StartDate: 2022-07-03 19:05:51+00:00 CpuId: 32x AMD (unknown model) [Zen 3], 7nm (SMT disabled) CommitSHA: f5159689a29131af92ba897515ff763ec195115c CommitTime: 2022-07-03 18:25:20 +0200 CommitAuthor: Juerg Hutter CommitSubject: GAPW/GAPW_XC regtest margin and code conventions (#2181) Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=f5159689a29131af92ba897515ff763ec195115c Sending build context to Docker daemon 363.3MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 405f018f9d1d: Already exists Digest: sha256:b6b83d3c331794420340093eb706a6f152d9c1fa51b262d9bf34594887c2c7ac Status: Downloaded newer image for ubuntu:22.04 ---> 27941809078c Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 92ee757f28a3 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> a398cc4ae5b3 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> e20712e9c254 Step 5/42 : RUN mkdir scripts ---> Using cache ---> c7b9413ca6be 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 ---> 5f4bcd2de9f5 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> c39d97839810 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --mpi-mode=mpich --with-gcc=system --dry-run ---> Using cache ---> d0b21d05b338 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 6e616c7670ff Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 5ba44cd61a38 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 1aa896c19a24 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> c7ccbf5e1b85 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 9cb6a1bd2cd3 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 1eed70bdd06a Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> ac04ff4ae473 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> cd0e2369620a Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 1b4ef27dc823 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 8c2ce1cbdb23 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> c08a0bc6f0ef Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 377bc99f74ae Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 415f340401e7 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 46d9c769ebc6 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 6aafee7e9835 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 2e0fc7bba01b Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> dd31a4351cf1 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> a67db58bafbb Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> e7d1480e5889 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> f822acadf693 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 0b0fdcc56471 Step 30/42 : COPY ./Makefile . ---> Using cache ---> a38c6462aef8 Step 31/42 : COPY ./src ./src ---> 110e39cbdeef Step 32/42 : COPY ./exts ./exts ---> 91e48dfd5b2a Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> 33e428e90230 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 80cbd712087a './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 80cbd712087a ---> c41490354543 Step 35/42 : COPY ./data ./data ---> 81f2026e87e0 Step 36/42 : COPY ./tests ./tests ---> d038f4a3b3c2 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 3fe4d25f5119 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 74c15544af02 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> d70f04571546 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in b276eb9211cb ========== 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 0.033 0.033 179.697 179.697 qs_mol_dyn_low 1 2.0 0.002 0.002 179.102 179.102 qs_forces 11 3.9 0.001 0.001 179.066 179.066 qs_energies 11 4.9 0.001 0.001 173.054 173.054 scf_env_do_scf 11 5.9 0.001 0.001 161.151 161.151 velocity_verlet 10 3.0 0.002 0.002 123.936 123.936 init_scf_loop 11 6.9 0.000 0.000 87.442 87.442 prepare_preconditioner 11 7.9 0.000 0.000 84.960 84.960 make_preconditioner 11 8.9 0.000 0.000 84.960 84.960 make_full_inverse_cholesky 11 9.9 0.000 0.000 83.827 83.827 scf_env_do_scf_inner_loop 108 6.5 0.010 0.010 73.519 73.519 cp_fm_cholesky_invert 11 10.9 58.875 58.875 58.875 58.875 qs_scf_new_mos 108 7.5 0.001 0.001 39.620 39.620 qs_scf_loop_do_ot 108 8.5 0.001 0.001 39.619 39.619 ot_scf_mini 108 9.5 0.002 0.002 38.256 38.256 cp_fm_cholesky_decompose 22 10.9 21.134 21.134 21.134 21.134 qs_ot_get_p 119 10.4 0.001 0.001 20.788 20.788 rebuild_ks_matrix 119 8.3 0.001 0.001 20.169 20.169 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.168 20.168 qs_ot_p2m_diag 50 11.0 0.154 0.154 19.525 19.525 dbcsr_multiply_generic 2286 12.5 0.165 0.165 19.353 19.353 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.188 19.188 calculate_rho_elec 119 8.7 0.950 0.950 19.188 19.188 cp_dbcsr_syevd 50 12.0 0.002 0.002 19.115 19.115 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.485 18.485 cp_fm_diag_elpa 50 13.0 0.000 0.000 18.028 18.028 cp_fm_diag_elpa_base 50 14.0 17.969 17.969 18.027 18.027 grid_collocate_task_list 119 9.7 14.862 14.862 14.862 14.862 ot_mini 108 10.5 0.001 0.001 14.089 14.089 sum_up_and_integrate 119 10.3 0.181 0.181 12.562 12.562 integrate_v_rspace 119 11.3 0.088 0.088 12.381 12.381 make_m2s 4572 13.5 0.045 0.045 10.620 10.620 grid_integrate_task_list 119 12.3 10.523 10.523 10.523 10.523 qs_ot_get_derivative 108 11.5 0.001 0.001 8.665 8.665 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.119 6.119 pw_transfer 1439 11.6 0.056 0.056 5.823 5.823 dbcsr_make_dense_low 5837 15.5 0.074 0.074 5.731 5.731 make_dense_data 5837 16.5 5.059 5.059 5.644 5.644 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.613 5.613 ot_diis_step 108 11.5 0.004 0.004 5.421 5.421 make_images 4572 14.5 2.061 2.061 5.351 5.351 dbcsr_make_images_dense 3978 14.8 0.017 0.017 4.950 4.950 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 4.849 4.849 apply_single 119 13.6 0.000 0.000 4.849 4.849 fft_wrap_pw1pw2_140 487 13.2 0.401 0.401 4.780 4.780 multiply_cannon 2286 13.5 0.166 0.166 4.769 4.769 init_scf_run 11 5.9 0.002 0.002 4.758 4.758 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.756 4.756 multiply_cannon_loop 2286 14.5 0.077 0.077 4.315 4.315 multiply_cannon_multrec 2286 15.5 4.187 4.187 4.236 4.236 wfi_extrapolate 11 7.9 0.001 0.001 4.212 4.212 dbcsr_complete_redistribute 329 12.2 1.885 1.885 3.855 3.855 copy_fm_to_dbcsr 176 11.2 0.001 0.001 3.784 3.784 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.021 49.266 49.276 qs_mol_dyn_low 1 2.0 0.004 0.009 49.159 49.167 qs_forces 11 3.9 0.001 0.001 49.116 49.116 qs_energies 11 4.9 0.001 0.001 45.777 45.779 scf_env_do_scf 11 5.9 0.001 0.002 42.029 42.029 scf_env_do_scf_inner_loop 108 6.5 0.002 0.017 38.785 38.785 velocity_verlet 10 3.0 0.001 0.003 29.379 29.380 rebuild_ks_matrix 119 8.3 0.000 0.001 18.834 18.969 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.020 18.834 18.968 qs_ks_update_qs_env 119 7.6 0.001 0.001 16.818 16.944 sum_up_and_integrate 119 10.3 0.018 0.020 14.443 14.473 integrate_v_rspace 119 11.3 0.004 0.005 14.425 14.454 qs_rho_update_rho_low 119 7.7 0.001 0.001 14.335 14.350 calculate_rho_elec 119 8.7 0.030 0.031 14.335 14.350 dbcsr_multiply_generic 2286 12.5 0.070 0.083 13.457 13.661 grid_collocate_task_list 119 9.7 8.959 11.006 8.959 11.006 grid_integrate_task_list 119 12.3 8.093 10.877 8.093 10.877 qs_scf_new_mos 108 7.5 0.001 0.001 10.654 10.798 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.654 10.798 multiply_cannon 2286 13.5 0.129 0.143 9.808 