 12.5 0.157 0.157 21.440 21.440 ot_scf_mini 108 9.5 0.003 0.003 20.118 20.118 qs_ks_update_qs_env 119 7.6 0.001 0.001 19.724 19.724 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.151 19.151 calculate_rho_elec 119 8.7 0.950 0.950 19.150 19.150 init_scf_loop 11 6.9 0.000 0.000 17.379 17.379 prepare_preconditioner 11 7.9 0.000 0.000 14.803 14.803 make_preconditioner 11 8.9 0.000 0.000 14.803 14.803 grid_collocate_task_list 119 9.7 14.695 14.695 14.695 14.695 sum_up_and_integrate 119 10.3 0.809 0.809 14.056 14.056 make_full_inverse_cholesky 11 9.9 0.030 0.030 13.514 13.514 integrate_v_rspace 119 11.3 0.091 0.091 13.247 13.247 ot_mini 108 10.5 0.001 0.001 13.037 13.037 make_m2s 4572 13.5 0.048 0.048 11.286 11.286 grid_integrate_task_list 119 12.3 10.796 10.796 10.796 10.796 qs_ot_get_derivative 108 11.5 0.001 0.001 7.043 7.043 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.669 6.669 pw_transfer 1439 11.6 0.067 0.067 6.620 6.620 fft_wrap_pw1pw2 1201 12.6 0.007 0.007 6.396 6.396 dbcsr_make_dense_low 5837 15.5 0.085 0.085 6.053 6.053 multiply_cannon 2286 13.5 0.253 0.253 5.995 5.995 ot_diis_step 108 11.5 0.003 0.003 5.991 5.991 make_dense_data 5837 16.5 5.399 5.399 5.954 5.954 make_images 4572 14.5 2.373 2.373 5.688 5.688 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.526 5.526 apply_single 119 13.6 0.000 0.000 5.526 5.526 multiply_cannon_loop 2286 14.5 0.042 0.042 5.380 5.380 fft_wrap_pw1pw2_140 487 13.2 0.503 0.503 5.341 5.341 multiply_cannon_multrec 2286 15.5 5.286 5.286 5.336 5.336 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.242 5.242 cp_fm_cholesky_decompose 22 10.9 5.006 5.006 5.006 5.006 cp_fm_cholesky_invert 11 10.9 4.318 4.318 4.318 4.318 dbcsr_copy 2102 12.0 0.216 0.216 3.891 3.891 init_scf_run 11 5.9 0.003 0.003 3.811 3.811 scf_env_initial_rho_setup 11 6.9 0.002 0.002 3.808 3.808 dbcsr_complete_redistribute 329 12.2 1.919 1.919 3.656 3.656 dbcsr_copy_into_existing 22 7.9 3.640 3.640 3.641 3.641 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.603 3.603 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.584 3.584 density_rs2pw 119 9.7 0.005 0.005 3.505 3.505 qs_ot_get_p 119 10.4 0.001 0.001 3.432 3.432 wfi_extrapolate 11 7.9 0.001 0.001 3.336 3.336 qs_create_task_list 11 7.9 0.000 0.000 3.224 3.224 generate_qs_task_list 11 8.9 1.954 1.954 3.224 3.224 fft3d_s 1202 14.6 3.211 3.211 3.217 3.217 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.965 2.965 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.719 2.719 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.659 2.659 potential_pw2rs 119 12.3 0.049 0.049 2.360 2.360 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.321 2.321 qs_ot_get_derivative_taylor 59 13.0 0.002 0.002 2.209 2.209 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.194 2.194 dbcsr_data_release 279532 16.0 2.191 2.191 2.191 2.191 pw_poisson_solve 119 10.3 0.353 0.353 2.063 2.063 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.977 1.977 qs_ot_p2m_diag 50 11.0 0.155 0.155 1.893 1.893 ------------------------------------------------------------------------------- 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 0.010 0.036 49.197 49.215 qs_mol_dyn_low 1 2.0 0.003 0.004 49.055 49.059 qs_forces 11 3.9 0.002 0.002 49.010 49.010 qs_energies 11 4.9 0.001 0.001 45.966 45.968 scf_env_do_scf 11 5.9 0.000 0.003 42.295 42.296 scf_env_do_scf_inner_loop 108 6.5 0.003 0.025 39.157 39.158 velocity_verlet 10 3.0 0.001 0.003 28.917 28.919 rebuild_ks_matrix 119 8.3 0.001 0.001 17.458 17.522 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.018 17.457 17.522 qs_ks_update_qs_env 119 7.6 0.001 0.001 15.585 15.643 dbcsr_multiply_generic 2286 12.5 0.079 0.084 14.612 14.826 qs_rho_update_rho_low 119 7.7 0.001 0.001 14.373 14.382 calculate_rho_elec 119 8.7 0.031 0.035 14.372 14.382 sum_up_and_integrate 119 10.3 0.034 0.039 12.931 12.958 integrate_v_rspace 119 11.3 0.004 0.005 12.897 12.925 qs_scf_new_mos 108 7.5 0.001 0.001 12.021 12.069 qs_scf_loop_do_ot 108 8.5 0.001 0.001 12.020 12.069 ot_scf_mini 108 9.5 0.002 0.002 11.322 11.366 multiply_cannon 2286 13.5 0.139 0.146 10.558 10.892 multiply_cannon_loop 2286 14.5 0.094 0.104 9.924 10.204 grid_collocate_task_list 119 9.7 9.350 9.686 9.350 9.686 grid_integrate_task_list 119 12.3 8.422 8.596 8.422 8.596 mp_waitall_1 158411 16.6 7.973 8.374 7.973 8.374 ot_mini 108 10.5 0.001 0.001 6.600 6.648 multiply_cannon_metrocomm3 18288 15.5 0.045 0.062 6.017 6.420 rs_pw_transfer 974 11.9 0.012 0.015 4.869 5.229 density_rs2pw 119 9.7 0.005 0.006 4.329 4.703 pw_transfer 1439 11.6 0.066 0.071 4.251 4.346 fft_wrap_pw1pw2 1201 12.6 0.009 0.009 4.116 4.199 multiply_cannon_multrec 18288 15.5 3.471 3.793 3.483 3.804 potential_pw2rs 119 12.3 0.006 0.007 3.657 3.675 fft_wrap_pw1pw2_140 487 13.2 0.581 0.716 3.399 3.573 qs_ot_get_derivative 108 11.5 0.001 0.001 3.353 3.398 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.227 3.350 apply_single 119 13.6 0.000 0.000 3.227 3.349 ot_diis_step 108 11.5 0.003 0.003 3.212 3.212 init_scf_loop 11 6.9 0.000 0.000 3.120 3.121 fft3d_ps 1201 14.6 1.285 1.481 2.806 2.927 make_m2s 4572 13.5 0.047 0.050 2.631 2.714 init_scf_run 11 5.9 0.000 0.006 2.568 2.569 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.568 2.569 make_images 4572 14.5 0.116 0.120 2.302 2.380 wfi_extrapolate 11 7.9 0.001 0.001 2.343 2.347 mp_waitany 9880 13.7 1.878 2.190 1.878 2.190 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.030 2.038 qs_ot_get_p 119 10.4 0.001 0.001 1.776 1.841 rs_pw_transfer_RS2PW_140 130 11.5 0.173 0.193 1.363 1.729 mp_alltoall_z22v 1201 16.6 1.265 1.461 1.265 1.461 make_images_data 4572 15.5 0.036 0.043 1.241 1.359 rs_pw_transfer_PW2RS_140 130 13.9 0.347 0.449 1.286 1.322 mp_alltoall_d11v 2130 13.8 1.074 1.282 1.074 1.282 prepare_preconditioner 11 7.9 0.000 0.000 1.243 1.260 make_preconditioner 11 8.9 0.000 0.000 1.243 1.260 mp_sum_d 4135 12.0 0.861 1.209 0.861 1.209 hybrid_alltoall_any 4725 16.4 0.063 0.172 1.057 1.183 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.129 1.142 mp_sum_l 11298 13.2 0.939 1.111 0.939 1.111 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.047 1.076 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.998 1.036 rs_pw_transfer_PW2RS_50 119 14.3 0.332 0.390 0.958 1.002 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.910 0.986 ------------------------------------------------------------------------------- 