StartDate: 2023-01-01 19:05:55+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: bc464008d20ef4ef3c97dde5a15ef58d48cf97dc CommitTime: 2023-01-01 14:08:47 +0100 CommitAuthor: Ole Schütt CommitSubject: Manual: Add 2023.1 release Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=bc464008d20ef4ef3c97dde5a15ef58d48cf97dc Sending build context to Docker daemon 366.5MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 6e3729cf69e0: Already exists Digest: sha256:27cb6e6ccef575a4698b66f5de06c7ecd61589132d5a91d098f7f3f9285415a9 Status: Downloaded newer image for ubuntu:22.04 ---> 6b7dfa7e8fdb Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> e98199835f6f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> ccd07bf8588a Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 0aa7ad9d2809 Step 5/42 : RUN mkdir scripts ---> Using cache ---> e9459f85bb88 Step 6/42 : COPY ./tools/toolchain/scripts/VERSION ./tools/toolchain/scripts/parse_if.py ./tools/toolchain/scripts/tool_kit.sh ./tools/toolchain/scripts/common_vars.sh ./tools/toolchain/scripts/signal_trap.sh ./tools/toolchain/scripts/get_openblas_arch.sh ./scripts/ ---> Using cache ---> 47c0caf3dab5 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 19088ac45e1f Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 92805a05cd8b Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> d51b4a6b3b7e Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> a18c614ddaa6 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 903dd37eb616 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> edb2bb8e5397 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 983b8bd5f663 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> b11ff944488d Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 2eee06160ddd Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 29b956f4a893 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 4b0375880c86 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 7747b12e843c Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 69369a62bc3e Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 109ed49835ab Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> a66a98b073fa Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 8aa98cc26e67 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 903c6ab45084 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> d7b7f3bd5079 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 6d0e2976a856 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> b1bcffa148c3 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> c6363caf72af Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 75d9416d8ec9 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 71ee22c39b1f Step 30/42 : COPY ./Makefile . ---> Using cache ---> 0cb1f5208e76 Step 31/42 : COPY ./src ./src ---> Using cache ---> 007ab5566d54 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 2ddff46a51fe Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> b82d12ca9c0c Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/ && echo 'Compiling cp2k...' && source /opt/cp2k-toolchain/install/setup && ( make -j ARCH=local VERSION=psmp &> /dev/null || true ) && ( [ ! -f ./exe/local/cp2k.psmp ] || ldd ./exe/local/cp2k.psmp | grep -q libmpi )" ---> Running in 2b8372f57b57 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 2b8372f57b57 ---> 0425e62c6f58 Step 35/42 : COPY ./data ./data ---> f7d9e63c409d Step 36/42 : COPY ./tests ./tests ---> 3c6234a19c17 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 48771fadf494 Step 38/42 : COPY ./benchmarks ./benchmarks ---> a1e6926a1833 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 0b2c4a32fddf Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 741c475728fb ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 69 input files and 0 errors. ========== Running Performance Test ========== Running H2O-64.inp with 1 threads and 32 ranks... done. Running H2O-64.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.027 0.027 86.475 86.475 qs_mol_dyn_low 1 2.0 0.003 0.003 85.866 85.866 qs_forces 11 3.9 0.001 0.001 85.827 85.827 qs_energies 11 4.9 0.001 0.001 79.973 79.973 scf_env_do_scf 11 5.9 0.001 0.001 69.250 69.250 velocity_verlet 10 3.0 0.002 0.002 55.889 55.889 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 53.027 53.027 rebuild_ks_matrix 119 8.3 0.001 0.001 19.940 19.940 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 19.939 19.939 dbcsr_multiply_generic 2286 12.5 0.159 0.159 19.518 19.518 qs_scf_new_mos 108 7.5 0.001 0.001 19.291 19.291 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.290 19.290 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.098 19.098 calculate_rho_elec 119 8.7 0.949 0.949 19.097 19.097 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.340 18.340 ot_scf_mini 108 9.5 0.002 0.002 17.946 17.946 init_scf_loop 11 6.9 0.000 0.000 16.093 16.093 grid_collocate_task_list 119 9.7 14.706 14.706 14.706 14.706 prepare_preconditioner 11 7.9 0.000 0.000 13.675 13.675 make_preconditioner 11 8.9 0.000 0.000 13.675 13.675 sum_up_and_integrate 119 10.3 0.520 0.520 12.929 12.929 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.591 12.591 integrate_v_rspace 119 11.3 0.097 0.097 12.408 12.408 ot_mini 108 10.5 0.001 0.001 11.759 11.759 make_m2s 4572 13.5 0.045 0.045 10.816 10.816 grid_integrate_task_list 119 12.3 10.454 10.454 10.454 10.454 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.328 6.328 qs_ot_get_derivative 108 11.5 0.001 0.001 6.187 6.187 pw_transfer 1439 11.6 0.062 0.062 5.971 5.971 dbcsr_make_dense_low 5837 15.5 0.069 0.069 5.818 5.818 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.766 5.766 make_dense_data 5837 16.5 5.194 5.194 5.735 5.735 ot_diis_step 108 11.5 0.004 0.004 5.569 5.569 make_images 4572 14.5 2.137 2.137 5.414 5.414 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.099 5.099 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.009 5.009 apply_single 119 13.6 0.000 0.000 5.009 5.009 fft_wrap_pw1pw2_140 487 13.2 0.474 0.474 4.952 4.952 multiply_cannon 2286 13.5 0.174 0.174 4.788 4.788 cp_fm_cholesky_decompose 22 10.9 4.410 4.410 4.410 4.410 multiply_cannon_loop 2286 14.5 0.061 0.061 4.332 4.332 multiply_cannon_multrec 2286 15.5 4.219 4.219 4.270 4.270 cp_fm_cholesky_invert 11 10.9 4.087 4.087 4.087 4.087 init_scf_run 11 5.9 0.002 0.002 3.817 3.817 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.815 3.815 dbcsr_copy 2102 12.0 0.227 0.227 3.698 3.698 dbcsr_complete_redistribute 329 12.2 1.907 1.907 3.619 3.619 density_rs2pw 119 9.7 0.005 0.005 3.442 3.442 dbcsr_copy_into_existing 22 7.9 3.432 3.432 3.433 3.433 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.330 3.330 wfi_extrapolate 11 7.9 0.001 0.001 3.305 3.305 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.248 3.248 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.988 2.988 qs_create_task_list 11 7.9 0.000 0.000 2.886 2.886 generate_qs_task_list 11 8.9 1.974 1.974 2.886 2.886 fft3d_s 1202 14.6 2.811 2.811 2.816 2.816 qs_ot_get_p 119 10.4 0.001 0.001 2.780 2.780 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.680 2.680 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.521 2.521 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.290 2.290 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.084 2.084 dbcsr_data_release 279534 