10.304 ot_scf_mini 108 9.5 0.002 0.002 9.994 10.123 multiply_cannon_loop 2286 14.5 0.094 0.126 9.289 9.863 mp_waitall_1 169478 16.3 8.332 9.014 8.332 9.014 rs_pw_transfer 974 11.9 0.011 0.014 6.125 6.559 multiply_cannon_metrocomm3 18288 15.5 0.038 0.052 5.539 6.300 ot_mini 108 10.5 0.001 0.001 5.788 5.933 density_rs2pw 119 9.7 0.005 0.007 5.047 5.482 mp_alltoall_d11v 2130 13.8 3.129 3.492 3.129 3.492 potential_pw2rs 119 12.3 0.006 0.008 3.402 3.410 pw_transfer 1439 11.6 0.099 0.115 3.340 3.390 mp_waitany 9880 13.7 2.824 3.308 2.824 3.308 multiply_cannon_multrec 18288 15.5 2.930 3.284 2.940 3.295 rs_gather_matrices 119 12.3 0.072 0.085 2.894 3.272 init_scf_loop 11 6.9 0.000 0.000 3.231 3.231 fft_wrap_pw1pw2 1201 12.6 0.009 0.012 3.176 3.222 qs_ot_get_derivative 108 11.5 0.001 0.001 3.006 3.134 rs_pw_transfer_RS2PW_140 130 11.5 0.300 0.372 2.634 3.070 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.681 2.800 apply_single 119 13.6 0.000 0.000 2.681 2.800 fft_wrap_pw1pw2_140 487 13.2 0.271 0.318 2.723 2.792 ot_diis_step 108 11.5 0.003 0.004 2.753 2.754 init_scf_run 11 5.9 0.000 0.004 2.580 2.580 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.580 2.580 make_m2s 4572 13.5 0.045 0.055 2.328 2.395 wfi_extrapolate 11 7.9 0.001 0.001 2.338 2.338 fft3d_ps 1201 14.6 1.216 1.276 2.286 2.337 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.148 2.156 make_images 4572 14.5 0.117 0.139 2.006 2.062 qs_ot_get_p 119 10.4 0.001 0.001 1.332 1.502 rs_pw_transfer_PW2RS_140 130 13.9 0.606 0.650 1.404 1.438 mp_sum_l 11218 13.2 0.875 1.305 0.875 1.305 prepare_preconditioner 11 7.9 0.000 0.000 1.213 1.230 make_preconditioner 11 8.9 0.000 0.000 1.213 1.230 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.862 1.165 mp_sum_d 4129 12.0 0.931 1.164 0.931 1.164 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.109 1.131 multiply_cannon_metrocomm1 18288 15.5 0.019 0.029 0.518 1.129 make_images_data 4572 15.5 0.035 0.041 1.028 1.120 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.991 1.061 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.941 1.021 hybrid_alltoall_any 4725 16.4 0.062 0.168 0.910 1.003 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 0.991 0.992 ------------------------------------------------------------------------------- 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=52.147000000000006, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=58.875, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=21.134, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=17.969, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.862, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.523, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.187, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", 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=17.822999999999997, 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="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.959, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.093, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.93, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=3.129, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.332, 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 0.026 0.026 203.550 203.550 qs_mol_dyn_low 1 2.0 0.003 0.003 202.917 202.917 qs_forces 11 3.9 0.001 0.001 202.880 202.880 qs_energies 11 4.9 0.001 0.001 195.237 195.237 scf_env_do_scf 11 5.9 0.001 0.001 181.322 181.322 velocity_verlet 10 3.0 0.002 0.002 141.589 141.589 init_scf_loop 11 6.9 0.000 0.000 91.892 91.892 scf_env_do_scf_inner_loop 96 6.5 0.009 0.009 89.284 89.284 prepare_preconditioner 11 7.9 0.000 0.000 87.728 87.728 make_preconditioner 11 8.9 0.000 0.000 87.728 87.728 make_full_inverse_cholesky 11 9.9 0.000 0.000 86.621 86.621 cp_fm_cholesky_invert 11 10.9 60.515 60.515 60.515 60.515 qs_scf_new_mos 96 7.5 0.001 0.001 34.667 34.667 qs_scf_loop_do_ot 96 8.5 0.001 0.001 34.667 34.667 rebuild_ks_matrix 107 8.3 0.001 0.001 33.538 33.538 qs_ks_build_kohn_sham_matrix 107 9.3 0.010 0.010 33.538 33.538 ot_scf_mini 96 9.5 0.002 0.002 33.371 33.371 qs_rho_update_rho_low 107 7.7 0.001 0.001 31.399 31.399 calculate_rho_elec 107 8.7 0.857 0.857 31.398 31.398 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.151 30.151 grid_collocate_task_list 107 9.7 27.444 27.444 27.444 27.444 sum_up_and_integrate 107 10.3 0.162 0.162 26.476 26.476 integrate_v_rspace 107 11.3 0.080 0.080 26.314 26.314 grid_integrate_task_list 107 12.3 24.534 24.534 24.534 24.534 cp_fm_cholesky_decompose 22 10.9 22.131 22.131 22.131 22.131 qs_ot_get_p 107 10.4 0.001 0.001 18.089 18.089 dbcsr_multiply_generic 1966 12.4 0.141 0.141 17.244 17.244 qs_ot_p2m_diag 44 11.0 0.136 0.136 17.004 17.004 cp_dbcsr_syevd 44 12.0 0.002 0.002 16.650 16.650 cp_fm_diag_elpa 44 13.0 0.000 0.000 15.693 15.693 cp_fm_diag_elpa_base 44 14.0 15.642 15.642 15.692 15.692 ot_mini 96 10.5 0.001 0.001 12.281 12.281 make_m2s 3932 13.4 0.040 0.040 9.351 9.351 qs_ot_get_derivative 96 11.5 0.001 0.001 7.674 7.674 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.838 6.838 init_scf_run 11 5.9 0.002 0.002 6.227 6.227 scf_env_initial_rho_setup 11 6.9 0.001 0.001 6.225 6.225 pw_transfer 1295 11.6 0.051 0.051 5.621 5.621 wfi_extrapolate 11 7.9 0.001 0.001 5.561 5.561 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.421 5.421 dbcsr_make_dense_low 4961 15.5 0.066 0.066 4.898 4.898 make_dense_data 4961 16.5 4.321 4.321 4.820 4.820 make_images 3932 14.4 1.818 1.818 4.746 4.746 fft_wrap_pw1pw2_140 439 13.2 0.400 0.400 4.686 4.686 ot_diis_step 96 11.5 0.003 0.003 4.605 4.605 multiply_cannon 1966 13.4 0.142 0.142 4.432 4.432 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.310 4.310 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.245 4.245 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.243 4.243 apply_single 107 13.6 0.000 0.000 4.243 4.243 ------------------------------------------------------------------------------- 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 0.021 82.269 82.279 qs_mol_dyn_low 1 2.0 0.003 0.004 82.009 82.013 qs_forces 11 3.9 0.001 0.001 81.971 81.971 qs_energies 11 4.9 0.001 0.001 76.443 76.447 scf_env_do_scf 11 5.9 0.000 0.002 70.877 70.878 scf_env_do_scf_inner_loop 96 6.5 0.002 0.017 65.701 65.701 velocity_verlet 10 3.0 0.001 0.003 48.708 48.709 rebuild_ks_matrix 107 8.3 0.000 0.001 36.384 36.502 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.019 36.384 36.501 sum_up_and_integrate 107 10.3 0.018 0.020 32.505 32.534 integrate_v_rspace 107 11.3 0.004 0.005 32.487 32.516 qs_ks_update_qs_env 107 7.6 0.001 0.001 32.196 32.296 qs_rho_update_rho_low 107 7.7 0.000 0.001 31.475 31.495 calculate_rho_elec 107 8.7 0.027 0.028 31.475 31.495 grid_integrate_task_list 107 12.3 22.877 29.309 22.877 29.309 grid_collocate_task_list 107 9.7 21.979 28.411 21.979 28.411 dbcsr_multiply_generic 1966 12.4 0.063 0.072 11.287 11.560 rs_pw_transfer 878 11.9 0.010 0.012 10.047 10.901 density_rs2pw 107 9.7 0.005 0.006 9.172 10.024 qs_scf_new_mos 96 7.5 0.001 0.001 8.963 9.062 qs_scf_loop_do_ot 96 8.5 0.001 0.001 8.962 9.062 multiply_cannon 1966 13.4 0.113 0.133 8.055 8.569 ot_scf_mini 96 9.5 0.002 0.002 8.401 8.494 multiply_cannon_loop 1966 14.4 0.088 0.113 7.558 8.119 mp_waitany 8968 13.7 7.176 8.074 7.176 8.074 rs_pw_transfer_RS2PW_140 118 11.5 0.247 0.284 6.982 