StartDate: 2022-03-16 11:03:00+00:00 CpuId: 64x Intel Xeon W 2000 / D-2100 (Skylake / Cascade Lake) {Skylake}, 14nm CommitSHA: 75771c7f8d7c83d53aa3b6ffac22d0d5bc926a4c CommitTime: 2022-03-16 10:58:38 +0100 CommitAuthor: Juerg Hutter CommitSubject: CP2K_FLAGS output regularized (#2009) Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=75771c7f8d7c83d53aa3b6ffac22d0d5bc926a4c Sending build context to Docker daemon 362.4MB Step 1/41 : FROM ubuntu:20.04 20.04: Pulling from library/ubuntu 7c3b88808835: Already exists Digest: sha256:8ae9bafbb64f63a50caab98fd3a5e37b3eb837a3e0780b78e5218e63193961f9 Status: Downloaded newer image for ubuntu:20.04 ---> 2b4cba85892a Step 2/41 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 2478d1e60fc2 Step 3/41 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> f04a754c1b4e Step 4/41 : RUN ./install_requirements.sh ubuntu:20.04 ---> Using cache ---> b7c4b3bf2ba3 Step 5/41 : RUN mkdir scripts ---> Using cache ---> 0be4797ba2b9 Step 6/41 : 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 ---> 20eb19422415 Step 7/41 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> bf33731cd10d Step 8/41 : RUN ./install_cp2k_toolchain.sh --install-all --mpi-mode=mpich --dry-run ---> Using cache ---> 19b0b3c97393 Step 9/41 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 9fcf7ef497eb Step 10/41 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 5196fa37023c Step 11/41 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> dd293eb974d0 Step 12/41 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> e76392d58f21 Step 13/41 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> a0c151ba1669 Step 14/41 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 89cd0e6c3bff Step 15/41 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 3f34682c7ad5 Step 16/41 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> f53b7bbcf5ed Step 17/41 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 6059648341ff Step 18/41 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> a38ee222da95 Step 19/41 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 033717c35479 Step 20/41 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> ce105c9308f4 Step 21/41 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> da58aaf5626a Step 22/41 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 88850f0a7d75 Step 23/41 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 6180e9da3590 Step 24/41 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> b03deb66bd99 Step 25/41 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> ea28303902dd Step 26/41 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 01ae9c180998 Step 27/41 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 0532b5422729 Step 28/41 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 78e52c29e47b Step 29/41 : WORKDIR /opt/cp2k ---> Using cache ---> 84f01a434462 Step 30/41 : COPY ./Makefile . ---> Using cache ---> 6f3765799877 Step 31/41 : COPY ./src ./src ---> 2c873141a893 Step 32/41 : COPY ./exts ./exts ---> 8750d0f03c3f Step 33/41 : COPY ./tools/build_utils ./tools/build_utils ---> 274144a69644 Step 34/41 : 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 )" ---> Running in 52c8d6d7e4c6 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 52c8d6d7e4c6 ---> 0cc0b41a1438 Step 35/41 : COPY ./data ./data ---> d2c41c6d4e1a Step 36/41 : COPY ./tests ./tests ---> 28c30ec39898 Step 37/41 : COPY ./tools/regtesting ./tools/regtesting ---> 97d5c8f92853 Step 38/41 : COPY ./benchmarks ./benchmarks ---> 8b00c073256b Step 39/41 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 8c2e368782e5 Step 40/41 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 3cd57b73abcc ========== 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 0.041 0.041 170.781 170.781 qs_mol_dyn_low 1 2.0 0.004 0.004 169.880 169.880 qs_forces 11 3.9 0.002 0.002 169.818 169.818 qs_energies 11 4.9 0.001 0.001 158.845 158.845 scf_env_do_scf 11 5.9 0.001 0.001 128.982 128.982 velocity_verlet 10 3.0 0.002 0.002 118.142 118.142 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 87.448 87.448 init_scf_loop 11 6.9 0.000 0.000 41.332 41.332 prepare_preconditioner 11 7.9 0.000 0.000 37.290 37.290 make_preconditioner 11 8.9 0.000 0.000 37.290 37.290 make_full_inverse_cholesky 11 9.9 0.000 0.000 35.188 35.188 rebuild_ks_matrix 119 8.3 0.001 0.001 34.153 34.153 qs_ks_build_kohn_sham_matrix 119 9.3 0.023 0.023 34.152 34.152 qs_ks_update_qs_env 119 7.6 0.001 0.001 32.009 32.009 qs_rho_update_rho 119 7.7 0.001 0.001 31.136 31.136 calculate_rho_elec 119 8.7 1.585 1.585 31.135 31.135 qs_scf_new_mos 108 7.5 0.001 0.001 30.672 30.672 qs_scf_loop_do_ot 108 8.5 0.001 0.001 30.671 30.671 ot_scf_mini 108 9.5 0.004 0.004 28.448 28.448 dbcsr_multiply_generic 2286 12.5 0.212 0.212 26.751 26.751 grid_collocate_task_list 119 9.7 24.544 24.544 24.544 24.544 sum_up_and_integrate 119 10.3 0.420 0.420 21.113 21.113 cp_fm_cholesky_invert 11 10.9 20.803 20.803 20.803 20.803 integrate_v_rspace 119 11.3 0.649 0.649 20.693 20.693 grid_integrate_task_list 119 12.3 17.283 17.283 17.283 17.283 ot_mini 108 10.5 0.001 0.001 16.965 16.965 make_m2s 4572 13.5 0.075 0.075 15.033 15.033 init_scf_run 11 5.9 0.001 0.001 14.405 14.405 scf_env_initial_rho_setup 11 6.9 0.001 0.001 14.404 14.404 wfi_extrapolate 11 7.9 0.001 0.001 13.503 13.503 cp_gemm 81 9.0 0.000 0.000 11.531 11.531 cp_gemm_cosma 81 10.0 11.531 11.531 11.531 11.531 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 11.372 11.372 qs_ot_get_derivative 108 11.5 0.002 0.002 8.722 8.722 pw_transfer 1439 11.6 0.107 0.107 8.560 8.560 ot_diis_step 108 11.5 0.006 0.006 8.238 8.238 fft_wrap_pw1pw2 1201 12.6 0.011 0.011 8.199 8.199 make_images 4572 14.5 2.926 2.926 8.025 8.025 cp_fm_cholesky_decompose 22 10.9 7.906 7.906 7.906 7.906 dbcsr_make_dense_low 5837 15.5 0.108 0.108 7.170 7.170 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 7.076 7.076 apply_single 119 13.6 0.001 0.001 7.076 7.076 make_dense_data 5837 16.5 6.297 6.297 7.037 7.037 fft_wrap_pw1pw2_140 487 13.2 0.602 0.602 6.928 6.928 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 6.895 6.895 qs_ot_get_p 119 10.4 0.002 0.002 6.875 6.875 dbcsr_complete_redistribute 329 12.2 3.160 3.160 6.599 6.599 dbcsr_make_images_dense 3978 14.8 0.030 0.030 6.486 6.486 multiply_cannon 2286 13.5 1.181 1.181 6.373 6.373 qs_env_update_s_mstruct 11 6.9 0.000 0.000 6.274 6.274 dbcsr_copy 2102 12.0 0.316 0.316 5.822 5.822 qs_create_task_list 11 7.9 0.000 0.000 5.707 5.707 generate_qs_task_list 11 8.9 3.923 3.923 5.707 5.707 dbcsr_copy_into_existing 22 7.9 5.453 5.453 5.453 5.453 copy_dbcsr_to_fm 153 11.3 0.004 0.004 5.425 5.425 qs_ot_p2m_diag 50 11.0 0.231 0.231 5.139 5.139 density_rs2pw 119 9.7 0.008 0.008 5.006 5.006 pw_poisson_solve 119 10.3 1.998 1.998 4.827 4.827 multiply_cannon_loop 2286 14.5 0.061 0.061 4.556 4.556 cp_dbcsr_syevd 50 12.0 0.005 0.005 4.526 4.526 multiply_cannon_multrec 2286 15.5 4.403 4.403 4.494 4.494 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 4.449 4.449 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 4.411 4.411 cp_fm_diag_elpa 50 13.0 0.001 0.001 4.345 4.345 cp_fm_diag_elpa_base 50 14.0 4.284 4.284 4.344 4.344 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.075 4.075 qs_energies_compute_matrix_w 11 5.9 0.000 0.000 3.909 3.909 calculate_w_matrix_ot 11 6.9 0.009 0.009 3.909 3.909 fft3d_s 1202 14.6 3.815 3.815 3.822 3.822 copy_fm_to_dbcsr 