StartDate: 2024-05-01 08:04:35+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 3add4946b9bb18f107c1b62045068fef1eb9b325 CommitTime: 2024-04-30 21:51:36 +0200 CommitAuthor: Mathieu Taillefumier CommitSubject: [PWDFT] SIRIUS returns -T S for the entropic term #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=3add4946b9bb18f107c1b62045068fef1eb9b325 Build-Cache: Yes Populating docker build cache... done. DEPRECATED: The legacy builder is deprecated and will be removed in a future release. BuildKit is currently disabled; enable it by removing the DOCKER_BUILDKIT=0 environment-variable. Sending build context to Docker daemon 394.2MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu e311a697a403: Pulling fs layer e311a697a403: Verifying Checksum e311a697a403: Download complete e311a697a403: Pull complete Digest: sha256:6d7b5d3317a71adb5e175640150e44b8b9a9401a7dd394f44840626aff9fa94d Status: Downloaded newer image for ubuntu:22.04 ---> 437ec753bef3 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 7a6476255769 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 9759504efaad Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> abda0bfe25be Step 5/42 : RUN mkdir scripts ---> Using cache ---> 6eb283287b7d 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 ---> ee4cd275054d Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> fd984e9d4562 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 5902e1a16638 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 69e44f9a893a Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 428b0608a456 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 3a7df50fbb07 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> f05686e6a599 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> a15c0849487c Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> e87fda45d6e9 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 2f3db5faf758 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 3c53ae4e8ae7 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 372303e3c837 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 718edd7c4dae Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 456e0995f7d4 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 6edd3007c804 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 113504d442bb Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 483a37b93ac9 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 4be2a0046810 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 64bd28db8437 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 8c4b07ff2360 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 86f8df362969 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> efa46bdef28d Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> c85db00b7948 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 6c23c537ae10 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 9a825c220b9a Step 31/42 : COPY ./src ./src ---> Using cache ---> 05240fcaedeb Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 3242dd1c9a07 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> a1b699dcdfb4 Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/" ---> Running in 86a5264d88ec './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Removing intermediate container 86a5264d88ec ---> a800becffcdb Step 35/42 : COPY ./data ./data ---> a6ca2a61ad1d Step 36/42 : COPY ./tests ./tests ---> 347a39968130 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> d2f84ab29d58 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 0e03aa1a4711 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> b1491cc145aa Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 857e6a39718f ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 75 input files and 0 errors. ========== Running Performance Test ========== Running H2O-64.inp with 1 threads and 32 ranks... done. Running H2O-64.