16.0 2.074 2.074 2.074 2.074 pw_poisson_solve 119 10.3 0.336 0.336 2.012 2.012 potential_pw2rs 119 12.3 0.045 0.045 1.857 1.857 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.850 1.850 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.779 1.779 cp_fm_upper_to_full 72 14.2 1.747 1.747 1.747 1.747 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.020 43.342 43.352 qs_mol_dyn_low 1 2.0 0.003 0.004 43.233 43.238 qs_forces 11 3.9 0.001 0.001 43.192 43.193 qs_energies 11 4.9 0.001 0.001 40.343 40.345 scf_env_do_scf 11 5.9 0.000 0.002 36.956 36.957 scf_env_do_scf_inner_loop 108 6.5 0.003 0.021 34.055 34.055 velocity_verlet 10 3.0 0.002 0.003 25.817 25.818 rebuild_ks_matrix 119 8.3 0.000 0.001 15.713 15.792 qs_ks_build_kohn_sham_matrix 119 9.3 0.014 0.015 15.712 15.792 qs_ks_update_qs_env 119 7.6 0.001 0.001 13.969 14.036 qs_rho_update_rho_low 119 7.7 0.001 0.008 12.839 12.847 calculate_rho_elec 119 8.7 0.029 0.031 12.838 12.847 dbcsr_multiply_generic 2286 12.5 0.070 0.075 12.538 12.699 sum_up_and_integrate 119 10.3 0.029 0.035 11.703 11.723 integrate_v_rspace 119 11.3 0.004 0.005 11.673 11.695 qs_scf_new_mos 108 7.5 0.001 0.001 9.834 9.889 qs_scf_loop_do_ot 108 8.5 0.001 0.001 9.833 9.888 multiply_cannon 2286 13.5 0.154 0.164 9.177 9.593 grid_collocate_task_list 119 9.7 9.031 9.337 9.031 9.337 ot_scf_mini 108 9.5 0.002 0.002 9.208 9.261 multiply_cannon_loop 2286 14.5 0.087 0.099 8.645 8.971 grid_integrate_task_list 119 12.3 8.042 8.249 8.042 8.249 mp_waitall_1 158411 16.6 7.004 7.521 7.004 7.521 ot_mini 108 10.5 0.001 0.001 5.354 5.411 multiply_cannon_metrocomm3 18288 15.5 0.035 0.038 4.867 5.344 rs_pw_transfer 974 11.9 0.010 0.013 4.092 4.425 density_rs2pw 119 9.7 0.005 0.006 3.454 3.815 pw_transfer 1439 11.6 0.101 0.112 3.206 3.247 multiply_cannon_multrec 18288 15.5 2.982 3.175 2.991 3.186 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.037 3.068 potential_pw2rs 119 12.3 0.007 0.008 3.000 3.021 init_scf_loop 11 6.9 0.000 0.000 2.888 2.888 qs_ot_get_derivative 108 11.5 0.001 0.001 2.746 2.800 fft_wrap_pw1pw2_140 487 13.2 0.251 0.292 2.577 2.642 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.508 2.600 apply_single 119 13.6 0.000 0.000 2.508 2.600 ot_diis_step 108 11.5 0.003 0.004 2.587 2.587 init_scf_run 11 5.9 0.000 0.005 2.396 2.396 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.395 2.396 make_m2s 4572 13.5 0.045 0.050 2.324 2.373 fft3d_ps 1201 14.6 1.154 1.241 2.181 2.257 wfi_extrapolate 11 7.9 0.001 0.001 2.169 2.169 make_images 4572 14.5 0.115 0.119 2.008 2.057 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.879 1.892 mp_waitany 9880 13.7 1.393 1.737 1.393 1.737 rs_pw_transfer_RS2PW_140 130 11.5 0.182 0.207 1.053 1.395 make_images_data 4572 15.5 0.034 0.042 1.145 1.292 qs_ot_get_p 119 10.4 0.001 0.001 1.195 1.250 rs_pw_transfer_PW2RS_140 130 13.9 0.340 0.409 1.165 1.199 prepare_preconditioner 11 7.9 0.000 0.000 1.174 1.196 make_preconditioner 11 8.9 0.000 0.000 1.174 1.196 hybrid_alltoall_any 4725 16.4 0.061 0.227 1.003 1.109 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.070 1.090 mp_alltoall_d11v 2130 13.8 0.814 0.993 0.814 0.993 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.857 0.944 mp_alltoall_z22v 1201 16.6 0.788 0.936 0.788 0.936 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.912 0.914 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.875 0.912 multiply_cannon_metrocomm1 18288 15.5 0.017 0.019 0.511 0.911 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.868 0.895 ------------------------------------------------------------------------------- Plot: name="H2O-64_timings_32omp", title="Timings of H2O-64 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32omp", name="rest", label="rest", y=47.492, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.706, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.454, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.194, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.41, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.219, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=14.89, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.031, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.042, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.982, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.393, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.004, 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 0.032 0.032 110.189 110.189 qs_mol_dyn_low 1 2.0 0.003 0.003 109.533 109.533 qs_forces 11 3.9 0.001 0.001 109.493 109.493 qs_energies 11 4.9 0.001 0.001 101.990 101.990 scf_env_do_scf 11 5.9 0.001 0.001 89.284 89.284 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 71.271 71.271 velocity_verlet 10 3.0 0.002 0.002 70.633 70.633 rebuild_ks_matrix 107 8.3 0.001 0.001 33.097 33.097 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.096 33.096 qs_rho_update_rho_low 107 7.7 0.000 0.000 31.147 31.147 calculate_rho_elec 107 8.7 0.853 0.853 31.147 31.147 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.782 29.782 grid_collocate_task_list 107 9.7 27.077 27.077 27.077 27.077 sum_up_and_integrate 107 10.3 0.453 0.453 26.560 26.560 integrate_v_rspace 107 11.3 0.081 0.081 26.107 26.107 grid_integrate_task_list 107 12.3 24.356 24.356 24.356 24.356 init_scf_loop 11 6.9 0.000 0.000 17.866 17.866 dbcsr_multiply_generic 1966 12.4 0.148 0.148 17.706 17.706 qs_scf_new_mos 96 7.5 0.001 0.001 17.043 17.043 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.043 17.043 ot_scf_mini 96 9.5 0.002 0.002 15.868 15.868 prepare_preconditioner 11 7.9 0.000 0.000 13.807 13.807 make_preconditioner 11 8.9 0.000 0.000 13.807 13.807 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.639 12.639 ot_mini 96 10.5 0.001 0.001 10.326 10.326 make_m2s 3932 13.4 0.039 0.039 9.870 9.870 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.597 6.597 pw_transfer 1295 11.6 0.056 0.056 5.555 5.555 init_scf_run 11 5.9 0.002 0.002 5.462 5.462 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.460 5.460 qs_ot_get_derivative 96 11.5 0.001 0.001 5.391 5.391 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.344 5.344 dbcsr_make_dense_low 4961 15.5 0.060 0.060 5.252 5.252 make_dense_data 4961 16.5 4.571 4.571 5.179 5.179 make_images 3932 14.4 1.925 1.925 4.964 4.964 ot_diis_step 96 11.5 0.003 0.003 4.932 4.932 wfi_extrapolate 11 7.9 0.001 0.001 4.856 4.856 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.648 4.648 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.633 4.633 apply_single 107 13.6 0.000 0.000 4.633 4.633 fft_wrap_pw1pw2_140 439 13.2 0.421 0.421 4.614 4.614 multiply_cannon 1966 13.4 0.150 0.150 4.433 4.433 cp_fm_cholesky_decompose 22 10.9 4.375 4.375 4.375 4.375 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.165 4.165 cp_fm_cholesky_invert 11 10.9 4.048 4.048 4.048 4.048 multiply_cannon_loop 1966 14.4 0.036 0.036 4.035 4.035 multiply_cannon_multrec 1966 15.4 3.954 3.954 3.998 3.998 dbcsr_complete_redistribute 317 12.2 1.895 1.895 3.824 3.824 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.724 3.724 dbcsr_copy 1855 11.9 0.198 0.198 3.518 3.518 qs_create_task_list 11 7.9 0.000 0.000 3.350 3.350 generate_qs_task_list 11 8.9 2.409 2.409 3.349 3.349 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.336 3.336 dbcsr_copy_into_existing 