7.838 mp_alltoall_d11v 1998 13.7 6.754 7.668 6.754 7.668 rs_gather_matrices 107 12.3 0.068 0.086 6.524 7.403 mp_waitall_1 146670 16.2 6.541 7.183 6.541 7.183 init_scf_loop 11 6.9 0.000 0.000 5.163 5.164 ot_mini 96 10.5 0.001 0.001 4.954 5.066 multiply_cannon_metrocomm3 15728 15.4 0.035 0.047 4.178 5.034 init_scf_run 11 5.9 0.000 0.004 4.370 4.375 scf_env_initial_rho_setup 11 6.9 0.000 0.003 4.370 4.375 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.317 4.336 wfi_extrapolate 11 7.9 0.001 0.001 3.971 3.971 pw_transfer 1295 11.6 0.090 0.099 3.180 3.228 fft_wrap_pw1pw2 1081 12.6 0.009 0.010 3.030 3.088 potential_pw2rs 107 12.3 0.006 0.007 3.049 3.059 multiply_cannon_multrec 15728 15.4 2.671 2.942 2.680 2.953 qs_ot_get_derivative 96 11.5 0.001 0.001 2.595 2.689 fft_wrap_pw1pw2_140 439 13.2 0.247 0.295 2.597 2.674 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.219 2.372 apply_single 107 13.6 0.000 0.000 2.219 2.372 ot_diis_step 96 11.5 0.003 0.003 2.325 2.326 fft3d_ps 1081 14.6 1.123 1.169 2.209 2.278 make_m2s 3932 13.4 0.040 0.049 2.080 2.148 make_images 3932 14.4 0.105 0.124 1.793 1.862 ------------------------------------------------------------------------------- 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=53.28400000000002, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=60.515, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.444, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.534, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=22.131, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=15.642, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", 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=16.942000000000007, 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="grid_collocate_task_list", label="grid_collocate_task_list", y=21.979, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.877, 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_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=7.176, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=6.754, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=6.541, 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 0.175 0.175 147.030 147.030 qs_energies 1 2.0 0.000 0.000 146.239 146.239 scf_env_do_scf 1 3.0 0.000 0.000 144.845 144.845 qs_ks_update_qs_env 8 5.0 0.000 0.000 111.157 111.157 rebuild_ks_matrix 7 6.0 0.000 0.000 111.103 111.103 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 111.103 111.103 hfx_ks_matrix 7 8.0 0.000 0.000 93.788 93.788 integrate_four_center 7 9.0 1.265 1.265 93.771 93.771 integrate_four_center_main 7 10.0 0.996 0.996 81.272 81.272 init_scf_loop 1 4.0 0.000 0.000 80.575 80.575 integrate_four_center_bin 450 11.0 80.277 80.277 80.277 80.277 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 64.260 64.260 prepare_preconditioner 1 5.0 0.000 0.000 27.986 27.986 make_preconditioner 1 6.0 0.000 0.000 27.986 27.986 arnoldi_normal_ev 11 9.3 0.001 0.001 16.432 16.432 estimate_cond_num 1 7.0 0.000 0.000 16.390 16.390 build_subspace 28 9.5 0.008 0.008 15.981 15.981 integrate_four_center_load 7 10.0 0.000 0.000 10.983 10.983 hfx_load_balance 1 11.0 0.001 0.001 10.983 10.983 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 9.799 9.799 admm_fit_mo_coeffs 7 9.0 0.000 0.000 8.623 8.623 cp_fm_cholesky_invert 2 9.5 8.146 8.146 8.146 8.146 make_full_inverse_cholesky 1 7.0 0.000 0.000 7.559 7.559 dbcsr_sym_m_v_mult 562 10.0 0.013 0.013 7.291 7.291 DGKS_ortho_d 673 10.6 6.946 6.946 6.948 6.948 hfx_load_balance_count 1 12.0 5.492 5.492 5.492 5.492 Gram_Schmidt_ortho_d 673 10.6 5.476 5.476 5.476 5.476 hfx_load_balance_bin 1 12.0 5.474 5.474 5.474 5.474 qs_scf_new_mos 7 5.0 0.000 0.000 4.385 4.385 qs_scf_loop_do_ot 7 6.0 0.000 0.000 4.385 4.385 purify_mo_diag 7 10.0 0.000 0.000 4.323 4.323 ot_scf_mini 7 7.0 0.000 0.000 4.300 4.300 fit_mo_coeffs 7 10.0 0.000 0.000 4.300 4.300 make_full_single_inverse 1 7.0 0.000 0.000 3.916 3.916 arnoldi_generalized_ev 1 8.0 0.000 0.000 3.838 3.838 gev_build_subspace 4 9.0 0.004 0.004 3.723 3.723 cp_fm_syevd 7 11.0 0.000 0.000 3.718 3.718 cp_fm_syevd_base 7 12.0 3.718 3.718 3.718 3.718 qs_vxc_create 14 8.0 0.000 0.000 3.643 3.643 xc_vxc_pw_create 14 9.0 0.124 0.124 3.643 3.643 dbcsr_copy 1318 10.8 0.877 0.877 3.636 3.636 qs_ot_get_p 8 7.8 0.000 0.000 3.271 3.271 dbcsr_create_new 3176 12.1 2.136 2.136 3.224 3.224 qs_ot_p2m_diag 7 9.0 0.022 0.022 3.192 3.192 cp_dbcsr_syevd 7 10.0 0.000 0.000 3.123 3.123 cp_fm_cholesky_decompose 3 8.7 2.988 2.988 2.988 2.988 cp_fm_diag_elpa 7 11.0 0.000 0.000 2.953 2.953 cp_fm_diag_elpa_base 7 12.0 2.945 2.945 2.953 2.953 ------------------------------------------------------------------------------- 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 0.192 0.211 131.685 131.695 qs_energies 1 2.0 0.000 0.000 131.361 131.362 scf_env_do_scf 1 3.0 0.000 0.001 130.930 130.930 qs_ks_update_qs_env 8 5.0 0.000 0.000 128.882 128.883 rebuild_ks_matrix 7 6.0 0.000 0.000 128.874 128.875 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 128.874 128.875 hfx_ks_matrix 7 8.0 0.000 0.001 122.839 122.840 integrate_four_center 7 9.0 0.052 0.342 122.830 122.831 integrate_four_center_main 7 10.0 0.003 0.003 79.468 111.004 integrate_four_center_bin 448 11.0 79.466 111.000 79.466 111.000 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 74.657 74.657 init_scf_loop 1 4.0 0.000 0.000 56.272 56.272 mp_sync 70 11.3 31.553 33.850 31.553 33.850 integrate_four_center_load 7 10.0 0.000 0.000 11.125 11.128 hfx_load_balance 1 11.0 0.001 0.001 11.125 11.128 mp_sum_l 1135 8.3 5.506 5.777 5.506 5.777 hfx_load_balance_dist 1 12.0 0.000 0.000 5.355 5.616 hfx_load_balance_bin 1 12.0 2.845 5.540 2.845 5.540 hfx_load_balance_count 1 12.0 2.846 5.506 2.846 5.506 qs_vxc_create 14 8.0 0.000 0.000 2.910 2.910 xc_vxc_pw_create 14 9.0 0.008 0.009 2.910 2.910 ------------------------------------------------------------------------------- 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=35.218999999999994, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.277, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=8.146, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="DGKS_ortho_d", label="DGKS_ortho_d", y=6.946, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.492, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="Gram_Schmidt_ortho_d", label="Gram_Schmidt_ortho_d", y=5.476, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.474, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sum_l", label="mp_sum_l", 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=9.469000000000008, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=79.466, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="DGKS_ortho_d", label="DGKS_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.846, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="Gram_Schmidt_ortho_d", label="Gram_Schmidt_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.845, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=31.553, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=5.506, 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 0.013 154.939 154.939 qs_energies 1 2.0 0.000 0.000 154.570 154.570 mp2_main 1 3.0 0.000 0.000 130.933 130.933 mp2_gpw_main 1 4.0 0.000 0.000 129.748 129.748 rpa_ri_compute_en 1 5.0 0.000 0.000 122.795 122.795 rpa_num_int 1 6.0 