176 11.2 0.002 0.002 3.534 3.534 ------------------------------------------------------------------------------- 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 0.014 0.020 77.871 77.872 qs_mol_dyn_low 1 2.0 0.008 0.011 77.690 77.697 qs_forces 11 3.9 0.002 0.002 77.628 77.628 qs_energies 11 4.9 0.002 0.002 72.396 72.398 scf_env_do_scf 11 5.9 0.001 0.001 65.622 65.625 scf_env_do_scf_inner_loop 108 6.5 0.003 0.011 60.823 60.823 velocity_verlet 10 3.0 0.002 0.003 46.699 46.701 rebuild_ks_matrix 119 8.3 0.001 0.001 30.189 30.230 qs_ks_build_kohn_sham_matrix 119 9.3 0.025 0.026 30.188 30.229 qs_ks_update_qs_env 119 7.6 0.001 0.002 26.816 26.857 qs_rho_update_rho 119 7.7 0.001 0.001 23.336 23.356 calculate_rho_elec 119 8.7 0.049 0.051 23.335 23.355 sum_up_and_integrate 119 10.3 0.050 0.054 23.186 23.201 integrate_v_rspace 119 11.3 0.005 0.006 23.135 23.155 dbcsr_multiply_generic 2286 12.5 0.139 0.144 19.313 19.388 grid_collocate_task_list 119 9.7 15.952 16.693 15.952 16.693 grid_integrate_task_list 119 12.3 15.736 16.291 15.736 16.291 qs_scf_new_mos 108 7.5 0.001 0.001 15.561 15.619 qs_scf_loop_do_ot 108 8.5 0.001 0.001 15.560 15.618 ot_scf_mini 108 9.5 0.004 0.004 14.619 14.676 multiply_cannon 2286 13.5 0.242 0.250 12.954 13.225 multiply_cannon_loop 2286 14.5 0.237 0.250 11.767 12.138 mp_waitall_1 169478 16.3 10.225 10.525 10.225 10.525 rs_pw_transfer 974 11.9 0.019 0.020 7.916 8.752 ot_mini 108 10.5 0.001 0.001 8.688 8.749 density_rs2pw 119 9.7 0.010 0.010 6.687 7.549 multiply_cannon_metrocomm3 18288 15.5 0.088 0.093 6.674 7.018 pw_transfer 1439 11.6 0.152 0.160 6.731 6.846 fft_wrap_pw1pw2 1201 12.6 0.015 0.016 6.398 6.495 potential_pw2rs 119 12.3 0.010 0.011 6.058 6.072 fft_wrap_pw1pw2_140 487 13.2 0.647 0.691 5.558 5.788 fft3d_ps 1201 14.6 2.599 2.785 4.796 4.869 init_scf_loop 11 6.9 0.001 0.001 4.779 4.780 init_scf_run 11 5.9 0.000 0.002 4.648 4.648 scf_env_initial_rho_setup 11 6.9 0.000 0.001 4.648 4.648 apply_preconditioner_dbcsr 119 12.6 0.000 0.001 4.421 4.480 apply_single 119 13.6 0.001 0.001 4.421 4.479 ot_diis_step 108 11.5 0.005 0.006 4.475 4.476 make_m2s 4572 13.5 0.079 0.081 4.382 4.449 qs_ot_get_derivative 108 11.5 0.001 0.002 4.172 4.232 wfi_extrapolate 11 7.9 0.001 0.001 4.214 4.214 multiply_cannon_multrec 18288 15.5 3.733 3.913 3.752 3.933 make_images 4572 14.5 0.193 0.199 3.654 3.716 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.622 3.629 mp_waitany 9880 13.7 2.727 3.591 2.727 3.591 rs_pw_transfer_RS2PW_140 130 11.5 0.608 0.647 2.444 3.298 rs_pw_transfer_PW2RS_140 130 13.9 1.474 1.536 3.060 3.101 mp_alltoall_d11v 2130 13.8 1.706 2.371 1.706 2.371 qs_ot_get_p 119 10.4 0.001 0.001 1.916 1.990 rs_gather_matrices 119 12.3 0.151 0.162 1.275 1.969 make_images_data 4572 15.5 0.064 0.071 1.750 1.843 mp_alltoall_z22v 1201 16.6 1.480 1.687 1.480 1.687 hybrid_alltoall_any 4725 16.4 0.132 0.458 1.548 1.630 prepare_preconditioner 11 7.9 0.000 0.000 1.599 1.615 make_preconditioner 11 8.9 0.000 0.000 1.599 1.615 qs_energies_init_hamiltonians 11 5.9 0.001 0.001 1.585 1.586 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 1.462 1.563 ------------------------------------------------------------------------------- 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=84.31099999999999, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=24.544, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=20.803, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=17.283, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=11.531, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=7.906, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.403, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", 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=29.497999999999998, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.952, 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="grid_integrate_task_list", label="grid_integrate_task_list", y=15.736, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_gemm_cosma", label="cp_gemm_cosma", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.733, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=10.225, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.727, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.036 0.036 223.820 223.820 qs_mol_dyn_low 1 2.0 0.004 0.004 222.946 222.946 qs_forces 11 3.9 0.002 0.002 222.885 222.885 qs_energies 11 4.9 0.001 0.001 208.423 208.423 scf_env_do_scf 11 5.9 0.001 0.001 174.414 174.414 velocity_verlet 10 3.0 0.002 0.002 150.028 150.028 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 129.718 129.718 rebuild_ks_matrix 107 8.3 0.001 0.001 63.918 63.918 qs_ks_build_kohn_sham_matrix 107 9.3 0.020 0.020 63.918 63.918 qs_ks_update_qs_env 107 7.6 0.001 0.001 57.820 57.820 qs_rho_update_rho 107 7.7 0.001 0.001 57.490 57.490 calculate_rho_elec 107 8.7 1.417 1.417 57.489 57.489 sum_up_and_integrate 107 10.3 0.381 0.381 52.262 52.262 integrate_v_rspace 107 11.3 0.532 0.532 51.881 51.881 grid_collocate_task_list 107 9.7 51.609 51.609 51.609 51.609 grid_integrate_task_list 107 12.3 48.840 48.840 48.840 48.840 init_scf_loop 11 6.9 0.000 0.000 44.479 44.479 prepare_preconditioner 11 7.9 0.000 0.000 37.098 37.098 make_preconditioner 11 8.9 0.000 0.000 37.098 37.098 make_full_inverse_cholesky 11 9.9 0.000 0.000 35.117 35.117 qs_scf_new_mos 96 7.5 0.001 0.001 27.033 27.033 qs_scf_loop_do_ot 96 8.5 0.001 0.001 27.032 27.032 ot_scf_mini 96 9.5 0.003 0.003 25.110 25.110 dbcsr_multiply_generic 1966 12.4 0.191 0.191 23.599 23.599 cp_fm_cholesky_invert 11 10.9 20.977 20.977 20.977 20.977 init_scf_run 11 5.9 0.001 0.001 17.272 17.272 scf_env_initial_rho_setup 11 6.9 0.001 0.001 17.272 17.272 wfi_extrapolate 11 7.9 0.001 0.001 16.120 16.120 ot_mini 96 10.5 0.001 0.001 15.211 15.211 make_m2s 3932 13.4 0.067 0.067 13.434 13.434 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 12.627 12.627 cp_gemm 81 9.0 0.000 0.000 11.623 11.623 cp_gemm_cosma 81 10.0 11.622 11.622 11.622 11.622 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 7.863 7.863 qs_ot_get_derivative 96 11.5 0.002 0.002 7.823 7.823 cp_fm_cholesky_decompose 22 10.9 7.774 7.774 7.774 7.774 pw_transfer 1295 11.6 0.098 0.098 7.684 7.684 qs_env_update_s_mstruct 11 6.9 0.000 0.000 7.537 7.537 ot_diis_step 96 11.5 0.006 0.006 7.384 7.384 fft_wrap_pw1pw2 1081 12.6 0.010 0.010 7.356 7.356 make_images 3932 14.4 2.684 2.684 7.115 7.115 qs_create_task_list 11 7.9 0.000 0.000 6.943 6.943 generate_qs_task_list 11 8.9 5.173 5.173 6.943 6.943 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 6.596 6.596 dbcsr_make_dense_low 4961 15.5 0.094 0.094 6.545 6.545 dbcsr_complete_redistribute 317 12.2 3.144 3.144 6.462 6.462 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 6.438 6.438 apply_single 107 13.6 0.001 0.001 6.437 6.437 make_dense_data 4961 16.5 5.796 5.796 6.429 6.429 fft_wrap_pw1pw2_140 439 13.2 0.533 0.533 6.209 6.209 qs_ot_get_p 107 10.4 0.001 0.001 5.924 5.924 dbcsr_make_images_dense 3386 14.7 0.026 0.026 5.857 5.857 dbcsr_copy 1855 11.9 0.290 0.290 5.778 5.778 multiply_cannon 1966 13.4 0.962 0.962 5.593 5.593 dbcsr_copy_into_existing 22 7.9 5.438 5.438 5.438 5.438 copy_dbcsr_to_fm 147 11.2 0.004 0.004 5.308 5.308 ------------------------------------------------------------------------------- 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 0.011 133.541 133.542 qs_mol_dyn_low 1 2.0 0.005 0.006 133.412 133.418 qs_forces 11 3.9 0.002 