22 7.9 3.291 3.291 3.291 3.291 density_rs2pw 107 9.7 0.004 0.004 3.217 3.217 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.099 3.099 fft3d_s 1082 14.6 2.644 2.644 2.648 2.648 qs_ot_get_p 107 10.4 0.001 0.001 2.469 2.469 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.462 2.462 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.351 2.351 ------------------------------------------------------------------------------- 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 0.020 69.010 69.020 qs_mol_dyn_low 1 2.0 0.003 0.003 68.911 68.916 qs_forces 11 3.9 0.001 0.001 68.871 68.872 qs_energies 11 4.9 0.001 0.001 64.214 64.215 scf_env_do_scf 11 5.9 0.000 0.002 59.444 59.444 scf_env_do_scf_inner_loop 96 6.5 0.002 0.016 54.963 54.964 velocity_verlet 10 3.0 0.002 0.003 41.011 41.012 rebuild_ks_matrix 107 8.3 0.000 0.001 29.958 30.052 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.016 29.958 30.051 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.378 26.460 sum_up_and_integrate 107 10.3 0.031 0.042 26.323 26.340 integrate_v_rspace 107 11.3 0.004 0.005 26.291 26.315 qs_rho_update_rho_low 107 7.7 0.000 0.001 25.199 25.207 calculate_rho_elec 107 8.7 0.026 0.028 25.199 25.207 grid_integrate_task_list 107 12.3 22.662 23.084 22.662 23.084 grid_collocate_task_list 107 9.7 21.703 22.184 21.703 22.184 dbcsr_multiply_generic 1966 12.4 0.063 0.066 11.556 11.725 qs_scf_new_mos 96 7.5 0.001 0.001 8.965 9.108 qs_scf_loop_do_ot 96 8.5 0.001 0.001 8.964 9.107 multiply_cannon 1966 13.4 0.133 0.153 8.587 8.922 ot_scf_mini 96 9.5 0.002 0.002 8.407 8.544 multiply_cannon_loop 1966 14.4 0.084 0.097 8.128 8.522 mp_waitall_1 136719 16.5 6.549 7.191 6.549 7.191 multiply_cannon_metrocomm3 15728 15.4 0.033 0.035 4.651 5.352 ot_mini 96 10.5 0.001 0.003 4.869 5.012 rs_pw_transfer 878 11.9 0.009 0.011 3.903 4.523 init_scf_loop 11 6.9 0.000 0.000 4.467 4.467 density_rs2pw 107 9.7 0.005 0.005 3.192 3.807 init_scf_run 11 5.9 0.000 0.004 3.752 3.752 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.752 3.752 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.699 3.712 wfi_extrapolate 11 7.9 0.001 0.001 3.411 3.411 pw_transfer 1295 11.6 0.091 0.101 2.912 2.955 multiply_cannon_multrec 15728 15.4 2.738 2.875 2.746 2.884 potential_pw2rs 107 12.3 0.006 0.007 2.825 2.851 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 2.761 2.799 qs_ot_get_derivative 96 11.5 0.001 0.001 2.501 2.632 fft_wrap_pw1pw2_140 439 13.2 0.228 0.260 2.353 2.418 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.331 2.405 apply_single 107 13.6 0.000 0.000 2.331 2.405 ot_diis_step 96 11.5 0.003 0.003 2.351 2.351 mp_waitany 8968 13.7 1.369 2.059 1.369 2.059 fft3d_ps 1081 14.6 1.044 1.135 1.973 2.054 make_m2s 3932 13.4 0.039 0.041 2.000 2.039 make_images 3932 14.4 0.102 0.107 1.719 1.766 mp_alltoall_d11v 1998 13.7 0.976 1.677 0.976 1.677 rs_pw_transfer_RS2PW_140 118 11.5 0.161 0.185 1.040 1.657 rs_gather_matrices 107 12.3 0.071 0.084 0.767 1.447 ------------------------------------------------------------------------------- Plot: name="H2O-64_nonortho_timings_32omp", title="Timings of H2O-64_nonortho with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="rest", label="rest", y=41.80799999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.077, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.356, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.571, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.375, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.048, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.954, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_nonortho_timings_32mpi", title="Timings of H2O-64_nonortho with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="rest", label="rest", y=13.989000000000011, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.703, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.662, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.738, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=6.549, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.369, 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 0.206 0.206 104.312 104.312 qs_energies 1 2.0 0.000 0.000 103.461 103.461 scf_env_do_scf 1 3.0 0.000 0.000 102.309 102.309 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.354 97.354 rebuild_ks_matrix 7 6.0 0.000 0.000 97.299 97.299 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.299 97.299 hfx_ks_matrix 7 8.0 0.000 0.000 88.429 88.429 integrate_four_center 7 9.0 1.845 1.845 88.408 88.408 integrate_four_center_main 7 10.0 0.880 0.880 80.665 80.665 integrate_four_center_bin 445 11.0 79.784 79.784 79.784 79.784 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.463 56.463 init_scf_loop 1 4.0 0.000 0.000 45.828 45.828 integrate_four_center_load 7 10.0 0.000 0.000 5.658 5.658 hfx_load_balance 1 11.0 0.001 0.001 5.658 5.658 qs_vxc_create 14 8.0 0.000 0.000 3.229 3.229 xc_vxc_pw_create 14 9.0 0.180 0.180 3.229 3.229 hfx_load_balance_count 1 12.0 2.823 2.823 2.823 2.823 hfx_load_balance_bin 1 12.0 2.818 2.818 2.818 2.818 calculate_rho_elec 15 7.4 0.118 0.118 2.459 2.459 xc_rho_set_and_dset_create 14 10.0 0.105 0.105 2.386 2.386 prepare_preconditioner 1 5.0 0.000 0.000 2.250 2.250 make_preconditioner 1 6.0 0.000 0.000 2.250 2.250 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.182 2.182 ------------------------------------------------------------------------------- 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 0.246 94.363 94.374 qs_energies 1 2.0 0.000 0.000 94.014 94.021 scf_env_do_scf 1 3.0 0.000 0.000 93.675 93.675 qs_ks_update_qs_env 8 5.0 0.000 0.000 91.770 91.770 rebuild_ks_matrix 7 6.0 0.000 0.000 91.762 91.762 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 91.762 91.762 hfx_ks_matrix 7 8.0 0.000 0.000 86.547 86.549 integrate_four_center 7 9.0 0.053 0.338 86.539 86.540 integrate_four_center_main 7 10.0 0.003 0.003 78.586 79.860 integrate_four_center_bin 448 11.0 78.583 79.857 78.583 79.857 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 52.494 52.494 init_scf_loop 1 4.0 0.000 0.000 41.180 41.180 integrate_four_center_load 7 10.0 0.000 0.000 5.709 5.710 hfx_load_balance 1 11.0 0.001 0.001 5.709 5.710 hfx_load_balance_count 1 12.0 2.763 2.854 2.763 2.854 hfx_load_balance_bin 1 12.0 2.763 2.850 2.763 2.850 mp_sync 70 11.3 1.579 2.708 1.579 2.708 qs_vxc_create 14 8.0 0.000 0.000 2.348 2.351 xc_vxc_pw_create 14 9.0 0.007 0.008 2.348 2.351 xc_rho_set_and_dset_create 14 10.0 0.009 0.010 1.882 2.002 ------------------------------------------------------------------------------- Plot: name="H2O-hyb_timings_32omp", title="Timings of H2O-hyb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32omp", name="rest", label="rest", y=15.956000000000003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=79.784, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.823, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.818, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.845, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.88, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.206, 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=8.394000000000005, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.583, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.763, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.763, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.053, 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=0.225, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=1.579, yerr=0.0 Running GW_PBE_4benzene.inp with 1 threads and 32 ranks... done. Running GW_PBE_4benzene.