0.001 0.001 122.790 122.790 compute_mat_P_omega 1 7.0 0.003 0.003 73.455 73.455 compute_mat_P_omega_contract 10 8.0 8.475 8.475 73.263 73.263 dbt_total 2336 9.6 0.011 0.011 60.986 60.986 dbt_contract 787 11.0 0.033 0.033 54.364 54.364 dbt_tas_total 1149 12.2 0.191 0.191 53.381 53.381 dbt_tas_multiply 807 12.1 0.002 0.002 51.949 51.949 dbt_tas_dbm 807 14.1 0.003 0.003 45.431 45.431 dbm_multiply 807 16.1 45.423 45.423 45.423 45.423 dbt_tas_mm_1N 524 15.1 0.002 0.002 34.676 34.676 GW_matrix_operations 10 7.0 0.011 0.011 31.854 31.854 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 31.096 31.096 cp_fm_cholesky_invert 10 8.0 31.042 31.042 31.042 31.042 scf_env_do_scf 1 3.0 0.000 0.000 23.463 23.463 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 23.463 23.463 qs_scf_new_mos 17 5.0 0.000 0.000 21.901 21.901 eigensolver 18 5.9 0.001 0.001 20.496 20.496 compute_mat_P_omega_calc_M_occ 250 9.0 8.497 8.497 18.328 18.328 cp_fm_diag_elpa 18 6.9 0.000 0.000 13.583 13.583 cp_fm_diag_elpa_base 18 7.9 13.545 13.545 13.582 13.582 cp_fm_cholesky_decompose 14 8.1 12.044 12.044 12.044 12.044 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 10.915 10.915 RPA_postprocessing_nokp 10 8.0 0.001 0.001 10.074 10.074 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 9.943 9.943 dbt_tas_mm_2 251 15.0 0.002 0.002 8.887 8.887 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 6.946 6.946 cp_fm_cholesky_restore 51 7.0 6.808 6.808 6.808 6.808 compute_QP_energies 1 7.0 0.000 0.000 5.590 5.590 compute_self_energy_cubic_gw 1 8.0 0.046 0.046 5.589 5.589 get_2c_integrals 1 6.0 0.000 0.000 5.429 5.429 dbt_copy 1103 10.7 0.116 0.116 5.174 5.174 contract_cubic_gw 21 9.0 0.000 0.000 4.640 4.640 ------------------------------------------------------------------------------- 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 0.021 32.065 32.075 qs_energies 1 2.0 0.000 0.001 31.973 31.974 mp2_main 1 3.0 0.000 0.002 30.990 30.991 mp2_gpw_main 1 4.0 0.000 0.000 30.951 30.951 rpa_ri_compute_en 1 5.0 0.000 0.000 29.700 29.701 rpa_num_int 1 6.0 0.000 0.002 29.699 29.700 dbt_total 2336 9.6 0.011 0.012 26.356 26.370 compute_mat_P_omega 1 7.0 0.001 0.005 25.304 25.330 compute_mat_P_omega_contract 10 8.0 0.420 0.445 25.139 25.142 dbt_contract 787 11.0 0.025 0.028 19.817 19.827 dbt_tas_total 1149 12.2 0.053 0.072 17.715 17.715 dbt_tas_multiply 807 12.1 0.002 0.002 17.652 17.654 dbt_tas_dbm 807 14.1 0.003 0.003 13.024 13.066 dbm_multiply 807 16.1 10.119 11.062 10.119 11.062 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.456 7.459 compute_mat_P_omega_calc_M_occ 250 9.0 0.401 0.429 7.447 7.448 dbt_tas_mm_2 251 15.0 0.001 0.001 6.145 6.158 dbt_copy 1111 10.7 0.011 0.012 5.691 5.978 dbt_reshape 1098 11.7 2.160 2.658 5.436 5.682 mp_sync 8706 11.6 4.775 5.627 4.775 5.627 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.370 5.373 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.645 5.042 compute_QP_energies 1 7.0 0.000 0.000 2.847 2.847 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 2.845 2.846 mp_waitall_2 3776 15.3 2.530 2.713 2.530 2.713 dbt_communicate_buffer 1098 12.7 0.054 0.072 2.570 2.698 contract_cubic_gw 21 9.0 0.000 0.000 2.216 2.218 dbt_reserve_blocks_index_array 2791 12.2 0.010 0.012 1.605 1.761 dbt_reserve_blocks_index 2849 13.1 0.064 0.074 1.603 1.757 dbt_crop 1042 12.0 0.924 1.166 1.432 1.726 dbt_tas_reserve_blocks_index 3300 14.5 0.115 0.146 1.572 1.723 dbm_reserve_blocks 3696 15.4 1.546 1.691 1.546 1.691 dbt_tas_replicate 396 14.1 0.536 0.721 1.138 1.280 mp2_ri_gpw_compute_in 1 5.0 0.001 0.009 1.246 1.248 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.997 1.000 cp_gemm 105 8.4 0.000 0.000 0.934 0.942 cp_gemm_cosma 105 9.4 0.934 0.942 0.934 0.942 scf_env_do_scf 1 3.0 0.000 0.000 0.938 0.938 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.937 0.938 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.932 0.934 convert_to_new_pgrid 2421 14.1 0.026 0.034 0.820 0.916 dbm_copy 1608 15.1 0.789 0.885 0.789 0.885 mp_max_i 1992 9.8 0.613 0.747 0.613 0.747 GW_matrix_operations 10 7.0 0.001 0.001 0.726 0.730 dbm_add 807 14.1 0.644 0.693 0.644 0.693 ------------------------------------------------------------------------------- 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=44.38799999999999, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=45.423, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=31.042, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=13.545, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=12.044, 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=8.497, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", 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=10.533999999999999, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.119, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, 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=0.401, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.775, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.53, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.16, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.546, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.017 0.017 379.557 379.557 qs_forces 1 2.0 0.000 0.000 379.002 379.002 rebuild_ks_matrix 7 6.6 0.000 0.000 358.804 358.804 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 358.804 358.804 hfx_ks_matrix 7 8.6 0.000 0.000 356.720 356.720 hfx_ri_update_ks 7 9.6 0.000 0.000 304.735 304.735 hfx_ri_update_ks_Pmat 7 10.6 31.826 31.826 304.732 304.732 dbt_total 4939 11.6 0.027 0.027 302.169 302.169 qs_energies 1 3.0 0.000 0.000 289.673 289.673 scf_env_do_scf 1 4.0 0.000 0.000 289.244 289.244 dbt_tas_total 2391 14.1 0.917 0.917 275.379 275.379 qs_ks_update_qs_env 8 6.0 0.000 0.000 269.525 269.525 dbt_contract 1473 13.0 0.120 0.120 254.297 254.297 dbt_tas_multiply 1482 14.0 0.004 0.004 244.356 244.356 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.004 225.818 225.818 dbt_tas_dbm 1482 16.0 0.005 0.005 222.760 222.760 dbm_multiply 1482 18.0 222.744 222.744 222.744 222.744 dbt_tas_mm_2 649 17.1 0.004 0.004 195.263 195.263 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 166.888 166.888 init_scf_loop 2 5.0 0.000 0.000 122.354 122.354 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 89.283 89.283 hfx_ri_update_forces 1 7.0 0.000 0.000 51.982 51.982 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 37.118 37.118 dbt_tas_reshape 906 14.4 0.016 0.016 22.843 22.843 dbt_tas_mm_3T 659 17.1 0.002 0.002 20.880 20.880 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 20.140 20.140 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 18.142 18.142 prepare_preconditioner 2 6.0 0.000 0.000 17.410 17.410 make_preconditioner 2 7.0 0.000 0.000 16.932 16.932 dbt_copy 2411 12.3 0.192 0.192 16.810 16.810 cp_fm_syevd 12 10.7 0.000 0.000 16.731 16.731 cp_fm_syevd_base 12 11.7 16.731 16.731 16.731 16.731 make_full_all 2 8.0 0.000 0.000 16.462 16.462 dbt_tas_merge 649 14.1 13.630 13.630 14.753 14.753 dbt_tas_reshape_buffer_fill 906 15.4 13.717 13.717 13.717 13.717 precalc_derivatives 1 8.0 0.005 0.005 12.029 12.029 dbm_reserve_blocks 8383 16.8 10.683 10.683 10.683 10.683 dbt_tas_reserve_blocks_index 7477 16.0 0.345 0.345 10.248 10.248 dbt_crop 2763 14.2 6.689 6.689 9.681 9.681 dbt_reshape 856 13.9 5.227 5.227 9.352 9.352 hfx_ri_pre_scf_Pmat_2c 