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=50.907, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.695, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.796, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.399, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.286, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=5.006, 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=18.103000000000005, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.35, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.422, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.471, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.878, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.973, 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 0.035 0.035 114.086 114.086 qs_mol_dyn_low 1 2.0 0.002 0.002 113.424 113.424 qs_forces 11 3.9 0.001 0.001 113.381 113.381 qs_energies 11 4.9 0.001 0.001 105.008 105.008 scf_env_do_scf 11 5.9 0.002 0.002 92.031 92.031 velocity_verlet 10 3.0 0.002 0.002 73.947 73.947 scf_env_do_scf_inner_loop 96 6.5 0.013 0.013 73.087 73.087 rebuild_ks_matrix 107 8.3 0.001 0.001 33.794 33.794 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.793 33.793 qs_rho_update_rho_low 107 7.7 0.000 0.000 30.908 30.908 calculate_rho_elec 107 8.7 0.850 0.850 30.908 30.908 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.259 30.259 sum_up_and_integrate 107 10.3 0.705 0.705 27.003 27.003 grid_collocate_task_list 107 9.7 26.799 26.799 26.799 26.799 integrate_v_rspace 107 11.3 0.083 0.083 26.298 26.298 grid_integrate_task_list 107 12.3 24.470 24.470 24.470 24.470 init_scf_loop 11 6.9 0.000 0.000 18.716 18.716 qs_scf_new_mos 96 7.5 0.000 0.000 18.713 18.713 qs_scf_loop_do_ot 96 8.5 0.001 0.001 18.713 18.713 dbcsr_multiply_generic 1966 12.4 0.141 0.141 18.670 18.670 ot_scf_mini 96 9.5 0.002 0.002 17.555 17.555 prepare_preconditioner 11 7.9 0.000 0.000 14.575 14.575 make_preconditioner 11 8.9 0.000 0.000 14.575 14.575 make_full_inverse_cholesky 11 9.9 0.032 0.032 13.364 13.364 ot_mini 96 10.5 0.001 0.001 11.190 11.190 make_m2s 3932 13.4 0.041 0.041 9.925 9.925 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.083 7.083 qs_ot_get_derivative 96 11.5 0.001 0.001 6.072 6.072 pw_transfer 1295 11.6 0.058 0.058 5.863 5.863 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.617 5.617 dbcsr_make_dense_low 4961 15.5 0.072 0.072 5.245 5.245 init_scf_run 11 5.9 0.003 0.003 5.237 5.237 scf_env_initial_rho_setup 11 6.9 0.002 0.002 5.234 5.234 multiply_cannon 1966 13.4 0.179 0.179 5.184 5.184 make_dense_data 4961 16.5 4.681 4.681 5.161 5.161 ot_diis_step 96 11.5 0.003 0.003 5.115 5.115 make_images 3932 14.4 2.076 2.076 5.053 5.053 fft_wrap_pw1pw2_140 439 13.2 0.575 0.575 4.882 4.882 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.858 4.858 apply_single 107 13.6 0.000 0.000 4.858 4.858 cp_fm_cholesky_decompose 22 10.9 4.769 4.769 4.769 4.769 multiply_cannon_loop 1966 14.4 0.038 0.038 4.749 4.749 multiply_cannon_multrec 1966 15.4 4.666 4.666 4.710 4.710 wfi_extrapolate 11 7.9 0.001 0.001 4.648 4.648 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.571 4.571 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.399 4.399 cp_fm_cholesky_invert 11 10.9 4.308 4.308 4.308 4.308 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.042 4.042 dbcsr_copy 1855 11.9 0.190 0.190 4.034 4.034 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.972 3.972 dbcsr_copy_into_existing 22 7.9 3.812 3.812 3.812 3.812 dbcsr_complete_redistribute 317 12.2 1.913 1.913 3.673 3.673 qs_create_task_list 11 7.9 0.000 0.000 3.665 3.665 generate_qs_task_list 11 8.9 2.395 2.395 3.665 3.665 density_rs2pw 107 9.7 0.004 0.004 3.258 3.258 qs_ot_get_p 107 10.4 0.001 0.001 3.225 3.225 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.070 3.070 fft3d_s 1082 14.6 2.737 2.737 2.742 2.742 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.622 2.622 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.379 2.379 ------------------------------------------------------------------------------- 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 0.010 0.027 76.542 76.555 qs_mol_dyn_low 1 2.0 0.003 0.004 76.407 76.412 qs_forces 11 3.9 0.002 0.002 76.363 76.364 qs_energies 11 4.9 0.001 0.001 71.497 71.510 scf_env_do_scf 11 5.9 0.000 0.002 66.366 66.370 scf_env_do_scf_inner_loop 96 6.5 0.003 0.021 61.448 61.448 velocity_verlet 10 3.0 0.001 0.003 43.598 43.599 rebuild_ks_matrix 107 8.3 0.001 0.001 32.673 32.771 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.015 32.672 32.771 qs_ks_update_qs_env 107 7.6 0.001 0.001 28.971 29.058 sum_up_and_integrate 107 10.3 0.033 0.040 28.490 28.534 integrate_v_rspace 107 11.3 0.004 0.004 28.456 28.503 qs_rho_update_rho_low 107 7.7 0.001 0.001 27.826 27.835 calculate_rho_elec 107 8.7 0.027 0.030 27.825 27.835 grid_integrate_task_list 107 12.3 23.640 24.158 23.640 24.158 grid_collocate_task_list 107 9.7 22.841 23.347 22.841 23.347 dbcsr_multiply_generic 1966 12.4 0.071 0.073 13.018 13.248 qs_scf_new_mos 96 7.5 0.001 0.001 10.657 10.761 qs_scf_loop_do_ot 96 8.5 0.001 0.001 10.656 10.760 ot_scf_mini 96 9.5 0.002 0.002 10.043 10.147 multiply_cannon 1966 13.4 0.125 0.132 9.278 9.788 multiply_cannon_loop 1966 14.4 0.083 0.094 8.691 9.105 mp_waitall_1 136719 16.5 6.910 7.370 6.910 7.370 ot_mini 96 10.5 0.001 0.001 6.013 6.122 multiply_cannon_metrocomm3 15728 15.4 0.039 0.046 5.161 5.642 rs_pw_transfer 878 11.9 0.010 0.012 4.787 5.550 density_rs2pw 107 9.7 0.004 0.005 4.355 5.107 init_scf_loop 11 6.9 0.000 0.000 4.901 4.902 pw_transfer 1295 11.6 0.061 0.067 4.025 4.100 init_scf_run 11 5.9 0.000 0.005 4.036 4.037 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.036 4.037 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 3.901 3.965 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.855 3.868 wfi_extrapolate 11 7.9 0.001 0.001 3.624 3.625 multiply_cannon_multrec 15728 15.4 3.126 3.388 3.136 3.398 potential_pw2rs 107 12.3 0.006 0.006 3.364 3.385 fft_wrap_pw1pw2_140 439 13.2 0.516 0.636 3.168 3.319 qs_ot_get_derivative 96 11.5 0.001 0.001 3.080 3.181 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.888 3.042 apply_single 107 13.6 0.000 0.001 2.888 3.042 mp_waitany 8968 13.7 2.140 2.914 2.140 2.914 ot_diis_step 96 11.5 0.003 0.003 2.911 2.911 fft3d_ps 1081 14.6 1.169 1.364 2.709 2.805 make_m2s 3932 13.4 0.041 0.045 2.410 2.485 rs_pw_transfer_RS2PW_140 118 11.5 0.152 0.168 1.634 2.409 mp_alltoall_d11v 1998 13.7 1.703 2.286 1.703 2.286 make_images 3932 14.4 0.104 0.107 2.119 2.190 rs_gather_matrices 107 12.3 0.086 0.095 1.396 1.963 qs_ot_get_p 107 10.4 0.001 0.001 1.480 1.622 ------------------------------------------------------------------------------- 