0.002 133.352 133.352 qs_energies 11 4.9 0.001 0.002 124.310 124.313 scf_env_do_scf 11 5.9 0.001 0.001 114.666 114.667 scf_env_do_scf_inner_loop 96 6.5 0.003 0.010 106.537 106.538 velocity_verlet 10 3.0 0.002 0.003 79.338 79.340 rebuild_ks_matrix 107 8.3 0.001 0.001 60.888 60.941 qs_ks_build_kohn_sham_matrix 107 9.3 0.022 0.023 60.887 60.940 sum_up_and_integrate 107 10.3 0.045 0.049 54.666 54.684 integrate_v_rspace 107 11.3 0.005 0.005 54.621 54.643 qs_ks_update_qs_env 107 7.6 0.001 0.001 53.702 53.749 qs_rho_update_rho 107 7.7 0.001 0.001 50.509 50.521 calculate_rho_elec 107 8.7 0.043 0.045 50.508 50.520 grid_integrate_task_list 107 12.3 47.086 47.953 47.086 47.953 grid_collocate_task_list 107 9.7 43.169 44.379 43.169 44.379 dbcsr_multiply_generic 1966 12.4 0.121 0.125 17.043 17.170 qs_scf_new_mos 96 7.5 0.001 0.001 13.579 13.613 qs_scf_loop_do_ot 96 8.5 0.001 0.001 13.578 13.613 ot_scf_mini 96 9.5 0.003 0.004 12.744 12.780 multiply_cannon 1966 13.4 0.210 0.217 11.470 11.816 multiply_cannon_loop 1966 14.4 0.206 0.218 10.429 10.688 rs_pw_transfer 878 11.9 0.016 0.018 7.922 9.268 mp_waitall_1 146670 16.2 9.027 9.234 9.027 9.234 init_scf_loop 11 6.9 0.000 0.001 8.110 8.111 density_rs2pw 107 9.7 0.009 0.010 6.713 8.097 init_scf_run 11 5.9 0.000 0.002 7.566 7.566 scf_env_initial_rho_setup 11 6.9 0.000 0.001 7.566 7.566 ot_mini 96 10.5 0.001 0.001 7.507 7.543 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 7.408 7.416 wfi_extrapolate 11 7.9 0.001 0.001 6.914 6.914 multiply_cannon_metrocomm3 15728 15.4 0.076 0.078 5.900 6.260 pw_transfer 1295 11.6 0.137 0.146 5.994 6.077 fft_wrap_pw1pw2 1081 12.6 0.014 0.015 5.698 5.777 potential_pw2rs 107 12.3 0.009 0.010 5.495 5.506 fft_wrap_pw1pw2_140 439 13.2 0.568 0.597 4.939 5.119 mp_waitany 8968 13.7 3.352 4.689 3.352 4.689 fft3d_ps 1081 14.6 2.325 2.486 4.276 4.336 rs_pw_transfer_RS2PW_140 118 11.5 0.449 0.481 2.955 4.298 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.884 3.939 apply_single 107 13.6 0.001 0.001 3.884 3.939 make_m2s 3932 13.4 0.068 0.071 3.855 3.913 ot_diis_step 96 11.5 0.005 0.005 3.886 3.887 mp_alltoall_d11v 1998 13.7 2.377 3.655 2.377 3.655 qs_ot_get_derivative 96 11.5 0.001 0.001 3.587 3.620 multiply_cannon_multrec 15728 15.4 3.338 3.488 3.355 3.506 make_images 3932 14.4 0.169 0.175 3.222 3.288 rs_gather_matrices 107 12.3 0.137 0.148 1.978 3.251 rs_pw_transfer_PW2RS_140 118 13.9 1.375 1.420 2.846 2.882 ------------------------------------------------------------------------------- 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=82.99799999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=51.609, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=48.84, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=20.977, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=11.622, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=7.774, 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="multiply_cannon_multrec", label="multiply_cannon_multrec", 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=27.569000000000003, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=43.169, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=47.086, 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="cp_gemm_cosma", label="cp_gemm_cosma", 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="mp_waitany", label="mp_waitany", y=3.352, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.338, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=9.027, 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 0.457 0.457 272.719 272.719 qs_energies 1 2.0 0.000 0.000 271.265 271.265 scf_env_do_scf 1 3.0 0.000 0.000 268.589 268.589 qs_ks_update_qs_env 8 5.0 0.000 0.000 249.383 249.383 rebuild_ks_matrix 7 6.0 0.000 0.000 249.266 249.266 qs_ks_build_kohn_sham_matrix 7 7.0 0.002 0.002 249.266 249.266 hfx_ks_matrix 7 8.0 0.000 0.000 177.469 177.469 integrate_four_center 7 9.0 2.489 2.489 177.433 177.433 integrate_four_center_main 7 10.0 1.128 1.128 163.493 163.493 integrate_four_center_bin 454 11.0 162.364 162.364 162.364 162.364 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 152.839 152.839 init_scf_loop 1 4.0 0.000 0.000 115.733 115.733 cp_gemm 129 10.3 0.001 0.001 55.568 55.568 cp_gemm_cosma 129 11.3 55.568 55.568 55.568 55.568 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 34.744 34.744 admm_fit_mo_coeffs 7 9.0 0.000 0.000 32.725 32.725 admm_mo_merge_derivs 7 8.0 0.000 0.000 27.943 27.943 merge_mo_derivs_diag 7 9.0 0.023 0.023 27.943 27.943 purify_mo_diag 7 10.0 0.001 0.001 18.651 18.651 prepare_preconditioner 1 5.0 0.000 0.000 14.920 14.920 make_preconditioner 1 6.0 0.000 0.000 14.920 14.920 fit_mo_coeffs 7 10.0 0.000 0.000 14.073 14.073 integrate_four_center_load 7 10.0 0.002 0.002 11.021 11.021 hfx_load_balance 1 11.0 0.006 0.006 11.020 11.020 arnoldi_normal_ev 11 9.3 0.003 0.003 8.803 8.803 estimate_cond_num 1 7.0 0.000 0.000 8.718 8.718 build_subspace 28 9.5 0.020 0.020 8.684 8.684 hfx_load_balance_bin 1 12.0 5.493 5.493 5.493 5.493 hfx_load_balance_count 1 12.0 5.488 5.488 5.488 5.488 ------------------------------------------------------------------------------- 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 0.225 0.231 193.995 193.996 qs_energies 1 2.0 0.000 0.000 193.618 193.619 scf_env_do_scf 1 3.0 0.000 0.001 192.994 192.995 qs_ks_update_qs_env 8 5.0 0.000 0.000 189.705 189.705 rebuild_ks_matrix 7 6.0 0.000 0.000 189.689 189.689 qs_ks_build_kohn_sham_matrix 7 7.0 0.002 0.002 189.689 189.689 hfx_ks_matrix 7 8.0 0.001 0.001 177.859 177.860 integrate_four_center 7 9.0 0.110 0.404 177.841 177.842 integrate_four_center_main 7 10.0 0.005 0.005 160.178 164.252 integrate_four_center_bin 448 11.0 160.173 164.247 160.173 164.247 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 112.776 112.776 init_scf_loop 1 4.0 0.000 0.000 80.216 80.216 integrate_four_center_load 7 10.0 0.000 0.001 11.314 11.322 hfx_load_balance 1 11.0 0.001 0.002 11.314 11.321 mp_sync 70 11.3 5.452 7.863 5.452 7.863 hfx_load_balance_count 1 12.0 5.390 5.676 5.390 5.676 hfx_load_balance_bin 1 12.0 5.380 5.627 5.380 5.627 qs_vxc_create 14 8.0 0.001 0.001 3.950 3.950 xc_vxc_pw_create 14 9.0 0.013 0.014 3.949 3.950 cp_gemm 129 10.3 0.001 0.001 3.925 3.932 cp_gemm_cosma 129 11.3 3.924 3.931 3.924 3.931 ------------------------------------------------------------------------------- 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=41.31699999999998, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=162.364, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=55.568, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.493, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.488, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=2.489, 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=13.566000000000003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=160.173, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="cp_gemm_cosma", label="cp_gemm_cosma", y=3.924, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.38, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.39, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.11, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=5.452, 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 0.014 0.014 366.975 366.975 qs_energies 1 2.0 0.000 0.000 366.416 366.416 mp2_main 1 3.0 0.000 0.000 359.833 359.833 mp2_gpw_main 1 4.0 0.000 0.000 359.393 359.393 rpa_ri_compute_en 1 