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.013 0.013 76.556 76.556 qs_energies 1 2.0 0.000 0.000 76.171 76.171 mp2_main 1 3.0 0.000 0.000 73.463 73.463 mp2_gpw_main 1 4.0 0.000 0.000 73.357 73.357 rpa_ri_compute_en 1 5.0 0.000 0.000 69.667 69.667 rpa_num_int 1 6.0 0.001 0.001 69.661 69.661 compute_mat_P_omega 1 7.0 0.003 0.003 59.721 59.721 compute_mat_P_omega_contract 10 8.0 8.801 8.801 59.526 59.526 dbt_total 2336 9.6 0.011 0.011 45.922 45.922 dbt_contract 787 11.0 0.033 0.033 39.245 39.245 dbt_tas_total 1149 12.2 0.197 0.197 38.335 38.335 dbt_tas_multiply 807 12.1 0.003 0.003 36.958 36.958 dbt_tas_dbm 807 14.1 0.003 0.003 30.431 30.431 dbm_multiply 807 16.1 30.423 30.423 30.423 30.423 dbt_tas_mm_1N 524 15.1 0.001 0.001 23.328 23.328 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 21.869 21.869 compute_mat_P_omega_calc_M_occ 250 9.0 8.839 8.839 16.896 16.896 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.501 6.501 dbt_tas_mm_2 251 15.0 0.001 0.001 5.629 5.629 dbt_copy 1103 10.7 0.068 0.068 5.284 5.284 compute_QP_energies 1 7.0 0.000 0.000 4.997 4.997 compute_self_energy_cubic_gw 1 8.0 0.053 0.053 4.996 4.996 contract_cubic_gw 21 9.0 0.000 0.000 4.004 4.004 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.683 3.683 dbt_tas_reserve_blocks_index 3261 14.3 0.142 0.142 3.309 3.309 dbm_reserve_blocks 3628 15.3 3.237 3.237 3.237 3.237 scf_env_do_scf 1 3.0 0.000 0.000 2.583 2.583 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.583 2.583 dbt_reserve_blocks_index 2280 13.1 0.051 0.051 2.552 2.552 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.507 2.507 convert_to_new_pgrid 2421 14.1 0.107 0.107 2.309 2.309 dbm_copy 1614 15.1 2.203 2.203 2.203 2.203 dbt_crop 1042 12.0 1.390 1.390 2.187 2.187 dbt_tas_reshape 367 15.0 0.019 0.019 2.105 2.105 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.104 2.104 dbt_tas_copy 574 11.4 1.289 1.289 2.074 2.074 compute_W_cubic_GW 10 7.0 0.004 0.004 1.996 1.996 get_2c_integrals 1 6.0 0.000 0.000 1.792 1.792 dbt_reshape 278 11.9 0.920 0.920 1.773 1.773 ------------------------------------------------------------------------------- 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 0.024 30.936 30.946 qs_energies 1 2.0 0.000 0.000 30.844 30.847 mp2_main 1 3.0 0.000 0.000 29.954 29.957 mp2_gpw_main 1 4.0 0.000 0.000 29.921 29.924 rpa_ri_compute_en 1 5.0 0.000 0.000 28.652 28.654 rpa_num_int 1 6.0 0.000 0.002 28.651 28.654 dbt_total 2336 9.6 0.011 0.012 25.384 25.392 compute_mat_P_omega 1 7.0 0.001 0.005 23.732 23.751 compute_mat_P_omega_contract 10 8.0 0.392 0.414 23.621 23.626 dbt_contract 787 11.0 0.025 0.026 19.200 19.203 dbt_tas_total 1149 12.2 0.048 0.056 17.312 17.313 dbt_tas_multiply 807 12.1 0.002 0.002 17.264 17.265 dbt_tas_dbm 807 14.1 0.002 0.003 13.164 13.173 dbm_multiply 807 16.1 9.957 10.977 9.957 10.977 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.042 7.045 compute_mat_P_omega_calc_M_occ 250 9.0 0.375 0.395 6.940 6.942 mp_sync 8706 11.6 4.924 6.299 4.924 6.299 dbt_tas_mm_2 251 15.0 0.001 0.001 5.870 5.871 dbt_copy 1111 10.7 0.011 0.012 5.371 5.654 dbt_reshape 1098 11.7 2.049 2.226 5.120 5.396 dbt_tas_mm_1N 524 15.1 0.001 0.001 4.707 5.109 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.048 5.049 compute_QP_energies 1 7.0 0.000 0.000 3.273 3.274 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 3.273 3.273 contract_cubic_gw 21 9.0 0.000 0.000 2.706 2.706 mp_waitall_2 3776 15.3 2.393 2.564 2.393 2.564 dbt_communicate_buffer 1098 12.7 0.053 0.056 2.448 2.553 dbt_reserve_blocks_index 2849 13.1 0.064 0.070 1.479 1.718 dbt_reserve_blocks_index_array 2791 12.2 0.009 0.011 1.470 1.707 dbt_tas_reserve_blocks_index 3300 14.5 0.111 0.120 1.447 1.682 dbm_reserve_blocks 3696 15.4 1.426 1.662 1.426 1.662 dbt_crop 1042 12.0 0.854 0.958 1.306 1.483 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.268 1.268 dbt_tas_replicate 396 14.1 0.524 0.685 1.050 1.115 parallel_gemm_fm 105 8.4 0.000 0.000 0.989 0.998 parallel_gemm_fm_cosma 105 9.4 0.989 0.998 0.989 0.998 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.927 0.929 convert_to_new_pgrid 2421 14.1 0.024 0.029 0.756 0.891 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.878 0.880 dbm_copy 1608 15.1 0.726 0.865 0.726 0.865 scf_env_do_scf 1 3.0 0.000 0.000 0.852 0.852 scf_env_do_scf_inner_loop 17 4.0 0.000 0.003 0.851 0.851 dbt_tas_mm_3N 22 15.1 0.000 0.000 0.495 0.759 compute_W_cubic_GW 10 7.0 0.001 0.001 0.749 0.755 mp_max_i 1994 9.8 0.516 0.729 0.516 0.729 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 0.648 0.648 mp_bcast_im 6 9.7 0.601 0.622 0.601 0.622 ------------------------------------------------------------------------------- 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=22.13299999999999, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=30.423, 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=8.839, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.801, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.237, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.203, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.92, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=8.693999999999999, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.957, 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=0.375, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.392, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.426, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.726, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.049, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.393, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.924, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.018 0.018 283.429 283.429 qs_forces 1 2.0 0.000 0.000 282.871 282.871 rebuild_ks_matrix 7 6.6 0.000 0.000 281.320 281.320 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 281.320 281.320 hfx_ks_matrix 7 8.6 0.000 0.000 279.462 279.462 hfx_ri_update_ks 7 9.6 0.000 0.000 239.975 239.975 hfx_ri_update_ks_Pmat 7 10.6 31.297 31.297 239.971 239.971 dbt_total 841 11.0 0.005 0.005 225.618 225.618 qs_energies 1 3.0 0.000 0.000 210.618 210.618 scf_env_do_scf 1 4.0 0.000 0.000 210.199 210.199 qs_ks_update_qs_env 8 6.0 0.000 0.000 209.117 209.117 dbt_contract 207 12.4 0.062 0.062 206.712 206.712 dbt_tas_total 375 13.4 1.646 1.646 205.730 205.730 dbt_tas_multiply 216 13.5 0.001 0.001 201.495 201.495 dbt_tas_dbm 216 15.5 0.001 0.001 189.421 189.421 dbm_multiply 216 17.5 189.418 189.418 189.418 189.418 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 184.565 184.565 dbt_tas_mm_2 91 16.5 0.001 0.001 175.816 175.816 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 134.743 134.743 init_scf_loop 2 5.0 0.000 0.000 75.454 75.454 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 72.206 72.206 hfx_ri_update_forces 1 7.0 1.544 1.544 39.484 39.484 hfx_ri_forces_Pmat_3c 1 8.0 4.671 4.671 22.658 22.658 dbt_copy 409 11.7 0.026 0.026 14.664 14.664 precalc_derivatives 1 8.0 2.128 2.128 13.019 13.019 dbt_reshape 