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=48.70100000000001, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=26.799, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.47, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.769, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.681, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.666, 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=17.885000000000005, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.841, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=23.64, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.126, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.14, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=6.91, 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 0.221 0.221 133.899 133.899 qs_energies 1 2.0 0.000 0.000 133.022 133.022 scf_env_do_scf 1 3.0 0.000 0.000 131.820 131.820 qs_ks_update_qs_env 8 5.0 0.000 0.000 126.299 126.299 rebuild_ks_matrix 7 6.0 0.000 0.000 126.243 126.243 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 126.243 126.243 hfx_ks_matrix 7 8.0 0.000 0.000 117.154 117.154 integrate_four_center 7 9.0 1.748 1.748 117.121 117.121 integrate_four_center_main 7 10.0 0.575 0.575 103.328 103.328 integrate_four_center_bin 429 11.0 102.753 102.753 102.753 102.753 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 75.125 75.125 init_scf_loop 1 4.0 0.000 0.000 56.681 56.681 integrate_four_center_load 7 10.0 0.000 0.000 11.738 11.738 hfx_load_balance 1 11.0 0.015 0.015 11.738 11.738 hfx_load_balance_count 1 12.0 5.867 5.867 5.867 5.867 hfx_load_balance_bin 1 12.0 5.838 5.838 5.838 5.838 qs_vxc_create 14 8.0 0.000 0.000 3.065 3.065 xc_vxc_pw_create 14 9.0 0.150 0.150 3.065 3.065 ------------------------------------------------------------------------------- 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 0.213 0.235 128.731 128.743 qs_energies 1 2.0 0.000 0.000 128.345 128.356 scf_env_do_scf 1 3.0 0.000 0.000 128.006 128.007 qs_ks_update_qs_env 8 5.0 0.000 0.000 125.916 125.917 rebuild_ks_matrix 7 6.0 0.000 0.000 125.908 125.910 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 125.908 125.910 hfx_ks_matrix 7 8.0 0.000 0.000 120.333 120.334 integrate_four_center 7 9.0 0.049 0.330 120.325 120.326 integrate_four_center_main 7 10.0 0.003 0.003 101.143 107.575 integrate_four_center_bin 448 11.0 101.139 107.571 101.139 107.571 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 75.993 75.994 init_scf_loop 1 4.0 0.000 0.000 52.011 52.012 mp_sync 56 11.2 6.820 12.506 6.820 12.506 integrate_four_center_load 7 10.0 0.000 0.000 11.710 11.711 hfx_load_balance 1 11.0 0.001 0.001 11.710 11.711 hfx_load_balance_bin 1 12.0 5.783 5.868 5.783 5.868 hfx_load_balance_count 1 12.0 5.773 5.855 5.773 5.855 ------------------------------------------------------------------------------- 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=16.89699999999999, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=102.753, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.867, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.838, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.748, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.575, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.221, 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=8.950999999999993, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=101.139, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.773, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.783, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.049, 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=0.213, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=6.82, yerr=0.0 Running GW_PBE_4benzene.inp with 1 threads and 32 ranks... done. Running GW_PBE_4benzene.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.017 0.017 76.460 76.460 qs_energies 1 2.0 0.000 0.000 76.046 76.046 mp2_main 1 3.0 0.000 0.000 73.274 73.274 mp2_gpw_main 1 4.0 0.000 0.000 73.172 73.172 rpa_ri_compute_en 1 5.0 0.000 0.000 69.476 69.476 rpa_num_int 1 6.0 0.001 0.001 69.470 69.470 compute_mat_P_omega 1 7.0 0.004 0.004 59.602 59.602 compute_mat_P_omega_contract 10 8.0 8.765 8.765 59.386 59.386 dbt_total 2336 9.6 0.015 0.015 45.789 45.789 dbt_contract 787 11.0 0.041 0.041 38.980 38.980 dbt_tas_total 1149 12.2 0.233 0.233 37.560 37.560 dbt_tas_multiply 807 12.1 0.002 0.002 36.428 36.428 dbt_tas_dbm 807 14.1 0.003 0.003 30.152 30.152 dbm_multiply 807 16.1 30.144 30.144 30.144 30.144 dbt_tas_mm_1N 524 15.1 0.001 0.001 23.119 23.119 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 21.862 21.862 compute_mat_P_omega_calc_M_occ 250 9.0 8.805 8.805 16.955 16.955 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.492 6.492 dbt_copy 1103 10.7 0.134 0.134 5.657 5.657 dbt_tas_mm_2 251 15.0 0.001 0.001 5.529 5.529 compute_QP_energies 1 7.0 0.000 0.000 4.844 4.844 compute_self_energy_cubic_gw 1 8.0 0.053 0.053 4.843 4.843 contract_cubic_gw 21 9.0 0.000 0.000 3.864 3.864 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.689 3.689 dbt_tas_reserve_blocks_index 3261 14.3 0.482 0.482 3.623 3.623 dbm_reserve_blocks 3628 15.3 3.205 3.205 3.205 3.205 dbt_reserve_blocks_index 2280 13.1 0.054 0.054 2.759 2.759 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.708 2.708 scf_env_do_scf 1 3.0 0.000 0.000 2.662 2.662 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.662 2.662 dbt_crop 1042 12.0 1.438 1.438 2.433 2.433 convert_to_new_pgrid 2421 14.1 0.067 0.067 2.339 2.339 dbm_copy 1614 15.1 2.272 2.272 2.272 2.272 dbt_tas_copy 574 11.4 1.270 1.270 2.185 2.185 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.177 2.177 compute_W_cubic_GW 10 7.0 0.005 0.005 2.016 2.016 dbt_reshape 278 11.9 1.030 1.030 1.859 1.859 dbt_tas_reshape 367 15.0 0.037 0.037 1.841 1.841 get_2c_integrals 1 6.0 0.000 0.000 1.694 1.694 ------------------------------------------------------------------------------- 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 0.026 33.637 33.650 qs_energies 1 2.0 0.000 0.000 33.513 33.515 mp2_main 1 3.0 0.000 0.005 32.541 32.543 mp2_gpw_main 1 4.0 0.000 0.000 32.405 32.407 rpa_ri_compute_en 1 5.0 0.000 0.000 31.155 31.157 rpa_num_int 1 6.0 0.000 0.002 31.155 31.156 dbt_total 2336 9.6 0.014 0.015 27.741 27.767 compute_mat_P_omega 1 7.0 0.001 0.007 26.368 26.391 compute_mat_P_omega_contract 10 8.0 0.360 0.375 26.201 26.207 dbt_contract 787 11.0 0.037 0.039 20.672 20.688 dbt_tas_total 1149 12.2 0.073 0.084 18.423 18.449 dbt_tas_multiply 807 12.1 0.002 0.002 18.334 18.347 dbt_tas_dbm 807 14.1 0.003 