5.0 0.000 0.000 346.996 346.996 rpa_num_int 1 6.0 0.001 0.001 346.971 346.971 compute_mat_P_omega 1 7.0 0.002 0.002 184.041 184.041 compute_mat_P_omega_contract 10 8.0 12.787 12.787 182.664 182.664 dbt_total 2336 9.6 0.023 0.023 174.586 174.586 cp_gemm 105 8.4 0.000 0.000 130.900 130.900 cp_gemm_cosma 105 9.4 130.899 130.899 130.899 130.899 dbt_contract 787 11.0 50.551 50.551 106.930 106.930 GW_matrix_operations 10 7.0 0.006 0.006 94.342 94.342 dbt_copy 1103 10.7 22.137 22.137 66.267 66.267 compute_mat_P_omega_calc_M_occ 250 9.0 12.797 12.797 66.181 66.181 dbt_tas_total 1149 12.2 0.333 0.333 52.910 52.910 dbt_tas_multiply 807 12.1 0.004 0.004 51.554 51.554 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 45.809 45.809 contract_P_omega_with_mat_L 10 8.0 0.000 0.000 43.658 43.658 dbt_tas_dbm 807 14.1 0.006 0.006 40.711 40.711 dbm_multiply 807 16.1 40.698 40.698 40.698 40.698 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 40.495 40.495 dbt_tas_mm_1N 524 15.1 0.002 0.002 24.760 24.760 dbt_tas_copy 574 11.4 17.432 17.432 21.094 21.094 compute_QP_energies 1 7.0 0.000 0.000 20.701 20.701 compute_self_energy_cubic_gw 1 8.0 0.110 0.110 20.701 20.701 compute_mat_P_omega_copy_M_occ 250 9.0 0.002 0.002 19.333 19.333 compute_mat_P_omega_calc_P_t 250 9.0 0.002 0.002 15.351 15.351 dbt_tas_mm_2 251 15.0 0.002 0.002 14.113 14.113 dbt_tas_reserve_blocks_index 3261 13.7 7.895 7.895 13.782 13.782 compute_mat_P_omega_copy_M_vir 250 9.0 0.002 0.002 13.705 13.705 dbt_copy_nocomm 251 12.0 11.921 11.921 13.540 13.540 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 12.382 12.382 dbt_reserve_blocks_index 2280 12.5 1.640 1.640 11.399 11.399 dbt_reserve_blocks_index_array 2222 11.6 0.014 0.014 11.361 11.361 cp_fm_cholesky_invert 10 8.0 9.537 9.537 9.537 9.537 contract_cubic_gw 21 9.0 0.000 0.000 8.919 8.919 ------------------------------------------------------------------------------- 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 0.008 56.167 56.168 qs_energies 1 2.0 0.001 0.001 56.049 56.050 mp2_main 1 3.0 0.000 0.000 54.499 54.500 mp2_gpw_main 1 4.0 0.000 0.001 54.437 54.438 rpa_ri_compute_en 1 5.0 0.000 0.000 52.528 52.529 rpa_num_int 1 6.0 0.001 0.001 52.520 52.521 dbt_total 2336 9.6 0.019 0.020 41.577 41.578 compute_mat_P_omega 1 7.0 0.001 0.002 40.346 40.352 compute_mat_P_omega_contract 10 8.0 0.791 0.813 40.070 40.075 dbt_contract 787 11.0 1.957 2.096 30.042 30.048 dbt_tas_total 1149 12.2 0.083 0.089 26.158 26.159 dbt_tas_multiply 807 12.1 0.003 0.004 26.069 26.071 dbt_tas_dbm 807 14.1 0.005 0.006 17.939 17.940 dbm_multiply 807 16.1 14.390 15.278 14.390 15.278 compute_mat_P_omega_calc_M_occ 250 9.0 0.763 0.790 13.349 13.350 dbt_copy 1111 10.7 4.228 4.490 9.850 10.197 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 9.743 9.743 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 8.259 8.260 dbt_tas_mm_1N 524 15.1 0.002 0.003 7.248 7.838 mp_sync 8706 11.6 6.567 7.765 6.567 7.765 dbt_tas_mm_2 251 15.0 0.002 0.003 7.546 7.547 cp_gemm 105 8.4 0.000 0.000 7.186 7.197 cp_gemm_cosma 105 9.4 7.185 7.197 7.185 7.197 GW_matrix_operations 10 7.0 0.001 0.002 4.679 4.686 compute_QP_energies 1 7.0 0.000 0.000 4.438 4.439 compute_self_energy_cubic_gw 1 8.0 0.006 0.008 4.436 4.438 dbt_communicate_buffer 1098 11.7 0.097 0.105 4.093 4.268 mp_waitall_2 3776 14.7 3.888 4.236 3.888 4.236 contract_cubic_gw 21 9.0 0.000 0.000 3.390 3.391 dbt_reserve_blocks_index 2849 12.4 0.109 0.116 2.735 3.011 dbt_reserve_blocks_index_array 2791 11.4 0.013 0.013 2.733 3.008 dbt_tas_reserve_blocks_index 3300 13.8 0.276 0.294 2.691 2.956 dbm_reserve_blocks 3696 14.8 2.492 2.734 2.492 2.734 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.665 2.665 contract_P_omega_with_mat_L 10 8.0 0.000 0.000 2.538 2.540 dbt_tas_replicate 396 14.1 1.233 1.486 2.341 2.388 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 1.904 1.907 convert_to_new_pgrid 2421 14.1 0.040 0.045 1.725 1.870 compute_mat_P_omega_copy_M_vir 250 9.0 0.002 0.002 1.849 1.853 dbm_copy 1608 15.1 1.675 1.825 1.675 1.825 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.634 1.641 scf_env_do_scf 1 3.0 0.000 0.000 1.491 1.492 scf_env_do_scf_inner_loop 17 4.0 0.001 0.001 1.491 1.492 mp_max_i 1992 9.8 1.015 1.283 1.015 1.283 dbm_add 807 14.1 1.103 1.173 1.103 1.173 ------------------------------------------------------------------------------- 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=105.25800000000004, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=130.899, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_contract", label="dbt_contract", y=50.551, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=40.698, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_copy", label="dbt_copy", y=22.137, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_tas_copy", label="dbt_tas_copy", y=17.432, 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=17.952000000000005, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_gemm_cosma", label="cp_gemm_cosma", y=7.185, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_contract", label="dbt_contract", y=1.957, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=14.39, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_copy", label="dbt_copy", y=4.228, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_tas_copy", label="dbt_tas_copy", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.888, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=6.567, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.024 0.024 756.998 756.998 qs_forces 1 2.0 0.000 0.000 756.098 756.098 rebuild_ks_matrix 7 6.6 0.000 0.000 745.147 745.147 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.002 745.147 745.147 hfx_ks_matrix 7 8.6 0.000 0.000 742.286 742.286 dbt_total 4858 11.6 0.053 0.053 635.369 635.369 hfx_ri_update_ks 7 9.6 0.000 0.000 524.721 524.721 hfx_ri_update_ks_Pmat 7 10.6 69.332 69.332 524.716 524.716 qs_energies 1 3.0 0.000 0.000 471.406 471.406 scf_env_do_scf 1 4.0 0.000 0.000 470.971 470.971 qs_ks_update_qs_env 8 6.0 0.000 0.000 460.540 460.540 dbt_contract 1473 13.0 190.185 190.185 425.860 425.860 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 284.613 284.613 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 274.303 274.303 dbt_tas_total 2391 14.1 2.118 2.118 252.901 252.901 dbt_tas_multiply 1482 14.0 0.007 0.007 220.414 220.414 hfx_ri_update_forces 1 7.0 0.000 0.000 217.559 217.559 init_scf_loop 2 5.0 0.000 0.000 196.664 196.664 hfx_ri_update_ks_Pmat_KS 567 11.6 0.007 0.007 186.666 186.666 dbt_tas_dbm 1482 16.0 0.010 0.010 178.747 178.747 dbm_multiply 1482 18.0 178.720 178.720 178.720 178.720 dbt_copy 2330 12.4 90.534 90.534 176.946 176.946 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.003 0.003 149.253 149.253 hfx_ri_forces_Pmat_3c 1 8.0 0.003 0.003 128.972 128.972 dbt_tas_mm_2 649 17.1 0.007 0.007 121.662 121.662 precalc_derivatives 1 8.0 0.010 0.010 70.356 70.356 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 52.774 52.774 dbt_tas_mm_3T 659 17.1 0.003 0.003 45.461 45.461 dbt_tas_reserve_blocks_index 7234 15.4 19.152 19.152 37.539 37.539 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.002 0.002 36.056 36.056 dbt_tas_copy 1474 13.1 26.929 26.929 34.762 34.762 dbt_tas_reshape 906 14.4 0.026 0.026 32.940 32.940 dbt_reserve_blocks_index 4836 14.6 3.846 3.846 31.827 31.827 dbt_reserve_blocks_index_array 4801 13.6 0.034 0.034 31.565 31.565 build_3c_derivatives 9 