132 13.2 6.245 6.245 10.316 10.316 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.476 9.476 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.422 9.422 build_3c_derivatives 3 9.0 2.712 2.712 7.323 7.323 dbt_tas_reserve_blocks_index 1287 15.4 0.277 0.277 7.223 7.223 dbm_reserve_blocks 1461 16.2 7.213 7.213 7.213 7.213 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.080 7.080 ------------------------------------------------------------------------------- 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 0.020 43.112 43.122 qs_forces 1 2.0 0.000 0.000 43.006 43.006 rebuild_ks_matrix 7 6.6 0.000 0.000 42.364 42.365 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 42.364 42.365 hfx_ks_matrix 7 8.6 0.000 0.000 41.453 41.459 dbt_total 841 11.0 0.005 0.005 36.786 36.793 dbt_contract 207 12.4 0.020 0.021 29.006 29.027 dbt_tas_total 375 13.4 0.047 0.162 26.936 26.936 dbt_tas_multiply 216 13.5 0.001 0.001 26.020 26.020 hfx_ri_update_ks 7 9.6 0.000 0.000 24.146 24.146 hfx_ri_update_ks_Pmat 7 10.6 1.181 1.259 24.145 24.145 qs_energies 1 3.0 0.000 0.000 22.693 22.693 scf_env_do_scf 1 4.0 0.000 0.001 22.560 22.561 qs_ks_update_qs_env 8 6.0 0.000 0.000 22.062 22.063 dbt_tas_dbm 216 15.5 0.001 0.001 20.829 20.842 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 20.303 20.303 dbm_multiply 216 17.5 18.291 19.559 18.291 19.559 hfx_ri_update_forces 1 7.0 0.055 0.058 17.306 17.313 hfx_ri_forces_Pmat_3c 1 8.0 0.166 0.178 12.890 12.912 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 12.565 12.565 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 11.498 11.499 init_scf_loop 2 5.0 0.000 0.000 9.995 9.995 dbt_tas_mm_2 91 16.5 0.001 0.001 9.717 9.718 mp_sync 2909 12.8 4.719 7.284 4.719 7.284 dbt_copy 421 11.8 0.009 0.011 6.344 6.644 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.362 5.865 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.757 4.757 dbt_reshape 252 12.8 2.200 2.294 4.359 4.534 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.993 4.213 precalc_derivatives 1 8.0 0.079 0.084 3.375 3.375 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.109 3.109 dbm_reserve_blocks 1477 16.3 2.436 2.834 2.436 2.834 dbt_tas_reserve_blocks_index 1302 15.5 0.216 0.226 2.434 2.793 dbt_crop 372 13.7 1.679 1.785 2.275 2.476 mp_waitall_2 1204 16.3 2.155 2.288 2.155 2.288 dbt_reserve_blocks_index 938 14.4 0.094 0.103 1.915 2.183 dbt_reserve_blocks_index_array 915 13.4 0.004 0.005 1.892 2.158 build_3c_derivatives 3 9.0 0.222 0.239 1.898 1.903 dbt_tas_replicate 175 15.2 0.648 0.686 1.605 1.685 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.623 1.628 dbt_communicate_buffer 252 13.8 0.011 0.013 1.459 1.541 convert_to_new_pgrid 648 15.5 0.033 0.065 1.254 1.541 dbt_tas_copy 169 12.8 0.758 0.802 1.353 1.482 dbm_copy 452 16.3 1.087 1.382 1.087 1.382 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.348 1.349 dbt_tas_communicate_buffer 352 16.4 0.013 0.013 0.917 0.964 ------------------------------------------------------------------------------- Plot: name="RI-HFX_H2O-32_timings_32omp", title="Timings of RI-HFX_H2O-32 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="rest", label="rest", y=44.58499999999998, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=189.418, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.297, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.213, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.245, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.671, 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 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=11.963999999999999, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=18.291, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.181, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.436, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.2, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.166, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.155, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.719, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.014 0.014 191.401 191.401 qs_energies 1 2.0 0.000 0.000 191.217 191.217 mp2_main 1 3.0 0.000 0.000 186.450 186.450 mp2_gpw_main 1 4.0 0.001 0.001 186.039 186.039 mp2_ri_gpw_compute_in 1 5.0 0.387 0.387 134.874 134.874 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 123.327 123.327 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 92.702 92.702 integrate_v_rspace 2666 8.0 0.643 0.643 79.773 79.773 grid_integrate_task_list 2666 9.0 77.130 77.130 77.130 77.130 mp2_ri_gpw_compute_en 1 5.0 0.086 0.086 51.145 51.145 mp2_ri_gpw_compute_en_RI_loop 1 6.0 10.082 10.082 49.272 49.272 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.077 2.077 32.099 32.099 local_gemm 2080 8.0 30.021 30.021 30.021 30.021 dbcsr_multiply_generic 5322 8.0 0.174 0.174 20.906 20.906 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.884 20.884 pw_transfer 63872 10.6 1.035 1.035 11.820 11.820 calculate_wavefunction 2656 8.0 8.121 8.121 11.594 11.594 get_2c_integrals 1 6.0 0.000 0.000 11.158 11.158 multiply_cannon 5322 9.0 0.430 0.430 10.712 10.712 fft_wrap_pw1pw2 53228 11.4 0.107 0.107 10.561 10.561 compute_2c_integrals 1 7.0 0.006 0.006 10.249 10.249 compute_2c_integrals_loop_lm 1 8.0 0.011 0.011 10.230 10.230 mp2_eri_2c_integrate_gpw 1 9.0 3.387 3.387 10.219 10.219 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.306 2.306 9.635 9.635 multiply_cannon_loop 5322 10.0 0.113 0.113 9.374 9.374 make_m2s 10644 9.0 0.061 0.061 8.003 8.003 multiply_cannon_multrec 5322 11.0 7.890 7.890 7.927 7.927 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 7.854 7.854 make_images 10644 10.0 3.151 3.151 7.696 7.696 fft_wrap_pw1pw2_20 21271 12.4 0.463 0.463 7.550 7.550 fft3d_s 53229 13.4 6.468 6.468 6.501 6.501 dbcsr_complete_redistribute 2689 9.0 1.142 1.142 5.768 5.768 dbcsr_finalize 10708 9.5 0.181 0.181 5.340 5.340 mp2_ri_gpw_compute_en_ener 2080 7.0 5.194 5.194 5.194 5.194 dbcsr_merge_all 8011 10.3 3.645 3.645 4.689 4.689 scf_env_do_scf 1 3.0 0.000 0.000 4.311 4.311 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.310 4.310 potential_pw2rs 5322 10.0 0.145 0.145 3.947 3.947 ------------------------------------------------------------------------------- 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 0.010 0.028 34.271 34.282 qs_energies 1 2.0 0.000 0.000 34.144 34.144 mp2_main 1 3.0 0.000 0.001 32.161 32.162 mp2_gpw_main 1 4.0 0.001 0.002 32.045 32.045 mp2_ri_gpw_compute_in 1 5.0 0.050 0.059 16.932 17.184 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.763 16.020 mp2_ri_gpw_compute_en 1 5.0 0.149 0.159 15.024 15.260 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.786 0.928 14.125 14.152 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.762 13.888 integrate_v_rspace 93 8.1 0.099 0.104 13.634 13.772 grid_integrate_task_list 93 9.1 13.339 13.496 13.339 13.496 mp2_ri_gpw_compute_en_expansio 65 7.0 0.097 0.116 10.706 10.837 local_gemm 65 8.0 10.609 10.739 10.609 10.739 mp2_ri_gpw_compute_en_comm 17 7.0 0.062 0.075 2.292 2.820 mp_sendrecv_dm3 1054 8.0 1.796 2.428 1.796 2.428 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.721 1.868 scf_env_do_scf 1 3.0 0.000 0.000 1.862 1.863 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 1.862 1.862 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.702 