0.003 12.797 12.815 dbm_multiply 807 16.1 10.035 10.831 10.035 10.831 compute_mat_P_omega_calc_M_occ 250 9.0 0.357 0.377 7.979 7.992 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.637 7.650 dbt_copy 1149 10.8 0.012 0.013 5.889 6.135 dbt_tas_mm_2 251 15.0 0.001 0.001 6.005 6.022 dbt_reshape 1136 11.8 2.462 2.602 5.587 5.826 mp_sync 8688 11.6 5.059 5.767 5.059 5.767 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.390 5.391 dbt_tas_mm_1N 524 15.1 0.001 0.001 4.496 4.857 compute_QP_energies 1 7.0 0.000 0.000 3.130 3.132 compute_self_energy_cubic_gw 1 8.0 0.002 0.004 3.128 3.130 mp_waitall_2 3812 15.3 2.314 2.505 2.314 2.505 contract_cubic_gw 21 9.0 0.000 0.000 2.497 2.497 dbt_communicate_buffer 1136 12.8 0.050 0.053 2.268 2.454 dbt_reserve_blocks_index 2887 13.1 0.063 0.069 1.567 1.734 dbt_reserve_blocks_index_array 2829 12.2 0.007 0.008 1.558 1.724 dbt_tas_reserve_blocks_index 3347 14.5 0.429 0.463 1.551 1.718 dbt_crop 1042 12.0 0.835 0.922 1.328 1.450 dbm_reserve_blocks 3752 15.4 1.206 1.375 1.206 1.375 mp2_ri_gpw_compute_in 1 5.0 0.003 0.004 1.244 1.244 dbt_tas_replicate 405 14.1 0.532 0.692 1.154 1.215 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.076 1.086 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.046 1.051 parallel_gemm_fm 105 8.4 0.000 0.000 1.020 1.030 parallel_gemm_fm_cosma 105 9.4 1.020 1.030 1.020 1.030 scf_env_do_scf 1 3.0 0.000 0.000 0.923 0.924 scf_env_do_scf_inner_loop 17 4.0 0.000 0.003 0.923 0.923 dbt_tas_create_split 2550 15.2 0.004 0.005 0.877 0.888 dbt_tas_create_split_rows_or_c 2550 16.2 0.012 0.013 0.873 0.885 mp_max_i 2004 9.8 0.678 0.855 0.678 0.855 mp_sum_l 6165 12.9 0.755 0.827 0.755 0.827 convert_to_new_pgrid 2421 14.1 0.023 0.027 0.676 0.785 compute_W_cubic_GW 10 7.0 0.001 0.001 0.767 0.776 dbm_copy 1608 15.1 0.647 0.755 0.647 0.755 ------------------------------------------------------------------------------- Plot: name="GW_PBE_4benzene_timings_32omp", title="Timings of GW_PBE_4benzene with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="rest", label="rest", y=22.238999999999997, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=30.144, 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=8.805, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.765, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.205, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.272, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.03, 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=11.197000000000003, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.035, 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=0.357, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.36, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.206, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.647, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.462, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.059, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.314, 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 0.022 0.022 239.623 239.623 qs_forces 1 2.0 0.000 0.000 239.026 239.026 rebuild_ks_matrix 7 6.6 0.000 0.000 237.458 237.458 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 237.458 237.458 hfx_ks_matrix 7 8.6 0.000 0.000 235.408 235.408 hfx_ri_update_ks 7 9.6 0.000 0.000 194.746 194.746 hfx_ri_update_ks_Pmat 7 10.6 39.448 39.448 194.734 194.734 qs_energies 1 3.0 0.000 0.000 173.821 173.821 scf_env_do_scf 1 4.0 0.001 0.001 173.461 173.461 dbt_total 809 11.0 0.007 0.007 172.591 172.591 qs_ks_update_qs_env 8 6.0 0.000 0.000 172.326 172.326 dbt_contract 207 12.4 0.056 0.056 152.666 152.666 dbt_tas_total 343 13.7 2.070 2.070 149.559 149.559 dbt_tas_multiply 216 13.5 0.001 0.001 146.420 146.420 dbt_tas_dbm 216 15.5 0.001 0.001 133.061 133.061 dbm_multiply 216 17.5 133.058 133.058 133.058 133.058 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 128.489 128.489 dbt_tas_mm_2 91 16.5 0.001 0.001 119.064 119.064 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 108.290 108.290 init_scf_loop 2 5.0 0.000 0.000 65.168 65.168 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 65.138 65.138 hfx_ri_update_forces 1 7.0 1.650 1.650 40.659 40.659 hfx_ri_forces_Pmat_3c 1 8.0 4.682 4.682 23.072 23.072 dbt_copy 409 11.7 0.078 0.078 16.776 16.776 precalc_derivatives 1 8.0 2.262 2.262 13.457 13.457 dbt_reshape 132 13.2 7.430 7.430 11.775 11.775 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.923 9.923 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.675 9.675 dbt_tas_reserve_blocks_index 1255 15.4 1.019 1.019 8.510 8.510 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.877 7.877 dbm_reserve_blocks 1397 16.3 7.691 7.691 7.691 7.691 build_3c_derivatives 3 9.0 3.145 3.145 7.530 7.530 dbt_reserve_blocks_index 818 14.4 0.109 0.109 6.680 6.680 dbt_reserve_blocks_index_array 795 13.4 0.006 0.006 6.557 6.557 dbt_crop 372 13.7 3.099 3.099 5.458 5.458 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 5.456 5.456 ------------------------------------------------------------------------------- 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 0.008 0.029 48.246 48.258 qs_forces 1 2.0 0.000 0.000 48.077 48.078 rebuild_ks_matrix 7 6.6 0.000 0.000 47.325 47.326 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 47.325 47.326 hfx_ks_matrix 7 8.6 0.000 0.000 46.368 46.376 dbt_total 809 11.0 0.006 0.006 41.187 41.203 dbt_contract 207 12.4 0.024 0.028 31.653 31.680 dbt_tas_total 343 13.7 0.072 0.198 28.082 28.086 dbt_tas_multiply 216 13.5 0.001 0.001 27.793 27.795 hfx_ri_update_ks 7 9.6 0.000 0.000 26.612 26.612 hfx_ri_update_ks_Pmat 7 10.6 1.179 1.240 26.607 26.608 qs_energies 1 3.0 0.000 0.000 24.836 24.836 scf_env_do_scf 1 4.0 0.000 0.001 24.692 24.692 qs_ks_update_qs_env 8 6.0 0.000 0.000 24.094 24.095 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 23.233 23.233 dbt_tas_dbm 216 15.5 0.001 0.001 21.372 21.381 hfx_ri_update_forces 1 7.0 0.061 0.071 19.756 19.763 dbm_multiply 216 17.5 19.258 19.743 19.258 19.743 hfx_ri_forces_Pmat_3c 1 8.0 0.158 0.172 14.576 14.576 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 13.762 13.762 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 12.547 12.547 init_scf_loop 2 5.0 0.000 0.000 10.928 10.928 dbt_tas_mm_2 91 16.5 0.001 0.001 10.057 10.065 dbt_copy 497 12.3 0.011 0.013 8.381 8.646 dbt_reshape 365 13.6 3.495 3.587 6.508 6.739 mp_sync 2769 12.9 5.404 6.168 5.404 6.168 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.325 5.702 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.769 4.769 