9.0 3.848 3.848 28.659 28.659 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.001 0.001 21.163 21.163 dbt_tas_reshape_buffer_obtain 906 15.4 13.567 13.567 19.697 19.697 dbt_split_copyback 87 12.2 13.967 13.967 15.780 15.780 ------------------------------------------------------------------------------- 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 0.012 117.509 117.510 qs_forces 1 2.0 0.000 0.000 117.231 117.232 rebuild_ks_matrix 7 6.6 0.000 0.000 115.998 115.999 qs_ks_build_kohn_sham_matrix 7 7.6 0.003 0.003 115.998 115.999 hfx_ks_matrix 7 8.6 0.001 0.001 113.957 113.978 dbt_total 4858 11.6 0.045 0.050 103.303 103.304 dbt_contract 1473 13.0 6.481 7.821 77.604 77.621 dbt_tas_total 2391 14.1 0.345 0.479 75.109 75.111 dbt_tas_multiply 1482 14.0 0.007 0.008 64.802 64.806 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 61.239 61.239 hfx_ri_update_ks 7 9.6 0.000 0.000 60.444 60.444 hfx_ri_update_ks_Pmat 7 10.6 3.264 4.490 60.442 60.442 qs_energies 1 3.0 0.000 0.000 55.976 55.976 scf_env_do_scf 1 4.0 0.000 0.000 55.741 55.741 qs_ks_update_qs_env 8 6.0 0.000 0.000 54.761 54.762 hfx_ri_update_forces 1 7.0 0.001 0.001 53.511 53.532 dbt_tas_dbm 1482 16.0 0.010 0.011 44.188 44.190 hfx_ri_forces_Pmat_3c 1 8.0 0.004 0.004 43.743 43.759 dbm_multiply 1482 18.0 30.336 35.400 30.336 35.400 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 32.656 32.656 mp_sync 17507 13.6 23.054 28.514 23.054 28.514 hfx_ri_update_ks_Pmat_KS 567 11.6 0.006 0.007 27.183 27.183 dbt_tas_mm_2 649 17.1 0.008 0.009 23.570 23.571 init_scf_loop 2 5.0 0.000 0.000 23.084 23.084 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.003 0.003 14.945 14.946 dbt_copy 2352 12.4 4.107 4.365 12.331 13.240 dbt_tas_mm_3T 659 17.1 0.004 0.004 8.093 8.858 dbt_tas_merge 649 14.1 3.734 5.040 6.914 8.534 precalc_derivatives 1 8.0 0.003 0.004 7.863 7.863 mp_waitall_2 6131 16.2 6.695 7.448 6.695 7.448 dbt_tas_mm_3N 163 16.5 0.001 0.001 6.875 6.964 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 6.347 6.347 dbt_tas_communicate_buffer 1908 16.3 0.116 0.121 5.195 5.779 dbt_tas_reserve_blocks_index 7352 15.5 0.693 0.833 4.701 5.722 dbm_reserve_blocks 8261 16.3 4.452 5.291 4.452 5.291 dbt_tas_reshape 999 14.5 0.022 0.023 4.827 5.278 dbt_tas_replicate 909 15.6 1.587 1.659 4.941 5.017 convert_to_new_pgrid 4446 16.0 0.092 0.183 4.143 4.663 dbt_reserve_blocks_index 5240 14.5 0.212 0.243 3.883 4.621 dbt_reserve_blocks_index_array 5205 13.5 0.025 0.027 3.876 4.612 dbm_copy 3041 16.9 3.883 4.418 3.883 4.418 mp_sum_l 38121 15.3 3.494 4.322 3.494 4.322 mp_max_i 3372 12.5 3.330 4.219 3.330 4.219 mp_alltoall_i 3170 15.2 3.558 4.051 3.558 4.051 build_3c_derivatives 9 9.0 0.619 0.669 3.766 3.771 dbm_add 1482 16.0 2.715 3.732 2.715 3.732 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.000 0.001 3.694 3.702 dbt_tas_merge_communicate_buff 649 15.1 0.014 0.017 2.560 3.089 dbt_communicate_buffer 1260 13.5 0.073 0.083 2.847 3.079 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.003 0.003 2.826 2.828 dbt_tas_reshape_alltoall 999 15.5 0.003 0.003 2.154 2.596 ------------------------------------------------------------------------------- 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=201.29800000000012, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_contract", label="dbt_contract", y=190.185, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=178.72, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_copy", label="dbt_copy", y=90.534, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=69.332, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_copy", label="dbt_tas_copy", y=26.929, 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 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="dbm_reserve_blocks", label="dbm_reserve_blocks", 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=39.120000000000005, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_contract", label="dbt_contract", y=6.481, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=30.336, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_copy", label="dbt_copy", y=4.107, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=3.264, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_copy", label="dbt_tas_copy", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=6.695, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=23.054, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=4.452, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.019 0.019 275.910 275.910 qs_energies 1 2.0 0.000 0.000 275.640 275.640 mp2_main 1 3.0 0.000 0.000 261.062 261.062 mp2_gpw_main 1 4.0 0.002 0.002 259.715 259.715 mp2_ri_gpw_compute_in 1 5.0 0.896 0.896 190.406 190.406 mp2_ri_gpw_compute_in_loop 1 6.0 0.032 0.032 157.804 157.804 mp2_eri_3c_integrate_gpw 2656 7.0 0.034 0.034 112.927 112.927 integrate_v_rspace 2666 8.0 3.231 3.231 91.638 91.638 grid_integrate_task_list 2666 9.0 84.859 84.859 84.859 84.859 mp2_ri_gpw_compute_en 1 5.0 0.058 0.058 69.253 69.253 mp2_ri_gpw_compute_en_RI_loop 1 6.0 33.123 33.123 65.564 65.564 calculate_wavefunction 5312 9.0 28.513 28.513 38.441 38.441 get_2c_integrals 1 6.0 0.000 0.000 31.639 31.639 compute_2c_integrals 1 7.0 0.014 0.014 29.594 29.594 compute_2c_integrals_loop_lm 1 8.0 0.028 0.028 29.549 29.549 mp2_eri_2c_integrate_gpw 1 9.0 5.130 5.130 29.521 29.521 dbcsr_multiply_generic 5322 8.0 0.337 0.337 29.100 29.100 ao_to_mo_and_store_B_mult_1 2656 7.0 0.025 0.025 29.055 29.055 mp2_ri_gpw_compute_en_expansio 2080 7.0 3.725 3.725 21.297 21.297 pw_transfer 63872 10.6 2.153 2.153 17.595 17.595 offload_gemm 2080 8.0 17.572 17.572 17.572 17.572 multiply_cannon 5322 9.0 3.293 3.293 16.431 16.431 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 10.331 10.331 15.604 15.604 fft_wrap_pw1pw2 53228 11.4 0.232 0.232 15.098 15.098 scf_env_do_scf 1 3.0 0.000 0.000 13.870 13.870 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 13.870 13.870 qs_scf_new_mos 10 5.0 0.000 0.000 11.780 11.780 multiply_cannon_loop 5322 10.0 0.188 0.188 11.573 11.573 mp2_ri_gpw_compute_en_ener 2080 7.0 11.134 11.134 11.134 11.134 fft3d_s 53229 13.4 10.001 10.001 10.073 10.073 fft_wrap_pw1pw2_20 21271 12.4 0.599 0.599 10.013 10.013 multiply_cannon_multrec 5322 11.0 9.947 9.947 10.009 10.009 make_m2s 10644 9.0 0.101 0.101 9.078 9.078 make_images 10644 10.0 3.134 3.134 8.475 8.475 eigensolver 11 5.8 0.001 0.001 8.084 8.084 cp_fm_diag_elpa 11 6.8 0.000 0.000 7.368 7.368 cp_fm_diag_elpa_base 11 7.8 7.116 7.116 7.368 7.368 potential_pw2rs 5322 10.0 0.271 0.271 6.725 6.725 copy_dbcsr_to_fm 2679 8.0 0.053 0.053 6.337 6.337 ------------------------------------------------------------------------------- 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 0.007 0.011 68.422 68.423 qs_energies 1 2.0 0.000 0.001 68.313 68.313 mp2_main 1 3.0 0.000 0.000 64.997 64.997 mp2_gpw_main 1 4.0 0.001 0.002 64.831 64.832 mp2_ri_gpw_compute_in 1 5.0 0.055 0.059 34.691 35.972 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 31.864 33.145 mp2_ri_gpw_compute_en 1 5.0 0.304 0.309 30.034 30.692 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.002 28.384 29.638 integrate_v_rspace 93 8.1 0.208 0.240 28.076 29.342 grid_integrate_task_list 93 9.1 27.469 28.715 27.469 28.715 mp2_ri_gpw_compute_en_RI_loop 1 6.0 3.057 3.497 25.644 25.944 mp2_ri_gpw_compute_en_comm 65 7.0 6.175 6.615 11.017 11.683 mp2_ri_gpw_compute_en_expansio 65 7.0 0.286 0.376 10.423 10.768 offload_gemm 65 