1.849 get_2c_integrals 1 6.0 0.000 0.000 1.098 1.128 multiply_cannon 176 9.0 0.015 0.016 1.035 1.101 multiply_cannon_loop 176 10.0 0.002 0.002 0.979 1.041 qs_scf_new_mos 10 5.0 0.000 0.000 0.919 0.931 eigensolver 11 5.8 0.001 0.001 0.901 0.903 multiply_cannon_multrec 246 11.0 0.850 0.893 0.855 0.899 compute_2c_integrals 1 7.0 0.002 0.003 0.811 0.832 pw_transfer 2120 10.5 0.044 0.046 0.739 0.751 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.723 0.748 mp2_eri_2c_integrate_gpw 1 9.0 0.195 0.200 0.721 0.747 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.743 0.746 cp_fm_redistribute_end 11 7.8 0.279 0.738 0.289 0.739 make_m2s 352 9.0 0.003 0.003 0.649 0.731 make_images 352 10.0 0.050 0.051 0.637 0.720 cp_fm_diag_elpa_base 11 7.8 0.434 0.699 0.445 0.714 fft_wrap_pw1pw2 1768 11.4 0.004 0.004 0.683 0.694 ------------------------------------------------------------------------------- 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=58.15700000000001, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=77.13, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=30.021, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=10.082, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.121, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.89, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 Plot: name="RI-MP2_ammonia_timings_32mpi", title="Timings of RI-MP2_ammonia with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="rest", label="rest", y=6.890999999999998, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.339, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.609, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=0.786, 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=0.85, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.796, 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 0.087 0.087 123.219 123.219 qs_energies 1 2.0 0.000 0.000 121.836 121.836 scf_env_do_scf 1 3.0 0.000 0.000 115.180 115.180 scf_env_do_scf_inner_loop 15 4.0 0.001 0.001 115.180 115.180 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.640 48.640 rebuild_ks_matrix 15 6.0 0.000 0.000 48.432 48.432 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.432 48.432 qs_scf_new_mos 15 5.0 0.000 0.000 41.734 41.734 eigensolver 15 6.0 0.001 0.001 33.795 33.795 qs_vxc_create 15 8.0 0.035 0.035 33.313 33.313 calculate_dispersion_nonloc 15 9.0 6.973 6.973 29.022 29.022 pw_transfer 1191 10.0 0.056 0.056 22.669 22.669 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 22.506 22.506 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.958 21.958 calculate_rho_elec 16 6.0 0.215 0.215 21.957 21.957 cp_fm_diag_elpa 15 7.0 0.000 0.000 21.693 21.693 cp_fm_diag_elpa_base 15 8.0 19.195 19.195 21.693 21.693 grid_collocate_task_list 16 7.0 20.607 20.607 20.607 20.607 fft_wrap_pw1pw2_150 765 12.0 3.594 3.594 16.380 16.380 sum_up_and_integrate 15 8.0 0.113 0.113 13.979 13.979 integrate_v_rspace 15 9.0 0.018 0.018 13.866 13.866 grid_integrate_task_list 15 10.0 13.349 13.349 13.349 13.349 cp_fm_cholesky_restore 45 7.0 9.914 9.914 9.914 9.914 fft3d_s 1087 13.0 9.831 9.831 9.838 9.838 pw_scatter_s 585 13.1 7.196 7.196 7.196 7.196 fft_wrap_pw1pw2_200 197 12.3 0.737 0.737 5.949 5.949 dbcsr_complete_redistribute 46 8.3 2.257 2.257 5.653 5.653 copy_dbcsr_to_fm 16 5.9 0.000 0.000 5.546 5.546 cp_fm_upper_to_full 30 8.0 4.685 4.685 4.685 4.685 vdW_energy 15 10.0 4.282 4.282 4.282 4.282 xc_vxc_pw_create 15 9.0 0.221 0.221 4.256 4.256 gspace_mixing 14 5.0 0.170 0.170 4.058 4.058 broyden_mixing 14 6.0 3.449 3.449 3.449 3.449 init_scf_run 1 3.0 0.000 0.000 3.115 3.115 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.083 3.083 xc_pw_derive 90 11.0 0.001 0.001 2.748 2.748 calculate_dm_sparse 15 6.0 0.017 0.017 2.745 2.745 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 2.668 2.668 ------------------------------------------------------------------------------- From /workspace/artifacts/diag_cu144_broy_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.014 0.028 63.702 63.714 qs_energies 1 2.0 0.000 0.000 63.443 63.448 scf_env_do_scf 1 3.0 0.000 0.001 59.412 59.413 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 59.412 59.413 qs_rho_update_rho_low 16 5.0 0.000 0.000 23.081 23.085 calculate_rho_elec 16 6.0 0.007 0.007 23.081 23.085 qs_ks_update_qs_env 15 5.0 0.000 0.000 23.035 23.049 rebuild_ks_matrix 15 6.0 0.000 0.000 23.002 23.016 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 23.002 23.016 grid_collocate_task_list 16 7.0 19.486 20.500 19.486 20.500 sum_up_and_integrate 15 8.0 0.010 0.015 14.010 14.064 integrate_v_rspace 15 9.0 0.000 0.001 13.999 14.057 qs_scf_new_mos 15 5.0 0.000 0.000 13.914 14.028 grid_integrate_task_list 15 10.0 12.941 13.114 12.941 13.114 eigensolver 15 6.0 0.001 0.002 12.946 12.973 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.512 9.515 cp_fm_diag_elpa_base 15 8.0 9.369 9.403 9.507 9.508 qs_vxc_create 15 8.0 0.001 0.001 8.710 8.722 calculate_dispersion_nonloc 15 9.0 0.903 0.920 6.936 6.958 pw_transfer 1191 10.0 0.084 0.093 6.451 6.507 fft_wrap_pw1pw2 1086 11.0 0.011 0.012 6.283 6.352 fft3d_ps 1086 13.0 2.339 2.549 4.678 4.873 fft_wrap_pw1pw2_150 765 12.0 0.250 0.290 3.950 3.988 rs_pw_transfer 158 9.4 0.001 0.002 3.471 3.895 density_rs2pw 16 7.0 0.001 0.001 3.475 3.852 mp_waitany 520 11.3 2.545 3.360 2.545 3.360 cp_fm_cholesky_restore 45 7.0 3.289 3.351 3.289 3.351 rs_pw_transfer_RS2PW_200 18 8.8 0.027 0.032 1.818 2.858 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.434 2.434 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.147 2.337 fft_wrap_pw1pw2_200 197 12.3 0.173 0.204 2.215 2.279 mp_alltoall_z22v 1086 15.0 1.772 2.264 1.772 2.264 xc_vxc_pw_create 15 9.0 0.015 0.019 1.773 1.800 rs_pw_transfer_RS2PW_70 16 9.0 0.006 0.008 0.656 1.771 x_to_yz 585 14.1 0.324 0.347 1.226 1.411 init_scf_run 1 3.0 0.000 0.000 1.372 1.373 build_core_ppnl 1 5.0 1.256 1.372 1.256 1.372 yz_to_x 501 13.9 0.220 0.313 1.090 1.338 vdW_energy 15 10.0 1.266 1.337 1.266 1.337 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.288 1.289 ------------------------------------------------------------------------------- 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=50.32299999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.607, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.195, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.349, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=9.914, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=9.831, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="mp_waitany", label="mp_waitany", 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=16.071999999999996, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.486, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=9.369, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.941, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.289, 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="mp_waitany", label="mp_waitany", y=2.545, 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 0.075 0.075 323.490 323.490 qs_energies 1 2.0 0.000 0.000 323.357 323.357 ls_scf 1 3.0 0.000 0.000 322.111 322.111 ls_scf_main 1 4.0 0.002 0.002 312.902 312.902 density_matrix_trs4 11 5.0 0.012 0.012 222.148 222.148 arnoldi_extremal 12 6.1 0.000 