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.237 4.355 precalc_derivatives 1 8.0 0.091 0.096 3.870 3.870 dbt_tas_reserve_blocks_index 1380 15.8 0.899 0.921 2.955 3.261 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.040 3.040 mp_waitall_2 1234 16.4 2.804 2.962 2.804 2.962 dbt_reserve_blocks_index 1051 14.7 0.108 0.114 2.445 2.727 dbt_reserve_blocks_index_array 1028 13.8 0.005 0.006 2.421 2.701 dbt_crop 372 13.7 1.679 1.725 2.407 2.574 dbm_reserve_blocks 1529 16.7 2.247 2.549 2.247 2.549 build_3c_derivatives 3 9.0 0.244 0.263 2.164 2.172 dbt_communicate_buffer 365 14.6 0.012 0.013 1.958 2.077 dbt_tas_replicate 149 15.4 0.630 0.651 1.661 1.748 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.633 1.633 convert_to_new_pgrid 648 15.5 0.039 0.087 1.307 1.582 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.511 1.514 dbm_copy 452 16.3 1.124 1.404 1.124 1.404 dbt_tas_copy 132 12.5 0.585 0.634 1.150 1.275 dbt_tas_communicate_buffer 328 16.8 0.010 0.011 0.960 1.035 mp_sum_l 6385 13.7 0.881 0.992 0.881 0.992 ------------------------------------------------------------------------------- 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=47.31399999999999, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=133.058, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=39.448, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.691, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=7.43, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.682, 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=13.701, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=19.258, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.179, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.247, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.495, 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=5.404, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.804, 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 0.018 0.018 178.691 178.691 qs_energies 1 2.0 0.000 0.000 178.492 178.492 mp2_main 1 3.0 0.000 0.000 173.693 173.693 mp2_gpw_main 1 4.0 0.002 0.002 173.289 173.289 mp2_ri_gpw_compute_in 1 5.0 0.380 0.380 117.996 117.996 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 108.835 108.835 mp2_eri_3c_integrate_gpw 2656 7.0 0.014 0.014 81.496 81.496 integrate_v_rspace 2666 8.0 0.686 0.686 68.268 68.268 grid_integrate_task_list 2666 9.0 65.597 65.597 65.597 65.597 mp2_ri_gpw_compute_en 1 5.0 0.085 0.085 55.267 55.267 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.710 9.710 52.796 52.796 mp2_ri_gpw_compute_en_expansio 2080 7.0 1.454 1.454 29.011 29.011 local_gemm 2080 8.0 27.556 27.556 27.556 27.556 dbcsr_multiply_generic 5322 8.0 0.176 0.176 20.749 20.749 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.725 20.725 mp2_ri_gpw_compute_en_ener 2080 7.0 12.212 12.212 12.212 12.212 pw_transfer 63872 10.6 0.963 0.963 11.903 11.903 calculate_wavefunction 2656 8.0 8.052 8.052 11.861 11.861 multiply_cannon 5322 9.0 0.497 0.497 10.932 10.932 fft_wrap_pw1pw2 53228 11.4 0.106 0.106 10.705 10.705 multiply_cannon_loop 5322 10.0 0.168 0.168 9.496 9.496 get_2c_integrals 1 6.0 0.000 0.000 8.719 8.719 multiply_cannon_multrec 5322 11.0 7.999 7.999 8.036 8.036 compute_2c_integrals 1 7.0 0.005 0.005 7.811 7.811 compute_2c_integrals_loop_lm 1 8.0 0.012 0.012 7.798 7.798 mp2_eri_2c_integrate_gpw 1 9.0 0.829 0.829 7.787 7.787 make_m2s 10644 9.0 0.060 0.060 7.652 7.652 fft_wrap_pw1pw2_20 21271 12.4 0.520 0.520 7.496 7.496 make_images 10644 10.0 2.870 2.870 7.280 7.280 fft3d_s 53229 13.4 6.574 6.574 6.616 6.616 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.446 2.446 6.497 6.497 copy_dbcsr_to_fm 2679 8.0 0.028 0.028 4.550 4.550 scf_env_do_scf 1 3.0 0.000 0.000 4.386 4.386 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.386 4.386 potential_pw2rs 5322 10.0 0.164 0.164 3.963 3.963 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.043 37.924 37.942 qs_energies 1 2.0 0.000 0.000 37.769 37.770 mp2_main 1 3.0 0.000 0.001 35.877 35.878 mp2_gpw_main 1 4.0 0.001 0.002 35.783 35.784 mp2_ri_gpw_compute_en 1 5.0 0.245 0.256 18.954 19.237 mp2_ri_gpw_compute_en_RI_loop 1 6.0 3.110 3.478 17.806 17.813 mp2_ri_gpw_compute_in 1 5.0 0.044 0.045 16.749 17.081 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.549 15.885 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.604 13.966 integrate_v_rspace 93 8.1 0.096 0.103 13.493 13.856 grid_integrate_task_list 93 9.1 13.198 13.557 13.198 13.557 mp2_ri_gpw_compute_en_expansio 65 7.0 0.124 0.151 10.779 10.941 local_gemm 65 8.0 10.655 10.823 10.655 10.823 mp2_ri_gpw_compute_en_comm 30 7.0 0.093 0.121 3.552 4.337 mp_sendrecv_dm3 1860 8.0 2.889 3.701 2.889 3.701 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.655 1.812 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.638 1.792 scf_env_do_scf 1 3.0 0.000 0.000 1.759 1.760 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 1.759 1.760 get_2c_integrals 1 6.0 0.004 0.011 1.134 1.159 multiply_cannon 176 9.0 0.016 0.017 0.997 1.068 multiply_cannon_loop 176 10.0 0.002 0.002 0.940 1.009 multiply_cannon_multrec 246 11.0 0.821 0.861 0.826 0.866 compute_2c_integrals 1 7.0 0.002 0.004 0.823 0.839 qs_scf_new_mos 10 5.0 0.000 0.000 0.824 0.832 eigensolver 11 5.8 0.001 0.001 0.773 0.774 compute_2c_integrals_loop_lm 1 8.0 0.002 0.003 0.739 0.761 mp2_eri_2c_integrate_gpw 1 9.0 0.196 0.202 0.738 0.760 ------------------------------------------------------------------------------- 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=47.565000000000026, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=65.597, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=27.556, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_ener", label="mp2_ri_gpw_compute_en_ener", y=12.212, 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=9.71, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.052, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.999, 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=7.250999999999998, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.198, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.655, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp2_ri_gpw_compute_en_ener", label="mp2_ri_gpw_compute_en_ener", y=0.0, 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=3.11, 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=0.821, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=2.889, 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 0.103 0.103 124.948 124.948 qs_energies 1 2.0 0.000 0.000 123.516 123.516 scf_env_do_scf 