1 13.0 0.000 0.000 8.695 8.695 dbt_reserve_blocks_index 4998 15.2 0.116 0.116 7.876 7.876 dbt_reserve_blocks_index_array 4963 14.3 0.018 0.018 7.824 7.824 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-HFX_H2O-32_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.023 58.123 58.134 qs_forces 1 2.0 0.000 0.000 57.933 57.933 rebuild_ks_matrix 7 6.6 0.000 0.000 57.273 57.274 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.002 57.273 57.274 hfx_ks_matrix 7 8.6 0.000 0.001 56.275 56.284 dbt_total 4939 11.6 0.027 0.033 50.759 50.775 dbt_contract 1473 13.0 0.092 0.100 39.166 39.177 hfx_ri_update_ks 7 9.6 0.000 0.000 38.643 38.644 hfx_ri_update_ks_Pmat 7 10.6 1.405 1.884 38.643 38.643 dbt_tas_total 2391 14.1 0.116 0.139 36.864 36.873 qs_energies 1 3.0 0.000 0.000 35.337 35.337 scf_env_do_scf 1 4.0 0.000 0.001 35.202 35.202 qs_ks_update_qs_env 8 6.0 0.000 0.000 34.691 34.692 dbt_tas_multiply 1482 14.0 0.005 0.005 32.945 32.947 dbt_tas_dbm 1482 16.0 0.005 0.006 25.366 25.395 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 22.583 22.584 dbm_multiply 1482 18.0 17.317 21.873 17.317 21.873 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.005 21.432 21.433 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 20.626 20.626 hfx_ri_update_forces 1 7.0 0.000 0.000 17.630 17.640 dbt_tas_mm_2 649 17.1 0.003 0.004 15.184 15.207 mp_sync 17669 13.5 12.333 14.691 12.333 14.691 init_scf_loop 2 5.0 0.000 0.000 14.575 14.575 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 12.204 12.213 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 7.852 7.859 dbt_copy 2429 12.3 0.030 0.033 6.443 6.898 dbt_tas_mm_3T 659 17.1 0.002 0.002 4.316 5.037 dbt_crop 2763 14.2 2.983 4.234 3.665 4.975 dbt_reshape 1257 13.5 2.092 2.578 4.414 4.704 precalc_derivatives 1 8.0 0.001 0.002 4.229 4.229 dbt_tas_mm_3N 163 16.5 0.000 0.001 3.960 4.082 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.829 3.829 mp_waitall_2 5988 16.5 2.876 3.123 2.876 3.123 dbt_tas_merge 649 14.1 1.562 2.138 2.704 3.110 dbm_reserve_blocks 8417 16.9 2.135 2.402 2.135 2.402 dbt_tas_reserve_blocks_index 7508 16.1 0.252 0.340 2.052 2.361 mp_max_i 3372 12.5 1.882 2.288 1.882 2.288 dbt_tas_replicate 909 15.6 0.602 0.789 2.192 2.252 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.000 0.000 2.209 2.215 dbt_tas_communicate_buffer 1825 16.3 0.059 0.074 2.007 2.212 build_3c_derivatives 9 9.0 0.229 0.341 1.996 1.998 dbt_reserve_blocks_index 5399 15.2 0.112 0.140 1.731 1.981 dbt_reserve_blocks_index_array 5364 14.2 0.014 0.015 1.730 1.981 mp_alltoall_i 4341 15.3 1.514 1.669 1.514 1.669 dbt_tas_reshape 916 14.4 0.008 0.009 1.568 1.636 dbt_communicate_buffer 1257 14.5 0.044 0.064 1.521 1.620 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.001 0.002 1.425 1.431 convert_to_new_pgrid 4446 16.0 0.039 0.045 1.248 1.389 dbm_copy 3043 16.9 1.209 1.352 1.209 1.352 mp_sum_l 38201 15.3 0.997 1.212 0.997 1.212 ------------------------------------------------------------------------------- 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=63.537000000000035, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=222.744, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.826, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="cp_fm_syevd_base", label="cp_fm_syevd_base", y=16.731, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=13.717, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_merge", label="dbt_tas_merge", y=13.63, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=10.683, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_crop", label="dbt_crop", y=6.689, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=17.511999999999993, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=17.317, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.405, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="cp_fm_syevd_base", label="cp_fm_syevd_base", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_merge", label="dbt_tas_merge", y=1.562, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.135, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_crop", label="dbt_crop", y=2.983, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=12.333, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.876, 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 0.013 0.013 286.574 286.574 qs_energies 1 2.0 0.000 0.000 286.395 286.395 mp2_main 1 3.0 0.000 0.000 251.817 251.817 mp2_gpw_main 1 4.0 0.001 0.001 249.173 249.173 mp2_ri_gpw_compute_in 1 5.0 0.374 0.374 205.023 205.023 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 180.432 180.432 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 153.397 153.397 integrate_v_rspace 2666 8.0 0.604 0.604 139.780 139.780 grid_integrate_task_list 2666 9.0 137.156 137.156 137.156 137.156 mp2_ri_gpw_compute_en 1 5.0 0.075 0.075 44.117 44.117 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.108 9.108 42.392 42.392 scf_env_do_scf 1 3.0 0.000 0.000 33.678 33.678 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 33.678 33.678 qs_scf_new_mos 10 5.0 0.000 0.000 32.445 32.445 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.201 2.201 26.520 26.520 eigensolver 11 5.8 0.001 0.001 24.615 24.615 offload_gemm 2080 8.0 24.319 24.319 24.319 24.319 get_2c_integrals 1 6.0 0.000 0.000 24.152 24.152 calculate_wavefunction 5312 9.0 15.908 15.908 23.563 23.563 cp_fm_diag_elpa 11 6.8 0.000 0.000 22.063 22.063 cp_fm_diag_elpa_base 11 7.8 21.916 21.916 22.063 22.063 dbcsr_multiply_generic 5322 8.0 0.173 0.173 20.851 20.851 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.818 20.818 compute_2c_integrals 1 7.0 0.006 0.006 18.118 18.118 compute_2c_integrals_loop_lm 1 8.0 0.009 0.009 18.099 18.099 mp2_eri_2c_integrate_gpw 1 9.0 3.503 3.503 18.090 18.090 pw_transfer 63872 10.6 0.922 0.922 11.525 11.525 multiply_cannon 5322 9.0 0.422 0.422 10.400 10.400 fft_wrap_pw1pw2 53228 11.4 0.112 0.112 10.320 10.320 multiply_cannon_loop 5322 10.0 0.306 0.306 9.044 9.044 qs_diis_b_step 9 6.0 0.000 0.000 8.830 8.830 make_m2s 10644 9.0 0.060 0.060 8.161 8.161 make_images 10644 10.0 3.127 3.127 7.855 7.855 cp_fm_symm 18 7.0 7.749 7.749 7.749 7.749 multiply_cannon_multrec 5322 11.0 7.298 7.298 7.335 7.335 fft_wrap_pw1pw2_20 21271 12.4 0.612 0.612 7.258 7.258 fft3d_s 53229 13.4 6.503 6.503 6.536 6.536 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.312 2.312 6.114 6.114 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.021 40.050 40.061 qs_energies 1 2.0 0.000 0.000 39.966 39.967 mp2_main 1 3.0 0.000 0.001 37.735 37.736 mp2_gpw_main 1 4.0 0.001 0.001 37.611 37.611 mp2_ri_gpw_compute_in 1 5.0 0.042 0.042 17.720 22.989 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 16.020 21.290 mp2_ri_gpw_compute_en 1 5.0 0.080 0.088 19.808 20.259 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.937 19.371 integrate_v_rspace 93 8.1 0.101 0.112 13.854 19.189 grid_integrate_task_list 93 9.1 13.497 18.803 13.497 18.803 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.588 0.671 13.505 13.575 mp2_ri_gpw_compute_en_expansio 65 7.0 0.076 0.091 10.508 10.849 offload_gemm 65 8.0 10.432 10.777 10.432 10.777 mp_min_d 2 7.0 5.310 5.729 5.310 5.729 mp2_ri_get_integ_group_size 1 6.0 0.000 0.000 5.270 5.721 mp2_ri_gpw_compute_en_comm 17 7.0 0.105 0.145 2.069 2.329 scf_env_do_scf 1 3.0 0.000 0.000 2.087 2.088 