0.000 139.431 139.431 arnoldi_normal_ev 12 7.1 0.014 0.014 139.431 139.431 dbcsr_matrix_vector_mult 652 9.0 0.173 0.173 137.060 137.060 build_subspace 23 8.1 0.076 0.076 137.033 137.033 dbcsr_matrix_vector_mult_local 652 10.0 135.458 135.458 135.467 135.467 ls_scf_dm_to_ks 11 5.0 0.000 0.000 85.495 85.495 matrix_ls_to_qs 11 6.0 0.000 0.000 82.215 82.215 dbcsr_multiply_generic 185 6.1 0.835 0.835 72.023 72.023 dbcsr_copy_into_existing 11 7.0 44.704 44.704 44.704 44.704 multiply_cannon 185 7.1 0.279 0.279 43.580 43.580 dbcsr_complete_redistribute 23 7.5 30.239 30.239 41.265 41.265 matrix_decluster 11 7.0 0.000 0.000 37.509 37.509 multiply_cannon_loop 185 8.1 0.230 0.230 31.432 31.432 make_m2s 370 7.1 0.038 0.038 24.187 24.187 make_images 370 8.1 10.478 10.478 22.641 22.641 multiply_cannon_multrec 185 9.1 22.375 22.375 22.401 22.401 dbcsr_finalize 646 7.5 0.155 0.155 14.403 14.403 dbcsr_merge_all 597 8.5 2.146 2.146 13.369 13.369 setup_rec_index_2d 370 8.1 11.781 11.781 11.781 11.781 dbcsr_sort_indices 1103 9.9 10.046 10.046 10.046 10.046 tree_to_linear_d 110 9.4 10.010 10.010 10.010 10.010 calculate_norms 370 9.1 8.801 8.801 8.801 8.801 quick_finalize 395 10.0 0.356 0.356 8.687 8.687 ls_scf_init_scf 1 4.0 0.000 0.000 8.536 8.536 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.196 8.196 dbcsr_special_finalize 370 9.1 0.002 0.002 8.039 8.039 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.545 7.545 ------------------------------------------------------------------------------- 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 0.007 0.020 63.668 63.678 qs_energies 1 2.0 0.000 0.000 63.580 63.580 ls_scf 1 3.0 0.000 0.000 63.532 63.532 ls_scf_main 1 4.0 0.000 0.007 61.075 61.076 density_matrix_trs4 11 5.0 0.006 0.016 58.677 58.731 dbcsr_multiply_generic 185 6.1 0.057 0.076 55.539 55.792 multiply_cannon 185 7.1 0.032 0.035 46.142 46.808 multiply_cannon_loop 185 8.1 0.105 0.123 43.893 44.785 multiply_cannon_multrec 1480 9.1 26.820 29.943 27.071 30.214 mp_waitall_1 11936 10.3 14.928 17.609 14.928 17.609 multiply_cannon_metrocomm3 1480 9.1 0.013 0.016 8.867 13.618 make_m2s 370 7.1 0.034 0.038 6.487 6.562 multiply_cannon_metrocomm1 1480 9.1 0.007 0.009 3.387 6.449 make_images 370 8.1 0.617 0.650 6.363 6.436 calculate_norms 2960 9.1 4.408 5.195 4.408 5.195 make_images_data 370 9.1 0.008 0.011 2.897 3.105 mp_sum_l 1119 5.6 1.906 2.818 1.906 2.818 hybrid_alltoall_any 393 9.9 0.173 0.914 2.519 2.694 arnoldi_extremal 12 6.1 0.000 0.000 2.307 2.320 arnoldi_normal_ev 12 7.1 0.001 0.004 2.307 2.320 build_subspace 23 8.1 0.018 0.023 2.209 2.210 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.077 2.131 dbcsr_complete_redistribute 23 7.5 1.157 1.284 1.851 1.983 dbcsr_matrix_vector_mult 652 9.0 0.009 0.044 1.892 1.960 matrix_ls_to_qs 11 6.0 0.000 0.000 1.804 1.938 ls_scf_init_scf 1 4.0 0.000 0.000 1.905 1.906 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.880 1.887 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.034 1.862 make_images_pack 370 9.1 1.582 1.802 1.585 1.806 matrix_decluster 11 7.0 0.000 0.000 1.667 1.799 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.718 1.720 dbcsr_matrix_vector_mult_local 652 10.0 1.564 1.619 1.566 1.621 dbcsr_finalize 646 7.5 0.007 0.008 1.313 1.440 buffer_matrices_ensure_size 370 8.1 1.212 1.379 1.212 1.379 ------------------------------------------------------------------------------- Plot: name="bench_dftb_timings_32omp", title="Timings of bench_dftb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32omp", name="rest", label="rest", y=70.132, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=135.458, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=44.704, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.239, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.375, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.781, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.801, 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_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=11.302999999999997, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.564, 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=1.157, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=26.82, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="setup_rec_index_2d", label="setup_rec_index_2d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.408, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.582, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.928, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.906, yerr=0.0 Running dbcsr.inp with 1 threads and 32 ranks... done. Running dbcsr.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/dbcsr_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.007 69.758 69.758 lib_test 1 2.0 0.000 0.000 69.751 69.751 dbcsr_run_tests 3 3.0 0.002 0.002 69.751 69.751 test_multiplies_multiproc 3 4.0 0.001 0.001 53.851 53.851 dbcsr_redistribute 9 5.0 35.182 35.182 36.745 36.745 dbcsr_make_random_matrix 9 4.0 12.591 12.591 15.793 15.793 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.790 15.790 multiply_cannon 9 6.0 0.001 0.001 11.154 11.154 multiply_cannon_loop 9 7.0 0.002 0.002 10.800 10.800 multiply_cannon_multrec 9 8.0 10.797 10.797 10.798 10.798 dbcsr_finalize 27 5.7 0.004 0.004 5.712 5.712 dbcsr_merge_all 18 6.5 1.960 1.960 4.989 4.989 dbcsr_data_release 975 7.6 2.787 2.787 2.787 2.787 tree_to_linear_d 9 7.0 1.873 1.873 1.873 1.873 make_m2s 18 6.0 0.001 0.001 1.568 1.568 make_images 18 7.0 0.543 0.543 1.519 1.519 ------------------------------------------------------------------------------- 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 0.010 17.386 17.391 lib_test 1 2.0 0.000 0.000 17.326 17.345 dbcsr_run_tests 3 3.0 0.000 0.001 17.325 17.345 test_multiplies_multiproc 3 4.0 0.000 0.003 16.477 16.510 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.137 15.241 multiply_cannon 9 6.0 0.001 0.002 13.427 13.710 multiply_cannon_loop 9 7.0 0.002 0.002 13.151 13.417 multiply_cannon_multrec 72 8.0 11.054 11.483 11.055 11.484 mp_waitall_1 576 9.2 2.396 2.987 2.396 2.987 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.878 2.455 dbcsr_data_release 444 7.6 0.800 0.896 0.800 0.896 mp_sum_l 390 2.5 0.376 0.855 0.376 0.855 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.373 0.852 dbcsr_make_random_matrix 9 4.0 0.661 0.689 0.801 0.825 dbcsr_finalize 27 5.7 0.000 0.000 0.702 0.812 dbcsr_destroy 111 5.9 0.000 0.000 0.640 0.730 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.212 0.717 make_m2s 18 6.0 0.001 0.001 0.646 0.671 make_images 18 7.0 0.021 0.024 0.643 0.668 dbcsr_merge_all 18 6.5 0.099 0.116 0.541 0.640 dbcsr_data_copy_aa2 18 7.5 0.328 0.422 0.328 0.422 dbcsr_redistribute 9 5.0 0.233 0.272 0.392 0.416 make_images_data 18 8.0 0.000 0.001 0.337 0.410 hybrid_alltoall_any 18 9.0 0.027 0.117 0.297 0.363 ------------------------------------------------------------------------------- Plot: name="dbcsr_timings_32omp", title="Timings of dbcsr