1 3.0 0.000 0.000 115.422 115.422 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 115.422 115.422 qs_ks_update_qs_env 15 5.0 0.000 0.000 49.547 49.547 rebuild_ks_matrix 15 6.0 0.000 0.000 49.337 49.337 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 49.337 49.337 qs_scf_new_mos 15 5.0 0.000 0.000 42.484 42.484 eigensolver 15 6.0 0.002 0.002 34.728 34.728 qs_vxc_create 15 8.0 0.037 0.037 34.036 34.036 calculate_dispersion_nonloc 15 9.0 7.035 7.035 29.743 29.743 pw_transfer 1191 10.0 0.058 0.058 23.523 23.523 fft_wrap_pw1pw2 1086 11.0 0.007 0.007 23.351 23.351 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.402 22.402 cp_fm_diag_elpa_base 15 8.0 19.776 19.776 22.402 22.402 qs_rho_update_rho_low 16 5.0 0.000 0.000 19.660 19.660 calculate_rho_elec 16 6.0 0.229 0.229 19.660 19.660 grid_collocate_task_list 16 7.0 18.299 18.299 18.299 18.299 fft_wrap_pw1pw2_150 765 12.0 3.591 3.591 17.028 17.028 sum_up_and_integrate 15 8.0 0.146 0.146 14.168 14.168 integrate_v_rspace 15 9.0 0.023 0.023 14.022 14.022 grid_integrate_task_list 15 10.0 13.319 13.319 13.319 13.319 fft3d_s 1087 13.0 10.664 10.664 10.671 10.671 cp_fm_cholesky_restore 45 7.0 10.019 10.019 10.019 10.019 pw_scatter_s 585 13.1 7.152 7.152 7.152 7.152 fft_wrap_pw1pw2_200 197 12.3 0.746 0.746 6.080 6.080 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.518 5.518 dbcsr_complete_redistribute 46 8.3 2.226 2.226 5.489 5.489 cp_fm_upper_to_full 30 8.0 4.931 4.931 4.931 4.931 gspace_mixing 14 5.0 0.171 0.171 4.755 4.755 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.592 4.592 vdW_energy 15 10.0 4.276 4.276 4.276 4.276 xc_vxc_pw_create 15 9.0 0.215 0.215 4.256 4.256 broyden_mixing 14 6.0 4.142 4.142 4.142 4.142 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 3.431 3.431 init_scf_run 1 3.0 0.000 0.000 3.023 3.023 xc_pw_derive 90 11.0 0.001 0.001 2.798 2.798 calculate_dm_sparse 15 6.0 0.015 0.015 2.585 2.585 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 2.507 2.507 ------------------------------------------------------------------------------- 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 0.015 0.032 59.907 59.925 qs_energies 1 2.0 0.000 0.000 59.609 59.618 scf_env_do_scf 1 3.0 0.000 0.001 55.479 55.480 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 55.479 55.480 qs_ks_update_qs_env 15 5.0 0.000 0.000 23.130 23.140 rebuild_ks_matrix 15 6.0 0.000 0.000 23.100 23.110 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 23.100 23.110 qs_rho_update_rho_low 16 5.0 0.000 0.000 19.053 19.057 calculate_rho_elec 16 6.0 0.007 0.007 19.053 19.057 grid_collocate_task_list 16 7.0 17.075 17.295 17.075 17.295 qs_scf_new_mos 15 5.0 0.000 0.000 13.760 13.824 sum_up_and_integrate 15 8.0 0.012 0.017 13.574 13.623 integrate_v_rspace 15 9.0 0.000 0.001 13.561 13.614 grid_integrate_task_list 15 10.0 12.810 12.985 12.810 12.985 eigensolver 15 6.0 0.001 0.002 12.816 12.836 qs_vxc_create 15 8.0 0.001 0.001 9.228 9.242 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.031 9.038 cp_fm_diag_elpa_base 15 8.0 8.904 8.919 9.025 9.027 calculate_dispersion_nonloc 15 9.0 0.890 0.897 7.393 7.417 pw_transfer 1191 10.0 0.064 0.071 7.162 7.190 fft_wrap_pw1pw2 1086 11.0 0.009 0.013 7.032 7.067 fft3d_ps 1086 13.0 2.355 2.602 4.918 5.165 fft_wrap_pw1pw2_150 765 12.0 0.438 0.496 4.494 4.509 cp_fm_cholesky_restore 45 7.0 3.651 3.711 3.651 3.711 mp_alltoall_z22v 1086 15.0 2.101 2.680 2.101 2.680 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.666 2.666 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.350 2.573 fft_wrap_pw1pw2_200 197 12.3 0.353 0.413 2.414 2.435 rs_pw_transfer 158 9.4 0.001 0.003 1.763 2.156 density_rs2pw 16 7.0 0.001 0.001 1.780 2.003 mp_waitany 520 11.3 1.318 1.893 1.318 1.893 xc_vxc_pw_create 15 9.0 0.014 0.017 1.835 1.868 x_to_yz 585 14.1 0.282 0.290 1.375 1.617 build_core_ppnl 1 5.0 1.462 1.606 1.462 1.606 yz_to_x 501 13.9 0.160 0.191 1.167 1.478 rs_pw_transfer_RS2PW_200 18 8.8 0.022 0.025 0.968 1.427 xc_pw_derive 90 11.0 0.001 0.001 1.232 1.300 vdW_energy 15 10.0 1.235 1.291 1.235 1.291 init_scf_run 1 3.0 0.000 0.000 1.242 1.243 ------------------------------------------------------------------------------- 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=52.87099999999998, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.776, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=18.299, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.319, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.664, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.019, 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=15.112000000000002, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.904, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=17.075, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.81, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.651, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.355, 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 0.094 0.094 289.230 289.230 qs_energies 1 2.0 0.000 0.000 289.070 289.070 ls_scf 1 3.0 0.000 0.000 287.724 287.724 ls_scf_main 1 4.0 0.003 0.003 277.875 277.875 density_matrix_trs4 11 5.0 0.015 0.015 175.438 175.438 ls_scf_dm_to_ks 11 5.0 0.000 0.000 96.286 96.286 matrix_ls_to_qs 11 6.0 0.000 0.000 92.654 92.654 dbcsr_multiply_generic 185 6.1 1.028 1.028 85.971 85.971 arnoldi_extremal 12 6.1 0.000 0.000 71.988 71.988 arnoldi_normal_ev 12 7.1 0.061 0.061 71.987 71.987 build_subspace 23 8.1 0.094 0.094 70.617 70.617 dbcsr_matrix_vector_mult 652 9.0 0.333 0.333 70.106 70.106 dbcsr_matrix_vector_mult_local 652 10.0 68.131 68.131 68.141 68.141 dbcsr_copy_into_existing 11 7.0 50.106 50.106 50.106 50.106 multiply_cannon 185 7.1 0.543 0.543 49.252 49.252 dbcsr_complete_redistribute 23 7.5 33.489 33.489 46.842 46.842 matrix_decluster 11 7.0 0.000 0.000 42.547 42.547 multiply_cannon_loop 185 8.1 0.232 0.232 35.742 35.742 make_m2s 370 7.1 0.040 0.040 31.129 31.129 make_images 370 8.1 13.483 13.483 28.101 28.101 multiply_cannon_multrec 185 9.1 25.601 25.601 25.654 25.654 dbcsr_finalize 646 7.5 0.306 0.306 17.839 17.839 dbcsr_merge_all 597 8.5 2.716 2.716 16.441 16.441 setup_rec_index_2d 370 8.1 12.746 12.746 12.746 12.746 dbcsr_sort_indices 1103 9.9 12.159 12.159 12.159 12.159 tree_to_linear_d 110 9.4 12.133 12.133 12.133 12.133 quick_finalize 395 10.0 0.469 0.469 10.570 10.570 calculate_norms 370 9.1 9.856 9.856 9.856 9.856 dbcsr_special_finalize 370 9.1 0.002 0.002 9.789 9.789 ls_scf_init_scf 1 4.0 0.000 0.000 9.126 9.126 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.768 