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 2.087 2.088 dbcsr_multiply_generic 176 8.0 0.008 0.008 1.787 2.063 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.771 2.046 mp_sendrecv_dm3 510 8.0 1.479 1.743 1.479 1.743 get_2c_integrals 1 6.0 0.000 0.001 1.646 1.659 compute_2c_integrals 1 7.0 0.003 0.004 1.352 1.364 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 0.987 1.290 mp2_eri_2c_integrate_gpw 1 9.0 0.201 0.321 0.986 1.289 multiply_cannon 176 9.0 0.014 0.015 1.039 1.123 qs_scf_new_mos 10 5.0 0.000 0.000 1.048 1.108 calculate_wavefunction 166 9.0 0.484 0.686 0.843 1.082 multiply_cannon_loop 176 10.0 0.002 0.003 0.984 1.066 eigensolver 11 5.8 0.001 0.001 1.045 1.045 make_m2s 352 9.0 0.003 0.003 0.711 0.903 make_images 352 10.0 0.051 0.059 0.699 0.890 multiply_cannon_multrec 246 11.0 0.837 0.878 0.843 0.884 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.879 0.880 cp_fm_redistribute_end 11 7.8 0.336 0.869 0.350 0.873 pw_transfer 2120 10.5 0.040 0.050 0.759 0.836 cp_fm_diag_elpa_base 11 7.8 0.509 0.821 0.520 0.835 ------------------------------------------------------------------------------- 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=70.86900000000003, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=137.156, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="offload_gemm", label="offload_gemm", y=24.319, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=21.916, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=15.908, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=9.108, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.298, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_min_d", label="mp_min_d", y=0.0, 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=6.913999999999994, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.497, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="offload_gemm", label="offload_gemm", y=10.432, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.509, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.484, 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=0.588, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.837, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_min_d", label="mp_min_d", y=5.31, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.479, 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 0.072 0.072 206.132 206.132 qs_energies 1 2.0 0.000 0.000 204.833 204.833 scf_env_do_scf 1 3.0 0.000 0.000 196.086 196.086 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 196.086 196.086 qs_scf_new_mos 15 5.0 0.000 0.000 122.836 122.836 eigensolver 15 6.0 0.001 0.001 115.367 115.367 cp_fm_diag_elpa 15 7.0 0.000 0.000 102.859 102.859 cp_fm_diag_elpa_base 15 8.0 100.287 100.287 102.859 102.859 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.454 48.454 rebuild_ks_matrix 15 6.0 0.000 0.000 48.248 48.248 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.248 48.248 qs_vxc_create 15 8.0 0.010 0.010 33.043 33.043 calculate_dispersion_nonloc 15 9.0 6.930 6.930 28.877 28.877 pw_transfer 1191 10.0 0.055 0.055 22.224 22.224 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 22.035 22.035 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.692 21.692 calculate_rho_elec 16 6.0 0.220 0.220 21.692 21.692 grid_collocate_task_list 16 7.0 20.422 20.422 20.422 20.422 fft_wrap_pw1pw2_150 765 12.0 3.111 3.111 15.795 15.795 sum_up_and_integrate 15 8.0 0.040 0.040 13.887 13.887 integrate_v_rspace 15 9.0 0.031 0.031 13.847 13.847 grid_integrate_task_list 15 10.0 13.308 13.308 13.308 13.308 fft3d_s 1087 13.0 10.316 10.316 10.324 10.324 cp_fm_cholesky_restore 45 7.0 10.313 10.313 10.313 10.313 pw_scatter_s 585 13.1 6.793 6.793 6.793 6.793 fft_wrap_pw1pw2_200 197 12.3 0.625 0.625 6.032 6.032 copy_dbcsr_to_fm 16 5.9 0.000 0.000 5.383 5.383 dbcsr_complete_redistribute 46 8.3 2.130 2.130 5.375 5.375 init_scf_run 1 3.0 0.000 0.000 5.317 5.317 cp_fm_upper_to_full 30 8.0 4.765 4.765 4.765 4.765 vdW_energy 15 10.0 4.364 4.364 4.364 4.364 gspace_mixing 14 5.0 0.170 0.170 4.299 4.299 xc_vxc_pw_create 15 9.0 0.212 0.212 4.157 4.157 ------------------------------------------------------------------------------- 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 0.013 0.029 61.756 61.766 qs_energies 1 2.0 0.000 0.000 61.457 61.458 scf_env_do_scf 1 3.0 0.000 0.001 57.357 57.357 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 57.357 57.357 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.740 24.759 rebuild_ks_matrix 15 6.0 0.000 0.000 24.709 24.728 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 24.708 24.728 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.614 20.616 calculate_rho_elec 16 6.0 0.007 0.007 20.614 20.616 grid_collocate_task_list 16 7.0 19.083 19.687 19.083 19.687 sum_up_and_integrate 15 8.0 0.006 0.009 13.958 14.013 integrate_v_rspace 15 9.0 0.001 0.001 13.952 14.009 grid_integrate_task_list 15 10.0 12.819 13.296 12.819 13.296 qs_scf_new_mos 15 5.0 0.000 0.000 12.709 12.918 eigensolver 15 6.0 0.001 0.002 11.699 11.724 qs_vxc_create 15 8.0 0.001 0.001 10.435 10.444 calculate_dispersion_nonloc 15 9.0 0.974 1.780 8.598 8.621 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.409 8.416 cp_fm_diag_elpa_base 15 8.0 8.255 8.276 8.405 8.408 pw_transfer 1191 10.0 0.086 0.092 8.032 8.127 fft_wrap_pw1pw2 1086 11.0 0.013 0.014 7.860 7.956 fft3d_ps 1086 13.0 2.565 2.831 6.167 6.325 fft_wrap_pw1pw2_150 765 12.0 0.296 0.318 5.436 5.502 mp_alltoall_z22v 1086 15.0 2.984 3.274 2.984 3.274 cp_fm_cholesky_restore 45 7.0 3.140 3.177 3.140 3.177 yz_to_x 501 13.9 0.248 0.334 2.310 2.493 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.470 2.470 fft_wrap_pw1pw2_200 197 12.3 0.181 0.200 2.301 2.373 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.151 2.354 xc_vxc_pw_create 15 9.0 0.015 0.018 1.836 1.860 rs_pw_transfer 158 9.4 0.001 0.002 1.459 1.726 density_rs2pw 16 7.0 0.001 0.001 1.413 1.570 mp_waitany 520 11.3 1.019 1.421 1.019 1.421 build_core_ppnl 1 5.0 1.257 1.393 1.257 1.393 init_scf_run 1 3.0 0.000 0.001 1.391 1.391 x_to_yz 585 14.1 0.343 0.366 1.265 1.371 vdW_energy 15 10.0 1.321 1.369 1.321 1.369 xc_pw_derive 90 11.0 0.001 0.002 1.245 1.321 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.307 1.307 ------------------------------------------------------------------------------- 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=51.48600000000002, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=100.287, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.422, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.308, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.316, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.313, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=15.474999999999994, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.255, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.083, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.819, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.14, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=2.984, 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 0.078 0.078 384.298 384.298 qs_energies 1 2.0 0.000 0.000 384.160 384.160 ls_scf 1 3.0 0.000 0.000 382.941 382.941 ls_scf_main 1 4.0 0.002 0.002 370.521 370.521 density_matrix_trs4 11 5.0 0.012 0.012 280.392 280.392 arnoldi_extremal 12 6.1 0.000 