8.0 10.137 10.489 10.137 10.489 mp_sendrecv_dm3 390 8.0 4.842 5.774 4.842 5.774 scf_env_do_scf 1 3.0 0.000 0.000 3.119 3.120 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 3.119 3.120 dbcsr_multiply_generic 176 8.0 0.013 0.015 2.827 3.082 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 2.794 3.046 get_2c_integrals 1 6.0 0.000 0.000 2.633 2.659 mp2_ri_create_group 1 6.0 0.000 0.000 2.494 2.506 replicate_iaK_2intgroup 1 7.0 1.721 1.901 2.318 2.506 compute_2c_integrals 1 7.0 0.006 0.009 2.242 2.255 compute_2c_integrals_loop_lm 1 8.0 0.001 0.004 1.990 2.107 mp2_eri_2c_integrate_gpw 1 9.0 0.430 0.488 1.989 2.105 mp2_ri_get_sizes 1 6.0 0.000 0.000 1.284 1.943 mp_min_d 1 7.0 1.284 1.942 1.284 1.942 calculate_wavefunction 166 9.0 0.875 0.930 1.635 1.717 make_m2s 352 9.0 0.005 0.005 1.507 1.699 make_images 352 10.0 0.067 0.069 1.493 1.685 pw_transfer 2120 10.5 0.082 0.088 1.543 1.586 qs_scf_new_mos 10 5.0 0.000 0.000 1.473 1.494 eigensolver 11 5.8 0.001 0.001 1.467 1.468 fft_wrap_pw1pw2 1768 11.4 0.009 0.010 1.429 1.467 ------------------------------------------------------------------------------- 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=100.709, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=84.859, 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=33.123, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=28.513, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="offload_gemm", label="offload_gemm", y=17.572, 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=11.134, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_comm", label="mp2_ri_gpw_compute_en_comm", 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=15.867000000000004, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=27.469, 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=3.057, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.875, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="offload_gemm", label="offload_gemm", y=10.137, 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="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=4.842, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp2_ri_gpw_compute_en_comm", label="mp2_ri_gpw_compute_en_comm", y=6.175, 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 0.102 0.102 208.765 208.765 qs_energies 1 2.0 0.000 0.000 206.753 206.753 scf_env_do_scf 1 3.0 0.000 0.000 195.456 195.456 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 195.456 195.456 qs_scf_new_mos 15 5.0 0.001 0.001 87.557 87.557 qs_ks_update_qs_env 15 5.0 0.000 0.000 75.003 75.003 rebuild_ks_matrix 15 6.0 0.000 0.000 74.605 74.605 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 74.605 74.605 eigensolver 15 6.0 0.002 0.002 73.166 73.166 cp_fm_diag_elpa 15 7.0 0.000 0.000 55.990 55.990 cp_fm_diag_elpa_base 15 8.0 50.653 50.653 55.989 55.989 qs_vxc_create 15 8.0 0.023 0.023 49.775 49.775 calculate_dispersion_nonloc 15 9.0 9.938 9.938 43.169 43.169 pw_transfer 1191 10.0 0.102 0.102 31.361 31.361 fft_wrap_pw1pw2 1086 11.0 0.015 0.015 31.027 31.027 qs_rho_update_rho 16 5.0 0.000 0.000 26.029 26.029 calculate_rho_elec 16 6.0 0.346 0.346 26.029 26.029 grid_collocate_task_list 16 7.0 24.090 24.090 24.090 24.090 sum_up_and_integrate 15 8.0 0.082 0.082 22.538 22.538 integrate_v_rspace 15 9.0 0.038 0.038 22.455 22.455 fft_wrap_pw1pw2_150 765 12.0 3.627 3.627 22.324 22.324 grid_integrate_task_list 15 10.0 21.712 21.712 21.712 21.712 pw_scatter_s 585 13.1 12.750 12.750 12.750 12.750 fft3d_s 1087 13.0 12.352 12.352 12.364 12.364 cp_fm_cholesky_restore 45 7.0 12.125 12.125 12.125 12.125 copy_dbcsr_to_fm 16 5.9 0.001 0.001 11.467 11.467 cp_fm_upper_to_full 30 8.0 10.386 10.386 10.386 10.386 dbcsr_complete_redistribute 46 8.3 3.688 3.688 10.057 10.057 fft_wrap_pw1pw2_200 197 12.3 0.750 0.750 8.427 8.427 vdW_energy 15 10.0 8.385 8.385 8.385 8.385 gspace_mixing 14 5.0 0.276 0.276 8.262 8.262 broyden_mixing 14 6.0 7.299 7.299 7.300 7.300 xc_vxc_pw_create 15 9.0 0.351 0.351 6.583 6.583 init_scf_run 1 3.0 0.000 0.000 5.337 5.337 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 5.092 5.092 dbcsr_finalize 159 9.9 0.024 0.024 4.323 4.323 ------------------------------------------------------------------------------- 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 0.017 0.020 92.918 92.919 qs_energies 1 2.0 0.000 0.001 92.507 92.508 scf_env_do_scf 1 3.0 0.000 0.000 87.240 87.241 scf_env_do_scf_inner_loop 15 4.0 0.002 0.003 87.240 87.241 qs_ks_update_qs_env 15 5.0 0.000 0.000 42.523 42.551 rebuild_ks_matrix 15 6.0 0.000 0.000 42.467 42.495 qs_ks_build_kohn_sham_matrix 15 7.0 0.005 0.005 42.467 42.495 qs_rho_update_rho 16 5.0 0.000 0.000 24.614 24.616 calculate_rho_elec 16 6.0 0.012 0.013 24.614 24.616 sum_up_and_integrate 15 8.0 0.017 0.021 23.429 23.473 integrate_v_rspace 15 9.0 0.001 0.001 23.412 23.458 grid_collocate_task_list 16 7.0 22.315 23.108 22.315 23.108 grid_integrate_task_list 15 10.0 21.445 22.033 21.445 22.033 qs_scf_new_mos 15 5.0 0.001 0.001 20.377 20.583 eigensolver 15 6.0 0.002 0.003 18.568 18.586 qs_vxc_create 15 8.0 0.001 0.001 18.411 18.428 calculate_dispersion_nonloc 15 9.0 1.478 1.582 14.858 14.875 pw_transfer 1191 10.0 0.145 0.151 14.611 14.772 fft_wrap_pw1pw2 1086 11.0 0.023 0.026 14.287 14.451 cp_fm_diag_elpa 15 7.0 0.000 0.000 13.502 13.513 cp_fm_diag_elpa_base 15 8.0 13.206 13.256 13.495 13.499 fft3d_ps 1086 13.0 6.177 6.416 10.898 11.189 fft_wrap_pw1pw2_150 765 12.0 0.772 0.835 9.587 9.634 cp_fm_cholesky_restore 45 7.0 4.792 4.858 4.792 4.858 fft_wrap_pw1pw2_200 197 12.3 0.442 0.473 4.506 4.632 xc_vxc_pw_create 15 9.0 0.038 0.052 3.552 3.563 mp_alltoall_z22v 1086 15.0 2.996 3.436 2.996 3.436 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.237 3.237 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.793 3.048 x_to_yz 585 14.1 1.091 1.124 2.654 2.846 rs_pw_transfer 158 9.4 0.003 0.003 2.114 2.639 xc_pw_derive 90 11.0 0.003 0.003 2.468 2.560 density_rs2pw 16 7.0 0.002 0.002 2.085 2.400 vdW_energy 15 10.0 2.245 2.334 2.245 2.334 yz_to_x 501 13.9 0.596 0.679 2.029 2.310 build_core_ppnl 1 5.0 1.871 2.065 1.871 2.065 xc_rho_set_and_dset_create 15 10.0 0.046 0.059 1.816 1.861 ------------------------------------------------------------------------------- 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=75.08299999999997, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=50.653, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=24.09, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=21.712, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=12.75, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=12.352, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=12.125, 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=24.983000000000004, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=13.206, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.315, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=21.445, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="pw_scatter_s", label="pw_scatter_s", y=0.0, 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=4.792, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.177, 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 0.095 0.095 343.516 343.516 qs_energies 1 2.0 0.000 0.000 343.342 343.342 ls_scf 1 3.0 0.000 0.000 341.412 341.412 ls_scf_main 1 4.0 0.002 0.002 325.231 325.231 density_matrix_trs4 11 5.0 0.012 0.012 185.966 185.966 ls_scf_dm_to_ks 