8.768 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 8.080 8.080 dbcsr_dot_sd 144 6.3 7.904 7.904 7.905 7.905 matrix_qs_to_ls 12 5.1 0.000 0.000 6.319 6.319 matrix_cluster 12 6.1 0.000 0.000 6.319 6.319 dbcsr_frobenius_norm 142 6.1 6.239 6.239 6.241 6.241 ------------------------------------------------------------------------------- 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 0.014 0.031 75.486 75.498 qs_energies 1 2.0 0.000 0.000 75.367 75.368 ls_scf 1 3.0 0.000 0.000 75.312 75.313 ls_scf_main 1 4.0 0.001 0.010 72.517 72.517 density_matrix_trs4 11 5.0 0.007 0.023 69.775 69.832 dbcsr_multiply_generic 185 6.1 0.064 0.077 66.208 66.565 multiply_cannon 185 7.1 0.035 0.039 54.491 55.638 multiply_cannon_loop 185 8.1 0.121 0.131 51.865 52.823 multiply_cannon_multrec 1480 9.1 31.374 34.018 31.641 34.293 mp_waitall_1 11936 10.3 18.107 21.363 18.107 21.363 multiply_cannon_metrocomm3 1480 9.1 0.015 0.023 13.570 17.266 make_m2s 370 7.1 0.036 0.042 7.617 7.707 make_images 370 8.1 0.650 0.678 7.479 7.569 calculate_norms 2960 9.1 5.187 5.590 5.187 5.590 mp_sum_l 1199 5.3 3.158 4.805 3.158 4.805 make_images_data 370 9.1 0.010 0.018 3.509 3.784 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 2.281 3.653 hybrid_alltoall_any 393 9.9 0.229 1.087 3.024 3.472 multiply_cannon_metrocomm1 1480 9.1 0.006 0.008 1.308 2.746 arnoldi_extremal 12 6.1 0.000 0.001 2.696 2.724 arnoldi_normal_ev 12 7.1 0.002 0.008 2.695 2.724 build_subspace 23 8.1 0.022 0.028 2.582 2.584 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.360 2.412 dbcsr_complete_redistribute 23 7.5 1.271 1.350 2.140 2.233 dbcsr_matrix_vector_mult 652 9.0 0.014 0.052 2.149 2.216 matrix_ls_to_qs 11 6.0 0.000 0.000 2.044 2.139 ls_scf_init_scf 1 4.0 0.000 0.000 2.123 2.124 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.093 2.098 make_images_pack 370 9.1 1.800 2.072 1.803 2.075 matrix_decluster 11 7.0 0.000 0.000 1.918 2.012 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.002 1.906 1.908 dbcsr_matrix_vector_mult_local 652 10.0 1.728 1.771 1.730 1.773 buffer_matrices_ensure_size 370 8.1 1.481 1.756 1.481 1.756 ------------------------------------------------------------------------------- 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=88.56400000000002, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=68.131, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=50.106, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=33.489, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=25.601, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images", label="make_images", y=13.483, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.856, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 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=12.211000000000013, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.728, 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=1.271, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=31.374, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images", label="make_images", y=0.65, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.187, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=3.158, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=18.107, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.8, 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 0.010 0.010 78.445 78.445 lib_test 1 2.0 0.000 0.000 78.433 78.433 dbcsr_run_tests 3 3.0 0.002 0.002 78.433 78.433 test_multiplies_multiproc 3 4.0 0.002 0.002 61.856 61.856 dbcsr_redistribute 9 5.0 40.258 40.258 41.974 41.974 dbcsr_multiply_generic 9 5.0 0.011 0.011 18.406 18.406 dbcsr_make_random_matrix 9 4.0 13.269 13.269 16.460 16.460 multiply_cannon 9 6.0 0.003 0.003 13.055 13.055 multiply_cannon_loop 9 7.0 0.028 0.028 12.682 12.682 multiply_cannon_multrec 9 8.0 12.654 12.654 12.654 12.654 dbcsr_finalize 27 5.7 0.031 0.031 5.975 5.975 dbcsr_merge_all 18 6.5 2.209 2.209 5.214 5.214 dbcsr_data_release 975 7.6 2.837 2.837 2.837 2.837 tree_to_linear_d 9 7.0 2.075 2.075 2.075 2.075 make_m2s 18 6.0 0.001 0.001 1.947 1.947 make_images 18 7.0 0.687 0.687 1.883 1.883 ------------------------------------------------------------------------------- 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 0.005 0.016 20.962 20.969 lib_test 1 2.0 0.000 0.000 20.923 20.941 dbcsr_run_tests 3 3.0 0.000 0.001 20.923 20.940 test_multiplies_multiproc 3 4.0 0.000 0.003 20.033 20.100 dbcsr_multiply_generic 9 5.0 0.001 0.001 18.465 18.564 multiply_cannon 9 6.0 0.002 0.002 16.389 16.790 multiply_cannon_loop 9 7.0 0.002 0.003 16.070 16.522 multiply_cannon_multrec 72 8.0 12.032 12.514 12.032 12.515 mp_waitall_1 576 9.2 4.423 5.476 4.423 5.476 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 3.963 4.967 mp_sum_l 470 2.5 0.686 1.438 0.686 1.438 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.669 1.421 dbcsr_make_random_matrix 9 4.0 0.697 0.706 0.852 0.888 make_m2s 18 6.0 0.001 0.001 0.806 0.847 make_images 18 7.0 0.021 0.025 0.802 0.844 dbcsr_data_release 444 7.6 0.633 0.739 0.633 0.739 dbcsr_finalize 27 5.7 0.000 0.000 0.621 0.722 dbcsr_redistribute 9 5.0 0.251 0.290 0.611 0.654 dbcsr_destroy 111 5.9 0.004 0.058 0.553 0.644 dbcsr_merge_all 18 6.5 0.097 0.120 0.535 0.618 make_images_data 18 8.0 0.001 0.001 0.432 0.524 hybrid_alltoall_any 18 9.0 0.038 0.203 0.373 0.450 ------------------------------------------------------------------------------- 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=7.217999999999989, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=40.258, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.269, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=12.654, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.837, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.209, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=2.1430000000000007, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.251, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.697, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=12.032, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.633, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.097, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=4.423, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.686, 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 0.089 0.089 143.451 143.451 qs_mol_dyn_low 1 2.0 0.004 0.004 141.880 141.880 velocity_verlet 5 3.0 0.004 0.004 116.680 116.680 qmmm_el_coupling 6 3.8 0.000 0.000 87.864 87.864 qmmm_elec_with_gaussian 6 4.8 0.040 0.040 87.860 87.860 