0.000 199.164 199.164 arnoldi_normal_ev 12 7.1 0.015 0.015 199.164 199.164 build_subspace 23 8.1 0.082 0.082 195.970 195.970 dbcsr_matrix_vector_mult 652 9.0 0.191 0.191 173.565 173.565 dbcsr_matrix_vector_mult_local 652 10.0 162.573 162.573 162.577 162.577 ls_scf_dm_to_ks 11 5.0 0.000 0.000 84.848 84.848 matrix_ls_to_qs 11 6.0 0.000 0.000 81.540 81.540 dbcsr_multiply_generic 185 6.1 0.813 0.813 73.643 73.643 dbcsr_copy_into_existing 11 7.0 44.678 44.678 44.678 44.678 multiply_cannon 185 7.1 0.362 0.362 44.374 44.374 dbcsr_complete_redistribute 23 7.5 29.826 29.826 40.574 40.574 matrix_decluster 11 7.0 0.000 0.000 36.861 36.861 multiply_cannon_loop 185 8.1 0.300 0.300 32.065 32.065 make_m2s 370 7.1 0.037 0.037 24.750 24.750 make_images 370 8.1 10.425 10.425 23.179 23.179 multiply_cannon_multrec 185 9.1 22.916 22.916 23.075 23.075 dbcsr_finalize 646 7.5 0.211 0.211 14.288 14.288 dbcsr_merge_all 597 8.5 2.178 2.178 13.156 13.156 DGKS_ortho_d 702 9.1 12.638 12.638 12.641 12.641 setup_rec_index_2d 370 8.1 11.856 11.856 11.856 11.856 ls_scf_init_scf 1 4.0 0.000 0.000 11.736 11.736 ls_scf_init_matrix_S 1 5.0 0.000 0.000 11.405 11.405 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 10.776 10.776 dbcsr_sort_indices 1103 9.9 10.729 10.729 10.729 10.729 Gram_Schmidt_ortho_d 702 9.1 10.514 10.514 10.515 10.515 tree_to_linear_d 110 9.4 9.745 9.745 9.745 9.745 quick_finalize 395 10.0 0.354 0.354 9.240 9.240 calculate_norms 370 9.1 8.691 8.691 8.691 8.691 dbcsr_special_finalize 370 9.1 0.002 0.002 8.548 8.548 ------------------------------------------------------------------------------- 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 0.020 66.670 66.680 qs_energies 1 2.0 0.000 0.000 66.577 66.577 ls_scf 1 3.0 0.000 0.000 66.517 66.518 ls_scf_main 1 4.0 0.001 0.008 63.900 63.901 density_matrix_trs4 11 5.0 0.006 0.017 61.284 61.361 dbcsr_multiply_generic 185 6.1 0.057 0.065 57.313 57.514 multiply_cannon 185 7.1 0.033 0.036 47.712 49.178 multiply_cannon_loop 185 8.1 0.112 0.135 45.275 46.639 multiply_cannon_multrec 1480 9.1 28.241 32.781 28.491 33.102 mp_waitall_1 11936 10.3 14.446 16.423 14.446 16.423 multiply_cannon_metrocomm3 1480 9.1 0.014 0.018 8.541 12.404 make_m2s 370 7.1 0.034 0.037 6.630 6.688 make_images 370 8.1 0.622 0.740 6.504 6.564 multiply_cannon_metrocomm1 1480 9.1 0.008 0.019 3.228 6.501 calculate_norms 2960 9.1 4.844 6.129 4.844 6.129 arnoldi_extremal 12 6.1 0.000 0.000 3.289 3.301 arnoldi_normal_ev 12 7.1 0.001 0.004 3.289 3.301 build_subspace 23 8.1 0.020 0.025 3.184 3.187 make_images_data 370 9.1 0.010 0.012 2.923 3.132 mp_sum_l 1119 5.6 2.047 3.027 2.047 3.027 dbcsr_matrix_vector_mult 652 9.0 0.009 0.054 2.195 2.906 hybrid_alltoall_any 393 9.9 0.188 0.997 2.568 2.811 dbcsr_matrix_vector_mult_local 652 10.0 1.678 2.624 1.680 2.627 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.268 2.346 dbcsr_complete_redistribute 23 7.5 1.181 1.561 1.892 2.062 ls_scf_init_scf 1 4.0 0.000 0.000 2.031 2.032 matrix_ls_to_qs 11 6.0 0.000 0.000 1.841 2.019 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.006 2.011 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.212 1.981 matrix_decluster 11 7.0 0.000 0.000 1.702 1.851 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.008 1.840 1.843 make_images_pack 370 9.1 1.586 1.729 1.590 1.734 buffer_matrices_ensure_size 370 8.1 1.361 1.446 1.361 1.446 dbcsr_finalize 646 7.5 0.008 0.009 1.282 1.403 ------------------------------------------------------------------------------- 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=102.97600000000006, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=162.573, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=44.678, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=29.826, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.916, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="DGKS_ortho_d", label="DGKS_ortho_d", y=12.638, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.691, 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 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=14.233000000000004, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.678, 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=1.181, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=28.241, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="DGKS_ortho_d", label="DGKS_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.844, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.047, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.446, 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 67.989 67.989 lib_test 1 2.0 0.000 0.000 67.982 67.982 dbcsr_run_tests 3 3.0 0.002 0.002 67.982 67.982 test_multiplies_multiproc 3 4.0 0.001 0.001 53.084 53.084 dbcsr_redistribute 9 5.0 34.469 34.469 35.954 35.954 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.565 15.565 dbcsr_make_random_matrix 9 4.0 12.053 12.053 14.801 14.801 multiply_cannon 9 6.0 0.001 0.001 11.166 11.166 multiply_cannon_loop 9 7.0 0.025 0.025 10.808 10.808 multiply_cannon_multrec 9 8.0 10.782 10.782 10.783 10.783 dbcsr_finalize 27 5.7 0.018 0.018 5.131 5.131 dbcsr_merge_all 18 6.5 1.883 1.883 4.463 4.463 dbcsr_data_release 975 7.6 2.493 2.493 2.493 2.493 tree_to_linear_d 9 7.0 1.790 1.790 1.790 1.790 make_m2s 18 6.0 0.001 0.001 1.481 1.481 make_images 18 7.0 0.541 0.541 1.435 1.435 ------------------------------------------------------------------------------- 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 0.004 0.010 17.629 17.634 lib_test 1 2.0 0.000 0.001 17.599 17.617 dbcsr_run_tests 3 3.0 0.001 0.001 17.595 17.613 test_multiplies_multiproc 3 4.0 0.000 0.002 16.769 16.833 dbcsr_multiply_generic 9 5.0 0.001 0.001 14.995 15.075 multiply_cannon 9 6.0 0.001 0.002 13.369 13.739 multiply_cannon_loop 9 7.0 0.002 0.002 13.102 13.406 multiply_cannon_multrec 72 8.0 10.982 11.526 10.983 11.527 mp_waitall_1 576 9.2 2.423 2.823 2.423 2.823 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.877 2.323 dbcsr_make_random_matrix 9 4.0 0.658 0.921 0.799 1.007 mp_sum_l 390 2.5 0.393 0.848 0.393 0.848 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.386 0.841 dbcsr_data_release 444 7.6 0.627 0.726 0.627 0.726 dbcsr_finalize 27 5.7 0.000 0.000 0.618 0.696 make_m2s 18 6.0 0.001 0.001 0.656 0.695 make_images 18 7.0 0.021 0.025 0.652 0.691 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.236 0.690 dbcsr_destroy 111 5.9 0.000 0.000 0.507 0.594 dbcsr_merge_all 18 6.5 0.088 0.112 0.496 0.561 dbcsr_checksum 6 5.0 0.155 0.528 0.529 0.529 dbcsr_redistribute 9 5.0 0.228 0.261 0.393 0.415 make_images_data 18 8.0 0.000 0.001 0.342 0.400 mp_sum_d 191 1.2 0.374 0.388 0.374 0.388 hybrid_alltoall_any 18 9.0 0.027 0.127 0.304 0.376 ------------------------------------------------------------------------------- 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=6.3089999999999975, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=34.469, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.053, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.782, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.493, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.883, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=2.230000000000002, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.228, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.658, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.982, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.627, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.088, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.423, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.393, 