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.035 0.035 89.137 89.137 qs_mol_dyn_low 1 2.0 0.003 0.003 88.557 88.557 qs_forces 11 3.9 0.001 0.001 88.515 88.515 qs_energies 11 4.9 0.001 0.001 81.960 81.960 scf_env_do_scf 11 5.9 0.002 0.002 70.807 70.807 velocity_verlet 10 3.0 0.002 0.002 57.433 57.433 scf_env_do_scf_inner_loop 108 6.5 0.013 0.013 56.675 56.675 dbcsr_multiply_generic 2286 12.5 0.160 0.160 21.167 21.167 rebuild_ks_matrix 119 8.3 0.001 0.001 21.153 21.153 qs_ks_build_kohn_sham_matrix 119 9.3 0.013 0.013 21.152 21.152 qs_scf_new_mos 108 7.5 0.001 0.001 20.998 20.998 qs_scf_loop_do_ot 108 8.5 0.001 0.001 20.997 20.997 qs_rho_update_rho_low 119 7.7 0.001 0.001 20.421 20.421 calculate_rho_elec 119 8.7 0.966 0.966 20.420 20.420 ot_scf_mini 108 9.5 0.002 0.002 19.633 19.633 qs_ks_update_qs_env 119 7.6 0.001 0.001 19.269 19.269 grid_collocate_task_list 119 9.7 15.560 15.560 15.560 15.560 init_scf_loop 11 6.9 0.000 0.000 13.837 13.837 sum_up_and_integrate 119 10.3 0.001 0.001 13.538 13.538 integrate_v_rspace 119 11.3 0.127 0.127 13.477 13.477 ot_mini 108 10.5 0.001 0.001 12.441 12.441 make_m2s 4572 13.5 0.047 0.047 11.200 11.200 prepare_preconditioner 11 7.9 0.000 0.000 11.055 11.055 make_preconditioner 11 8.9 0.000 0.000 11.055 11.055 grid_integrate_task_list 119 12.3 11.021 11.021 11.021 11.021 make_full_inverse_cholesky 11 9.9 0.025 0.025 9.843 9.843 fft_wrap_pw1pw2 1201 11.6 0.010 0.010 6.926 6.926 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.604 6.604 qs_ot_get_derivative 108 11.5 0.001 0.001 6.595 6.595 multiply_cannon 2286 13.5 0.190 0.190 6.086 6.086 fft_wrap_pw1pw2_140 487 12.2 1.139 1.139 5.945 5.945 ot_diis_step 108 11.5 0.003 0.003 5.843 5.843 make_images 4572 14.5 2.332 2.332 5.803 5.803 dbcsr_make_dense_low 5837 15.5 0.066 0.066 5.780 5.780 make_dense_data 5837 16.5 5.219 5.219 5.700 5.700 multiply_cannon_loop 2286 14.5 0.053 0.053 5.603 5.603 multiply_cannon_multrec 2286 15.5 5.502 5.502 5.549 5.549 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.379 5.379 apply_single 119 13.6 0.000 0.000 5.378 5.378 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.080 5.080 init_scf_run 11 5.9 0.003 0.003 3.953 3.953 scf_env_initial_rho_setup 11 6.9 0.002 0.002 3.950 3.950 density_rs2pw 119 9.7 0.004 0.004 3.895 3.895 dbcsr_copy 2102 12.0 0.236 0.236 3.759 3.759 dbcsr_complete_redistribute 329 12.2 1.750 1.750 3.735 3.735 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.703 3.703 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.686 3.686 qs_ot_get_p 119 10.4 0.001 0.001 3.522 3.522 dbcsr_copy_into_existing 22 7.9 3.460 3.460 3.461 3.461 wfi_extrapolate 11 7.9 0.001 0.001 3.456 3.456 qs_create_task_list 11 7.9 0.000 0.000 3.273 3.273 generate_qs_task_list 11 8.9 1.953 1.953 3.273 3.273 copy_dbcsr_to_fm 153 11.3 0.002 0.002 3.104 3.104 cp_fm_cholesky_invert 11 10.9 2.855 2.855 2.855 2.855 fft3d_s 1202 13.6 2.848 2.848 2.853 2.853 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.850 2.850 cp_fm_cholesky_decompose 22 10.9 2.777 2.777 2.777 2.777 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.512 2.512 potential_pw2rs 119 12.3 0.048 0.048 2.329 2.329 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.301 2.301 dbcsr_data_release 279534 16.0 2.287 2.287 2.287 2.287 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.076 2.076 qs_ot_p2m_diag 50 11.0 0.155 0.155 2.060 2.060 copy_fm_to_dbcsr 176 11.2 0.001 0.001 2.058 2.058 pw_poisson_solve 119 10.3 0.002 0.002 2.043 2.043 qs_ot_get_derivative_taylor 59 13.0 0.002 0.002 2.014 2.014 dbcsr_finalize 5186 13.8 0.103 0.103 1.833 1.833 cp_fm_upper_to_full 72 14.2 1.813 1.813 1.813 1.813 ------------------------------------------------------------------------------- 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 0.009 0.038 50.009 50.026 qs_mol_dyn_low 1 2.0 0.003 0.005 49.870 49.874 qs_forces 11 3.9 0.002 0.002 49.826 49.827 qs_energies 11 4.9 0.001 0.001 46.696 46.699 scf_env_do_scf 11 5.9 0.000 0.003 42.968 42.969 scf_env_do_scf_inner_loop 108 6.5 0.003 0.022 39.561 39.561 velocity_verlet 10 3.0 0.001 0.003 29.838 29.840 rebuild_ks_matrix 119 8.3 0.000 0.001 18.177 18.245 qs_ks_build_kohn_sham_matrix 119 9.3 0.017 0.019 18.176 18.244 qs_ks_update_qs_env 119 7.6 0.001 0.001 16.215 16.277 dbcsr_multiply_generic 2286 12.5 0.076 0.080 15.506 15.632 qs_rho_update_rho_low 119 7.7 0.001 0.001 13.548 13.555 calculate_rho_elec 119 8.7 0.030 0.032 13.547 13.555 sum_up_and_integrate 119 10.3 0.002 0.002 13.215 13.236 integrate_v_rspace 119 11.3 0.004 0.005 13.190 13.212 qs_scf_new_mos 108 7.5 0.001 0.001 12.687 12.777 qs_scf_loop_do_ot 108 8.5 0.001 0.001 12.686 12.776 ot_scf_mini 108 9.5 0.002 0.003 12.005 12.096 multiply_cannon 2286 13.5 0.142 0.161 11.320 11.746 multiply_cannon_loop 2286 14.5 0.106 0.115 10.646 10.899 grid_collocate_task_list 119 9.7 9.125 9.440 9.125 9.440 grid_integrate_task_list 119 12.3 8.750 8.933 8.750 8.933 mp_waitall_1 158411 16.6 8.495 8.865 8.495 8.865 ot_mini 108 10.5 0.001 0.001 6.822 