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 86.746 86.746 qmmm_elec_gaussian_low_G 6 6.8 85.831 85.831 85.831 85.831 qs_forces 6 3.8 0.001 0.001 44.087 44.087 qs_energies 6 4.8 0.000 0.000 38.637 38.637 scf_env_do_scf 6 5.8 0.001 0.001 36.044 36.044 rebuild_ks_matrix 45 8.4 0.000 0.000 32.103 32.103 qs_ks_build_kohn_sham_matrix 45 9.4 0.006 0.006 32.103 32.103 scf_env_do_scf_inner_loop 39 6.8 0.005 0.005 31.186 31.186 qs_ks_update_qs_env 45 7.8 0.000 0.000 27.129 27.129 pw_transfer 966 12.3 0.062 0.062 20.047 20.047 fft_wrap_pw1pw2 801 13.6 0.007 0.007 19.776 19.776 fft_wrap_pw1pw2_150 507 15.2 2.933 2.933 19.354 19.354 qs_vxc_create 45 10.4 0.001 0.001 16.927 16.927 xc_vxc_pw_create 45 11.4 0.758 0.758 16.926 16.926 xc_pw_derive 270 13.4 0.002 0.002 11.261 11.261 xc_rho_set_and_dset_create 45 12.4 1.275 1.275 9.433 9.433 fft3d_s 802 15.6 8.600 8.600 8.608 8.608 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.945 7.945 calculate_rho_elec 45 8.9 0.648 0.648 7.944 7.944 pw_integral_ab 2539 7.4 7.429 7.429 7.429 7.429 xc_pw_divergence 45 12.4 0.001 0.001 6.653 6.653 pw_scatter_s 429 15.8 6.615 6.615 6.615 6.615 qmmm_forces 6 3.8 0.003 0.003 6.332 6.332 qmmm_forces_with_gaussian 6 4.8 0.047 0.047 5.874 5.874 qs_ks_ddapc 45 10.4 0.001 0.001 5.445 5.445 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 4.991 4.991 init_scf_loop 6 6.8 0.000 0.000 4.853 4.853 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.511 4.511 sum_up_and_integrate 45 10.4 0.950 0.950 4.341 4.341 density_rs2pw 45 9.9 0.002 0.002 3.862 3.862 qmmm_forces_gaussian_low_G 6 6.8 3.735 3.735 3.735 3.735 cp_ddapc_apply_CD 45 11.4 0.007 0.007 3.586 3.586 pw_poisson_solve 51 9.9 0.771 0.771 3.532 3.532 grid_collocate_task_list 45 9.9 3.435 3.435 3.435 3.435 integrate_v_rspace 45 11.4 0.008 0.008 3.390 3.390 fist_calc_energy_force 6 3.8 0.002 0.002 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 0.037 0.052 64.500 64.513 qs_mol_dyn_low 1 2.0 0.003 0.004 63.354 63.417 qs_forces 6 3.8 0.001 0.001 47.617 47.617 qs_energies 6 4.8 0.000 0.001 45.498 45.498 scf_env_do_scf 6 5.8 0.000 0.001 44.410 44.411 scf_env_do_scf_inner_loop 113 6.2 0.003 0.019 42.590 42.593 rebuild_ks_matrix 119 8.1 0.000 0.000 31.748 31.756 qs_ks_build_kohn_sham_matrix 119 9.1 0.017 0.021 31.747 31.756 qs_ks_update_qs_env 119 7.3 0.001 0.001 29.941 29.949 velocity_verlet 5 3.0 0.002 0.005 25.605 25.609 pw_transfer 2446 12.3 0.162 0.185 23.041 23.566 fft_wrap_pw1pw2 2059 13.4 0.023 0.027 22.640 23.218 fft_wrap_pw1pw2_150 1321 14.9 3.522 4.290 21.672 22.162 qs_vxc_create 119 10.1 0.003 0.004 17.263 17.269 xc_vxc_pw_create 119 11.1 0.159 0.225 17.261 17.266 fft3d_ps 2059 15.4 7.745 8.776 15.244 17.071 xc_pw_derive 714 13.1 0.008 0.010 13.338 13.594 qs_rho_update_rho_low 119 7.3 0.001 0.001 12.277 12.287 calculate_rho_elec 119 8.3 0.050 0.057 12.276 12.286 sum_up_and_integrate 119 10.1 0.084 0.102 10.459 10.479 integrate_v_rspace 119 11.1 0.004 0.005 10.374 10.402 xc_pw_divergence 119 12.1 0.004 0.005 8.736 9.004 mp_alltoall_z22v 2059 17.4 6.092 8.562 6.092 8.562 xc_rho_set_and_dset_create 119 12.1 0.348 0.449 8.058 8.280 qmmm_forces 6 3.8 0.002 0.003 7.898 7.898 density_rs2pw 119 9.3 0.006 0.007 7.439 7.793 qmmm_forces_with_gaussian 6 4.8 0.007 0.008 7.449 7.734 rs_pw_transfer 988 11.5 0.013 0.015 7.325 7.651 qmmm_el_coupling 6 3.8 0.000 0.000 6.812 7.029 qmmm_elec_with_gaussian 6 4.8 0.003 0.005 6.811 7.028 potential_pw2rs 119 12.1 0.006 0.007 6.401 6.421 x_to_yz 1095 16.8 0.807 0.896 4.005 5.053 grid_collocate_task_list 119 9.3 4.569 4.985 4.569 4.985 yz_to_x 964 16.0 0.545 0.668 3.438 4.945 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.151 4.185 grid_integrate_task_list 119 12.1 3.645 3.862 3.645 3.862 mp_waitany 4028 12.8 3.098 3.797 3.098 3.797 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.532 3.688 qmmm_forces_gaussian_low_G 6 6.8 3.413 3.444 3.413 3.444 qmmm_elec_gaussian_low_G 6 6.8 2.932 3.084 2.932 3.084 pw_restrict_s3 18 5.8 1.424 1.511 2.638 2.895 rs_pw_transfer_PW2RS_150 125 13.9 0.811 1.006 2.775 2.821 pw_gather_p 964 15.0 2.205 2.613 2.205 2.613 rs_pw_transfer_RS2PW_150 125 11.2 0.647 0.839 2.195 2.559 qs_ks_ddapc 119 10.1 0.002 0.003 2.405 2.529 qs_scf_new_mos 113 7.2 0.001 0.001 2.519 2.525 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.519 2.524 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.226 2.440 pw_prolongate_s3 18 6.8 1.200 1.262 2.226 2.440 ot_scf_mini 113 9.2 0.001 0.001 2.429 2.433 dbcsr_multiply_generic 2588 12.3 0.060 0.063 2.066 2.130 mp_sum_d 5822 12.2 1.258 1.975 1.258 1.975 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.826 1.827 pw_integral_ab 2761 7.7 1.181 1.345 1.657 1.818 init_scf_loop 6 6.8 0.000 0.000 1.815 1.815 mp_sum_dm3 33 5.7 1.597 1.651 1.597 1.651 pw_scatter_p 1095 15.8 1.596 1.640 1.596 1.640 ot_mini 113 10.2 0.000 0.001 1.328 1.333 ------------------------------------------------------------------------------- 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=24.87299999999999, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=85.831, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.6, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=7.429, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=6.615, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.735, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.435, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=2.933, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=31.400999999999996, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.932, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=1.181, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_scatter_s", label="pw_scatter_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.413, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.569, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=3.522, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.645, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.745, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=6.092, yerr=0.0 Summary: Performance test took 34 minutes. Status: OK Removing intermediate container c213f675eccc ---> 7c2c808b5593 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in e801cba9f905 Removing intermediate container e801cba9f905 ---> 9ba5eb02a2af Step 42/42 : ENTRYPOINT [] ---> Running in a2ffbc43feb9 Removing intermediate container a2ffbc43feb9 ---> c29532398c92 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built c29532398c92 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: 2023-08-15 20:31:45+00:00