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 0.048 0.048 135.319 135.319 qs_mol_dyn_low 1 2.0 0.003 0.003 133.901 133.901 velocity_verlet 5 3.0 0.003 0.003 109.655 109.655 qmmm_el_coupling 6 3.8 0.000 0.000 83.931 83.931 qmmm_elec_with_gaussian 6 4.8 0.087 0.087 83.928 83.928 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 83.188 83.188 qmmm_elec_gaussian_low_G 6 6.8 82.284 82.284 82.284 82.284 qs_forces 6 3.8 0.000 0.000 41.413 41.413 qs_energies 6 4.8 0.000 0.000 37.373 37.373 scf_env_do_scf 6 5.8 0.001 0.001 33.926 33.926 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.784 24.784 rebuild_ks_matrix 45 8.4 0.000 0.000 23.865 23.865 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.865 23.865 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.246 20.246 pw_transfer 966 12.3 0.048 0.048 16.255 16.255 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.032 16.032 fft_wrap_pw1pw2_150 507 15.2 2.026 2.026 15.619 15.619 qs_vxc_create 45 10.4 0.001 0.001 12.792 12.792 xc_vxc_pw_create 45 11.4 0.640 0.640 12.792 12.792 init_scf_loop 6 6.8 0.000 0.000 9.136 9.136 xc_pw_derive 270 13.4 0.002 0.002 8.785 8.785 fft3d_s 802 15.6 7.133 7.133 7.140 7.140 qs_rho_update_rho_low 45 7.9 0.000 0.000 6.963 6.963 calculate_rho_elec 45 8.9 0.562 0.562 6.963 6.963 xc_rho_set_and_dset_create 45 12.4 0.660 0.660 6.821 6.821 prepare_preconditioner 6 7.8 0.000 0.000 5.892 5.892 pw_scatter_s 429 15.8 5.594 5.594 5.594 5.594 make_preconditioner 6 8.8 0.000 0.000 5.529 5.529 qmmm_forces 6 3.8 0.001 0.001 5.450 5.450 xc_pw_divergence 45 12.4 0.001 0.001 5.281 5.281 make_full_all 6 9.8 0.001 0.001 5.265 5.265 qmmm_forces_with_gaussian 6 4.8 0.117 0.117 5.135 5.135 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.284 4.284 pw_integral_ab 2539 7.4 4.230 4.230 4.230 4.230 qs_ks_ddapc 45 10.4 0.001 0.001 4.143 4.143 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.626 3.626 qmmm_forces_gaussian_low_G 6 6.8 3.572 3.572 3.572 3.572 grid_collocate_task_list 45 9.9 3.256 3.256 3.256 3.256 cp_fm_diag_elpa 18 11.2 0.000 0.000 3.153 3.153 cp_fm_diag_elpa_base 18 12.2 3.146 3.146 3.153 3.153 density_rs2pw 45 9.9 0.001 0.001 3.145 3.145 sum_up_and_integrate 45 10.4 0.114 0.114 3.002 3.002 pw_poisson_solve 51 9.9 1.235 1.235 2.917 2.917 integrate_v_rspace 45 11.4 0.006 0.006 2.888 2.888 ------------------------------------------------------------------------------- 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 0.031 0.051 57.112 57.123 qs_mol_dyn_low 1 2.0 0.003 0.004 55.937 55.994 qs_forces 6 3.8 0.000 0.001 40.228 40.228 qs_energies 6 4.8 0.000 0.001 38.398 38.399 scf_env_do_scf 6 5.8 0.000 0.001 37.431 37.431 scf_env_do_scf_inner_loop 113 6.2 0.002 0.015 35.926 35.926 rebuild_ks_matrix 119 8.1 0.000 0.000 26.405 26.415 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.019 26.405 26.415 qs_ks_update_qs_env 119 7.3 0.001 0.001 24.856 24.866 velocity_verlet 5 3.0 0.002 0.004 23.630 23.633 pw_transfer 2446 12.3 0.191 0.221 16.664 17.155 fft_wrap_pw1pw2 2059 13.4 0.024 0.027 16.227 16.718 fft_wrap_pw1pw2_150 1321 14.9 1.272 1.447 15.616 16.003 qs_vxc_create 119 10.1 0.002 0.007 13.143 13.147 xc_vxc_pw_create 119 11.1 0.156 0.221 13.141 13.145 fft3d_ps 2059 15.4 6.943 7.670 12.100 12.820 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.841 10.842 calculate_rho_elec 119 8.3 0.049 0.066 10.840 10.841 xc_pw_derive 714 13.1 0.011 0.013 9.866 10.158 sum_up_and_integrate 119 10.1 0.052 0.059 9.515 9.783 integrate_v_rspace 119 11.1 0.003 0.004 9.463 9.727 qmmm_forces 6 3.8 0.002 0.002 7.827 7.827 qmmm_forces_with_gaussian 6 4.8 0.365 0.405 7.361 7.738 rs_pw_transfer 988 11.5 0.011 0.015 7.343 7.567 xc_rho_set_and_dset_create 119 12.1 0.362 0.596 6.445 7.087 qmmm_el_coupling 6 3.8 0.000 0.000 6.997 7.085 qmmm_elec_with_gaussian 6 4.8 0.365 0.406 6.996 7.082 xc_pw_divergence 119 12.1 0.005 0.006 6.331 6.602 density_rs2pw 119 9.3 0.006 0.009 6.317 6.506 potential_pw2rs 119 12.1 0.005 0.007 5.624 5.631 grid_collocate_task_list 119 9.3 4.348 4.709 4.348 4.709 mp_alltoall_z22v 2059 17.4 3.628 4.162 3.628 4.162 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.832 4.080 grid_integrate_task_list 119 12.1 3.401 3.992 3.401 3.992 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.323 3.556 qmmm_forces_gaussian_low_G 6 6.8 3.154 3.396 3.154 3.396 x_to_yz 1095 16.8 0.881 0.997 2.887 3.171 qmmm_elec_gaussian_low_G 6 6.8 2.734 2.969 2.734 2.969 rs_pw_transfer_PW2RS_150 125 13.9 1.319 1.402 2.851 2.908 mp_waitany 4028 12.8 2.381 2.795 2.381 2.795 pw_restrict_s3 18 5.8 1.348 1.624 2.562 2.776 rs_pw_transfer_RS2PW_150 125 11.2 1.044 1.299 2.423 2.661 yz_to_x 964 16.0 0.586 0.795 2.209 2.643 dbcsr_multiply_generic 2588 12.3 0.057 0.076 2.177 2.374 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.144 2.268 pw_prolongate_s3 18 6.8 1.139 1.344 2.144 2.268 qs_scf_new_mos 113 7.2 0.000 0.000 2.100 2.106 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.100 2.106 mp_waitall_1 188862 16.2 1.851 2.057 1.851 2.057 qs_ks_ddapc 119 10.1 0.002 0.002 1.945 2.035 ot_scf_mini 113 9.2 0.001 0.001 2.015 2.021 mp_sum_dm3 33 5.7 1.669 1.757 1.669 1.757 pw_integral_ab 2761 7.7 1.262 1.337 1.521 1.630 pw_scatter_p 1095 15.8 1.561 1.614 1.561 1.614 pw_gather_p 964 15.0 1.241 1.601 1.241 1.601 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.559 1.559 init_scf_loop 6 6.8 0.000 0.000 1.503 1.503 ot_mini 113 10.2 0.001 0.001 1.231 1.237 ------------------------------------------------------------------------------- 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=29.249999999999986, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=82.284, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.133, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.594, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.23, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.572, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.256, 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="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=31.642, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.734, 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=1.262, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.154, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.348, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.943, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.401, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.628, yerr=0.0 Summary: Performance test took 45 minutes. Status: OK Removing intermediate container b276eb9211cb ---> d36fb2cddd35 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in c89120926de9 Removing intermediate container c89120926de9 ---> 234db1684fdf Step 42/42 : ENTRYPOINT [] ---> Running in 840ad6acd6ab Removing intermediate container 840ad6acd6ab ---> 56b574056354 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 56b574056354 Successfully tagged gcr.io/cp2k-org-project/img_cp2k-perf-openmp-arch-14b:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2022-07-03 20:02:00+00:00