11 5.0 0.000 0.000 131.908 131.908 matrix_ls_to_qs 11 6.0 0.000 0.000 127.381 127.381 dbcsr_multiply_generic 185 6.1 0.645 0.645 117.835 117.835 multiply_cannon 185 7.1 3.346 3.346 80.442 80.442 dbcsr_copy_into_existing 11 7.0 74.486 74.486 74.486 74.486 dbcsr_complete_redistribute 23 7.5 42.220 42.220 58.203 58.203 multiply_cannon_loop 185 8.1 0.456 0.456 57.816 57.816 multiply_cannon_multrec 185 9.1 55.259 55.259 55.368 55.368 matrix_decluster 11 7.0 0.000 0.000 52.893 52.893 arnoldi_extremal 12 6.1 0.000 0.000 48.421 48.421 arnoldi_normal_ev 12 7.1 0.029 0.029 48.420 48.420 build_subspace 23 8.1 0.141 0.141 47.716 47.716 dbcsr_matrix_vector_mult 652 9.0 0.267 0.267 36.826 36.826 dbcsr_matrix_vector_mult_local 652 10.0 35.103 35.103 35.112 35.112 make_m2s 370 7.1 0.032 0.032 30.630 30.630 make_images 370 8.1 7.807 7.807 28.008 28.008 dbcsr_finalize 646 7.5 0.237 0.237 21.845 21.845 dbcsr_merge_all 597 8.5 3.691 3.691 19.733 19.733 setup_rec_index_2d 370 8.1 19.019 19.019 19.019 19.019 dbcsr_sort_indices 1103 9.9 15.483 15.483 15.483 15.483 ls_scf_init_scf 1 4.0 0.000 0.000 14.868 14.868 ls_scf_init_matrix_S 1 5.0 0.000 0.000 14.402 14.402 tree_to_linear_d 110 9.4 13.679 13.679 13.679 13.679 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 13.431 13.431 quick_finalize 395 10.0 0.561 0.561 13.281 13.281 dbcsr_special_finalize 370 9.1 0.003 0.003 12.251 12.251 dbcsr_dot_sd 144 6.3 9.513 9.513 9.514 9.514 dbcsr_frobenius_norm 142 6.1 8.166 8.166 8.169 8.169 make_images_data 370 9.1 0.011 0.011 7.752 7.752 matrix_qs_to_ls 12 5.1 0.000 0.000 7.657 7.657 matrix_cluster 12 6.1 0.000 0.000 7.657 7.657 dbcsr_new_transposed 2 7.0 0.141 0.141 7.465 7.465 dbcsr_redistribute 2 8.0 7.216 7.216 7.286 7.286 ------------------------------------------------------------------------------- From /workspace/artifacts/bench_dftb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.009 103.625 103.626 qs_energies 1 2.0 0.000 0.000 103.524 103.525 ls_scf 1 3.0 0.000 0.000 103.444 103.445 ls_scf_main 1 4.0 0.001 0.003 99.343 99.343 density_matrix_trs4 11 5.0 0.009 0.014 95.273 95.352 dbcsr_multiply_generic 185 6.1 0.086 0.108 89.560 89.837 multiply_cannon 185 7.1 0.046 0.050 74.920 76.095 multiply_cannon_loop 185 8.1 0.255 0.269 70.770 72.815 multiply_cannon_multrec 1480 9.1 45.625 47.964 46.159 48.503 mp_waitall_1 11936 10.3 22.197 25.535 22.197 25.535 multiply_cannon_metrocomm3 1480 9.1 0.021 0.023 13.006 17.475 make_m2s 370 7.1 0.037 0.041 10.234 10.332 make_images 370 8.1 0.720 0.750 10.105 10.207 multiply_cannon_metrocomm1 1480 9.1 0.012 0.014 5.347 7.904 calculate_norms 2960 9.1 5.911 6.145 5.911 6.145 make_images_data 370 9.1 0.014 0.015 4.293 4.584 arnoldi_extremal 12 6.1 0.000 0.001 4.181 4.192 arnoldi_normal_ev 12 7.1 0.002 0.008 4.180 4.192 build_subspace 23 8.1 0.044 0.058 4.041 4.045 hybrid_alltoall_any 393 9.9 0.364 1.866 3.590 3.900 mp_sum_l 1039 5.9 2.967 3.880 2.967 3.880 ls_scf_dm_to_ks 11 5.0 0.000 0.000 3.510 3.596 dbcsr_matrix_vector_mult 652 9.0 0.020 0.083 3.348 3.426 dbcsr_complete_redistribute 23 7.5 1.966 2.057 3.162 3.233 matrix_ls_to_qs 11 6.0 0.000 0.000 3.107 3.179 ls_scf_init_scf 1 4.0 0.000 0.000 3.121 3.122 ls_scf_init_matrix_S 1 5.0 0.000 0.000 3.083 3.090 make_images_pack 370 9.1 2.710 2.998 2.715 3.005 matrix_decluster 11 7.0 0.000 0.000 2.840 2.915 dbcsr_multiply_generic_mpsum_f 137 7.1 0.001 0.001 2.019 2.837 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 2.827 2.828 dbcsr_matrix_vector_mult_local 652 10.0 2.610 2.752 2.614 2.758 buffer_matrices_ensure_size 370 8.1 2.483 2.582 2.483 2.582 dbcsr_add_d 280 6.0 0.002 0.002 2.265 2.343 dbcsr_add_anytype 280 7.0 1.232 1.311 2.263 2.342 dbcsr_finalize 646 7.5 0.015 0.016 2.103 2.205 ------------------------------------------------------------------------------- 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=117.429, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=74.486, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=55.259, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=42.22, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=35.103, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=19.019, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", 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=19.638999999999996, 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="multiply_cannon_multrec", label="multiply_cannon_multrec", y=45.625, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=1.966, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=2.61, 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="make_images_pack", label="make_images_pack", y=2.71, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.967, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=22.197, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.911, 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 0.006 0.006 107.872 107.872 lib_test 1 2.0 0.000 0.000 107.863 107.863 dbcsr_run_tests 3 3.0 0.003 0.003 107.863 107.863 test_multiplies_multiproc 3 4.0 0.001 0.001 87.546 87.546 dbcsr_redistribute 9 5.0 58.505 58.505 62.028 62.028 dbcsr_multiply_generic 9 5.0 0.001 0.001 23.698 23.698 dbcsr_make_random_matrix 9 4.0 14.757 14.757 20.215 20.215 multiply_cannon 9 6.0 0.002 0.002 17.056 17.056 multiply_cannon_loop 9 7.0 0.003 0.003 16.532 16.532 multiply_cannon_multrec 9 8.0 16.528 16.528 16.529 16.529 dbcsr_finalize 27 5.7 0.005 0.005 9.222 9.222 dbcsr_merge_all 18 6.5 3.164 3.164 8.440 8.440 tree_to_linear_d 9 7.0 3.323 3.323 3.323 3.323 mp_alltoall_d11v 27 6.0 3.200 3.200 3.200 3.200 dbcsr_data_release 975 7.6 2.539 2.539 2.539 2.539 make_m2s 18 6.0 0.001 0.001 2.266 2.266 make_images 18 7.0 0.715 0.715 2.189 2.189 ------------------------------------------------------------------------------- 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 0.005 27.899 27.900 lib_test 1 2.0 0.000 0.001 27.867 27.890 dbcsr_run_tests 3 3.0 0.000 0.001 27.866 27.888 test_multiplies_multiproc 3 4.0 0.001 0.002 26.672 26.783 dbcsr_multiply_generic 9 5.0 0.001 0.002 24.611 24.709 multiply_cannon 9 6.0 0.003 0.003 22.106 22.529 multiply_cannon_loop 9 7.0 0.004 0.004 21.623 22.012 multiply_cannon_multrec 72 8.0 18.099 18.997 18.100 18.999 mp_waitall_1 576 9.2 3.980 4.699 3.980 4.699 multiply_cannon_metrocomm1 72 8.0 0.002 0.002 3.121 4.002 mp_sum_l 310 2.7 0.574 1.337 0.574 1.337 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.569 1.332 dbcsr_make_random_matrix 9 4.0 0.909 0.936 1.147 1.195 make_m2s 18 6.0 0.001 0.001 1.036 1.105 make_images 18 7.0 0.027 0.028 1.033 1.102 dbcsr_finalize 27 5.7 0.001 0.001 0.932 1.058 dbcsr_merge_all 18 6.5 0.156 0.186 0.830 0.959 dbcsr_data_release 444 7.6 0.723 0.841 0.723 0.841 dbcsr_redistribute 9 5.0 0.425 0.481 0.758 0.818 multiply_cannon_metrocomm3 72 8.0 0.000 0.001 0.388 0.809 dbcsr_destroy 111 5.9 0.006 0.060 0.629 0.734 make_images_data 18 8.0 0.001 0.001 0.523 0.630 ------------------------------------------------------------------------------- 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=9.019999999999996, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=58.505, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=16.528, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=14.757, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="tree_to_linear_d", label="tree_to_linear_d", y=3.323, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=3.2, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.539, 