with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32omp", name="rest", label="rest", y=6.440999999999988, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.182, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.591, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.797, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.787, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.96, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=1.7669999999999995, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.233, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.661, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.054, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.8, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.099, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.376, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.396, 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 0.049 127.882 127.882 qs_mol_dyn_low 1 2.0 0.003 0.003 126.497 126.497 velocity_verlet 5 3.0 0.003 0.003 102.943 102.943 qmmm_el_coupling 6 3.8 0.000 0.000 84.073 84.073 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 84.070 84.070 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 83.423 83.423 qmmm_elec_gaussian_low_G 6 6.8 82.531 82.531 82.531 82.531 qs_forces 6 3.8 0.000 0.000 34.055 34.055 qs_energies 6 4.8 0.000 0.000 30.185 30.185 scf_env_do_scf 6 5.8 0.001 0.001 27.885 27.885 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.339 24.339 rebuild_ks_matrix 45 8.4 0.000 0.000 23.417 23.417 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.417 23.417 qs_ks_update_qs_env 45 7.8 0.000 0.000 19.975 19.975 pw_transfer 966 12.3 0.051 0.051 16.812 16.812 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.626 16.626 fft_wrap_pw1pw2_150 507 15.2 2.215 2.215 16.211 16.211 qs_vxc_create 45 10.4 0.001 0.001 12.951 12.951 xc_vxc_pw_create 45 11.4 0.684 0.684 12.950 12.950 xc_pw_derive 270 13.4 0.002 0.002 9.070 9.070 fft3d_s 802 15.6 7.574 7.574 7.582 7.582 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.088 7.088 calculate_rho_elec 45 8.9 0.562 0.562 7.088 7.088 xc_rho_set_and_dset_create 45 12.4 0.588 0.588 6.624 6.624 pw_scatter_s 429 15.8 5.587 5.587 5.587 5.587 xc_pw_divergence 45 12.4 0.001 0.001 5.581 5.581 qmmm_forces 6 3.8 0.001 0.001 5.188 5.188 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 4.860 4.860 pw_integral_ab 2539 7.4 4.410 4.410 4.410 4.410 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.147 4.147 qs_ks_ddapc 45 10.4 0.001 0.001 4.090 4.090 init_scf_loop 6 6.8 0.000 0.000 3.541 3.541 qmmm_forces_gaussian_low_G 6 6.8 3.455 3.455 3.455 3.455 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.449 3.449 sum_up_and_integrate 45 10.4 0.339 0.339 3.325 3.325 density_rs2pw 45 9.9 0.002 0.002 3.276 3.276 grid_collocate_task_list 45 9.9 3.249 3.249 3.249 3.249 integrate_v_rspace 45 11.4 0.006 0.006 2.986 2.986 fist_calc_energy_force 6 3.8 0.001 0.001 2.572 2.572 ------------------------------------------------------------------------------- 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 52.610 52.621 qs_mol_dyn_low 1 2.0 0.003 0.004 51.621 51.678 qs_forces 6 3.8 0.000 0.001 37.462 37.462 qs_energies 6 4.8 0.000 0.000 35.676 35.680 scf_env_do_scf 6 5.8 0.000 0.001 34.781 34.781 scf_env_do_scf_inner_loop 113 6.2 0.002 0.016 33.375 33.375 rebuild_ks_matrix 119 8.1 0.000 0.000 24.442 24.449 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.016 24.442 24.448 qs_ks_update_qs_env 119 7.3 0.001 0.001 22.940 22.946 velocity_verlet 5 3.0 0.002 0.003 21.806 21.809 pw_transfer 2446 12.3 0.206 0.224 16.186 16.610 fft_wrap_pw1pw2 2059 13.4 0.024 0.026 15.738 16.206 fft_wrap_pw1pw2_150 1321 14.9 1.226 1.407 15.199 15.646 qs_vxc_create 119 10.1 0.002 0.003 12.791 12.794 xc_vxc_pw_create 119 11.1 0.148 0.216 12.789 12.792 fft3d_ps 2059 15.4 6.760 7.491 11.707 12.364 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.174 10.175 calculate_rho_elec 119 8.3 0.048 0.054 10.173 10.175 xc_pw_derive 714 13.1 0.010 0.012 9.601 9.871 sum_up_and_integrate 119 10.1 0.081 0.092 8.554 8.571 integrate_v_rspace 119 11.1 0.003 0.003 8.473 8.498 qmmm_forces 6 3.8 0.002 0.002 7.239 7.239 qmmm_forces_with_gaussian 6 4.8 0.008 0.009 6.981 7.106 xc_pw_divergence 119 12.1 0.005 0.006 6.229 6.468 xc_rho_set_and_dset_create 119 12.1 0.355 0.438 6.228 6.400 rs_pw_transfer 988 11.5 0.011 0.013 6.062 6.242 qmmm_el_coupling 6 3.8 0.000 0.000 6.044 6.136 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 6.043 6.134 density_rs2pw 119 9.3 0.006 0.007 5.697 5.863 potential_pw2rs 119 12.1 0.006 0.008 4.868 4.881 mp_alltoall_z22v 2059 17.4 3.525 4.829 3.525 4.829 grid_collocate_task_list 119 9.3 4.334 4.521 4.334 4.521 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.822 3.873 grid_integrate_task_list 119 12.1 3.358 3.554 3.358 3.554 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.303 3.440 x_to_yz 1095 16.8 0.823 0.907 2.666 3.258 qmmm_forces_gaussian_low_G 6 6.8 3.143 3.191 3.143 3.191 yz_to_x 964 16.0 0.536 0.659 2.218 2.858 qmmm_elec_gaussian_low_G 6 6.8 2.713 2.843 2.713 2.843 pw_restrict_s3 18 5.8 1.350 1.378 2.550 2.636 mp_waitany 4028 12.8 2.169 2.538 2.169 2.538 rs_pw_transfer_PW2RS_150 125 13.9 0.719 0.806 2.201 2.228 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.071 2.161 pw_prolongate_s3 18 6.8 1.164 1.196 2.071 2.161 qs_scf_new_mos 113 7.2 0.000 0.000 2.004 2.008 qs_scf_loop_do_ot 113 8.2 0.000 0.000 2.003 2.008 rs_pw_transfer_RS2PW_150 125 11.2 0.593 0.721 1.786 1.965 ot_scf_mini 113 9.2 0.001 0.001 1.921 1.926 qs_ks_ddapc 119 10.1 0.002 0.002 1.822 1.887 dbcsr_multiply_generic 2588 12.3 0.057 0.058 1.818 1.846 pw_integral_ab 2761 7.7 1.229 1.329 1.426 1.577 pw_scatter_p 1095 15.8 1.518 1.558 1.518 1.558 pw_gather_p 964 15.0 1.236 1.546 1.236 1.546 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.515 1.515 init_scf_loop 6 6.8 0.000 0.000 1.404 1.404 mp_waitall_1 177795 16.4 1.099 1.225 1.099 1.225 mp_sum_dm3 33 5.7 1.175 1.223 1.175 1.223 ot_mini 113 10.2 0.000 0.000 1.175 1.179 ------------------------------------------------------------------------------- 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=21.076000000000008, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=82.531, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.574, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.587, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.41, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.455, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.249, 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=27.548000000000002, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.713, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_scatter_s", label="pw_scatter_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=1.229, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.143, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.334, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.358, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.76, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.525, yerr=0.0 Summary: Performance test took 33 minutes. Status: OK Removing intermediate container 741c475728fb ---> 8ac5c6631cd7 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 29782b026b28 Removing intermediate container 29782b026b28 ---> 2e916872da47 Step 42/42 : ENTRYPOINT [] ---> Running in 32525cfaacc5 Removing intermediate container 32525cfaacc5 ---> 089ccb28a80d [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 089ccb28a80d 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: 2023-01-01 19:50:46+00:00