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=3.189, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.425, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=18.099, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.909, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="tree_to_linear_d", label="tree_to_linear_d", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.723, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.98, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.574, 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 0.049 0.049 147.030 147.030 qs_mol_dyn_low 1 2.0 0.005 0.005 144.916 144.916 velocity_verlet 5 3.0 0.004 0.004 117.078 117.078 qmmm_el_coupling 6 3.8 0.000 0.000 73.106 73.106 qmmm_elec_with_gaussian 6 4.8 0.194 0.194 73.099 73.099 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 72.071 72.071 qmmm_elec_gaussian_low_G 6 6.8 70.567 70.567 70.567 70.567 qs_forces 6 3.8 0.001 0.001 58.219 58.219 qs_energies 6 4.8 0.000 0.000 51.842 51.842 scf_env_do_scf 6 5.8 0.001 0.001 47.824 47.824 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 40.286 40.286 rebuild_ks_matrix 45 8.4 0.000 0.000 39.217 39.217 qs_ks_build_kohn_sham_matrix 45 9.4 0.008 0.008 39.217 39.217 qs_ks_update_qs_env 45 7.8 0.000 0.000 33.632 33.632 pw_transfer 966 12.3 0.076 0.076 24.903 24.903 fft_wrap_pw1pw2 801 13.6 0.009 0.009 24.520 24.520 fft_wrap_pw1pw2_150 507 15.2 2.556 2.556 23.959 23.959 qs_vxc_create 45 10.4 0.001 0.001 20.356 20.356 xc_vxc_pw_create 45 11.4 1.027 1.027 20.355 20.355 xc_pw_derive 270 13.4 0.004 0.004 13.669 13.669 xc_rho_set_and_dset_create 45 12.4 1.296 1.296 11.480 11.480 qs_rho_update_rho 45 7.9 0.000 0.000 10.971 10.971 calculate_rho_elec 45 8.9 0.907 0.907 10.971 10.971 pw_scatter_s 429 15.8 10.942 10.942 10.942 10.942 fft3d_s 802 15.6 9.494 9.494 9.505 9.505 qmmm_forces 6 3.8 0.002 0.002 8.166 8.166 pw_integral_ab 2539 7.4 7.795 7.795 7.795 7.795 xc_pw_divergence 45 12.4 0.002 0.002 7.734 7.734 qmmm_forces_with_gaussian 6 4.8 0.173 0.173 7.631 7.631 init_scf_loop 6 6.8 0.000 0.000 7.532 7.532 qs_ks_ddapc 45 10.4 0.001 0.001 6.916 6.916 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 6.489 6.489 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 5.598 5.598 pw_poisson_solve 51 9.9 2.411 2.411 5.543 5.543 qmmm_forces_gaussian_low_G 6 6.8 5.365 5.365 5.365 5.365 grid_collocate_task_list 45 9.9 5.099 5.099 5.099 5.099 density_rs2pw 45 9.9 0.003 0.003 4.964 4.964 fist_calc_energy_force 6 3.8 0.002 0.002 4.598 4.598 sum_up_and_integrate 45 10.4 0.246 0.246 4.528 4.528 integrate_v_rspace 45 11.4 0.013 0.013 4.282 4.282 cp_ddapc_apply_CD 45 11.4 0.007 0.007 4.269 4.269 force_nonbond 6 4.8 3.300 3.300 3.300 3.300 ------------------------------------------------------------------------------- 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 0.036 0.039 95.292 95.293 qs_mol_dyn_low 1 2.0 0.005 0.008 93.581 93.677 qs_forces 6 3.8 0.001 0.001 70.314 70.315 qs_energies 6 4.8 0.001 0.001 67.065 67.066 scf_env_do_scf 6 5.8 0.000 0.001 65.391 65.391 scf_env_do_scf_inner_loop 113 6.2 0.003 0.010 62.720 62.721 rebuild_ks_matrix 119 8.1 0.000 0.001 46.891 46.910 qs_ks_build_kohn_sham_matrix 119 9.1 0.024 0.026 46.890 46.909 qs_ks_update_qs_env 119 7.3 0.001 0.001 44.107 44.125 velocity_verlet 5 3.0 0.003 0.003 38.724 38.728 pw_transfer 2446 12.3 0.303 0.323 30.284 30.601 fft_wrap_pw1pw2 2059 13.4 0.038 0.040 29.397 29.716 fft_wrap_pw1pw2_150 1321 14.9 2.714 2.923 28.479 28.716 qs_vxc_create 119 10.1 0.004 0.005 24.466 24.472 xc_vxc_pw_create 119 11.1 0.278 0.376 24.462 24.467 fft3d_ps 2059 15.4 13.069 14.288 22.253 22.863 xc_pw_derive 714 13.1 0.018 0.022 18.364 18.955 qs_rho_update_rho 119 7.3 0.001 0.001 17.998 17.999 calculate_rho_elec 119 8.3 0.087 0.097 17.997 17.998 sum_up_and_integrate 119 10.1 0.100 0.109 16.308 16.346 integrate_v_rspace 119 11.1 0.005 0.006 16.208 16.250 rs_pw_transfer 988 11.5 0.017 0.019 12.817 13.175 qmmm_forces 6 3.8 0.003 0.003 12.896 12.897 xc_pw_divergence 119 12.1 0.010 0.012 12.363 12.832 qmmm_forces_with_gaussian 6 4.8 0.447 0.539 12.505 12.646 xc_rho_set_and_dset_create 119 12.1 0.657 0.813 11.341 11.951 density_rs2pw 119 9.3 0.012 0.014 11.194 11.646 potential_pw2rs 119 12.1 0.011 0.012 10.093 10.107 qmmm_el_coupling 6 3.8 0.000 0.000 9.167 9.222 qmmm_elec_with_gaussian 6 4.8 0.418 0.550 9.164 9.218 mp_alltoall_z22v 2059 17.4 5.768 7.834 5.768 7.834 grid_collocate_task_list 119 9.3 6.456 6.877 6.456 6.877 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 5.881 5.993 grid_integrate_task_list 119 12.1 5.656 5.903 5.656 5.903 rs_pw_transfer_PW2RS_150 125 13.9 2.844 2.913 5.575 5.616 yz_to_x 964 16.0 1.300 1.488 4.139 5.480 x_to_yz 1095 16.8 2.061 2.300 4.989 5.353 rs_pw_transfer_RS2PW_150 125 11.2 2.214 2.344 4.594 4.938 qmmm_forces_gaussian_low_G 6 6.8 4.801 4.912 4.801 4.912 pw_restrict_s3 18 5.8 2.538 2.577 4.804 4.858 mp_waitany 4028 12.8 4.054 4.573 4.054 4.573 qs_scf_new_mos 113 7.2 0.001 0.001 3.903 3.912 qs_scf_loop_do_ot 113 8.2 0.001 0.001 3.903 3.912 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 3.836 3.887 pw_prolongate_s3 18 6.8 2.025 2.068 3.836 3.887 ot_scf_mini 113 9.2 0.002 0.002 3.734 3.742 dbcsr_multiply_generic 2588 12.3 0.101 0.117 3.486 3.540 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.417 3.480 qs_ks_ddapc 119 10.1 0.003 0.004 3.164 3.325 pw_integral_ab 2761 7.7 2.413 2.459 2.837 3.010 mp_sum_dm3 33 5.7 2.640 2.836 2.640 2.836 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 2.795 2.796 init_scf_loop 6 6.8 0.000 0.000 2.667 2.667 pw_gather_p 964 15.0 2.201 2.649 2.201 2.649 qmmm_elec_gaussian_low_G 6 6.8 2.461 2.517 2.461 2.517 mp_waitall_1 188862 16.2 2.289 2.446 2.289 2.446 ot_mini 113 10.2 0.001 0.001 2.355 2.366 pw_scatter_p 1095 15.8 2.122 2.241 2.122 2.241 pw_derive 732 13.9 1.870 2.137 1.870 2.137 ------------------------------------------------------------------------------- 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=37.768000000000015, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=70.567, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=10.942, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=9.494, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=7.795, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=5.365, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=5.099, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=54.668, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.461, 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="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=2.413, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=4.801, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=6.456, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=13.069, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=5.768, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=5.656, yerr=0.0 Summary: Performance test took 64 minutes. Status: OK Removing intermediate container 3cd57b73abcc ---> 22f7715cd24f Step 41/41 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in f10d4523d401 Removing intermediate container f10d4523d401 ---> 1e25bd5a47e4 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 1e25bd5a47e4 Successfully tagged gcr.io/cp2k-org-project/img_cp2k-perf-openmp-arch-b51:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2022-03-16 12:23:37+00:00