6.923 multiply_cannon_metrocomm3 18288 15.5 0.050 0.053 6.467 6.769 density_rs2pw 119 9.7 0.005 0.006 3.963 4.391 multiply_cannon_multrec 18288 15.5 3.766 3.947 3.778 3.958 potential_pw2rs 119 12.3 0.007 0.007 3.809 3.814 fft_wrap_pw1pw2 1201 11.6 0.018 0.019 3.628 3.678 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.520 3.599 apply_single 119 13.6 0.000 0.001 3.519 3.598 ot_diis_step 108 11.5 0.003 0.003 3.523 3.523 init_scf_loop 11 6.9 0.000 0.000 3.388 3.389 qs_ot_get_derivative 108 11.5 0.001 0.001 3.282 3.369 fft_wrap_pw1pw2_140 487 12.2 0.169 0.183 3.055 3.126 make_m2s 4572 13.5 0.048 0.059 2.887 2.954 transfer_pw2rs 487 13.2 0.007 0.010 2.776 2.780 fft3d_ps 1201 13.6 1.349 1.433 2.617 2.677 transfer_rs2pw 487 10.6 0.008 0.009 2.229 2.669 init_scf_run 11 5.9 0.000 0.006 2.638 2.641 scf_env_initial_rho_setup 11 6.9 0.000 0.005 2.637 2.640 make_images 4572 14.5 0.119 0.126 2.528 2.607 wfi_extrapolate 11 7.9 0.001 0.001 2.392 2.392 mp_waitany 9880 13.7 1.706 2.226 1.706 2.226 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.141 2.150 qs_ot_get_p 119 10.4 0.001 0.001 1.937 2.087 transfer_rs2pw_140 130 11.5 0.247 0.302 1.278 1.719 make_images_data 4572 15.5 0.040 0.047 1.396 1.519 transfer_pw2rs_140 130 13.9 0.489 0.516 1.456 1.473 prepare_preconditioner 11 7.9 0.000 0.000 1.399 1.413 make_preconditioner 11 8.9 0.000 0.000 1.399 1.413 hybrid_alltoall_any 4725 16.4 0.074 0.228 1.252 1.385 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.282 1.299 mp_alltoall_d11v 2130 13.8 0.961 1.219 0.961 1.219 mp_sum_l 11298 13.2 0.769 1.124 0.769 1.124 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.019 1.074 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.013 1.047 mp_alltoall_z22v 1201 15.6 0.959 1.042 0.959 1.042 transfer_pw2rs_50 119 14.3 0.392 0.410 1.014 1.041 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 1.034 1.036 ------------------------------------------------------------------------------- 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=48.37499999999999, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.56, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=11.021, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.502, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.219, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=3.46, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=18.167000000000005, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.125, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.75, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.766, 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="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.495, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.706, 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 0.037 0.037 118.663 118.663 qs_mol_dyn_low 1 2.0 0.003 0.003 117.996 117.996 qs_forces 11 3.9 0.001 0.001 117.953 117.953 qs_energies 11 4.9 0.001 0.001 109.420 109.420 scf_env_do_scf 11 5.9 0.002 0.002 95.509 95.509 scf_env_do_scf_inner_loop 96 6.5 0.012 0.012 79.309 79.309 velocity_verlet 10 3.0 0.002 0.002 75.182 75.182 rebuild_ks_matrix 107 8.3 0.001 0.001 35.597 35.597 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.013 35.596 35.596 qs_rho_update_rho_low 107 7.7 0.001 0.001 34.542 34.542 calculate_rho_elec 107 8.7 0.878 0.878 34.541 34.541 qs_ks_update_qs_env 107 7.6 0.001 0.001 31.930 31.930 grid_collocate_task_list 107 9.7 29.721 29.721 29.721 29.721 sum_up_and_integrate 107 10.3 0.002 0.002 28.146 28.146 integrate_v_rspace 107 11.3 0.098 0.098 28.058 28.058 grid_integrate_task_list 107 12.3 25.623 25.623 25.623 25.623 dbcsr_multiply_generic 1966 12.4 0.140 0.140 20.362 20.362 qs_scf_new_mos 96 7.5 0.001 0.001 20.334 20.334 qs_scf_loop_do_ot 96 8.5 0.001 0.001 20.334 20.334 ot_scf_mini 96 9.5 0.002 0.002 19.023 19.023 init_scf_loop 11 6.9 0.000 0.000 16.046 16.046 ot_mini 96 10.5 0.001 0.001 11.857 11.857 prepare_preconditioner 11 7.9 0.000 0.000 11.582 11.582 make_preconditioner 11 8.9 0.000 0.000 11.582 11.582 make_m2s 3932 13.4 0.042 0.042 10.470 10.470 make_full_inverse_cholesky 11 9.9 0.028 0.028 10.373 10.373 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.251 7.251 fft_wrap_pw1pw2 1081 11.6 0.010 0.010 6.883 6.883 qs_ot_get_derivative 96 11.5 0.001 0.001 6.271 6.271 multiply_cannon 1966 13.4 0.215 0.215 6.231 6.231 init_scf_run 11 5.9 0.003 0.003 5.959 5.959 scf_env_initial_rho_setup 11 6.9 0.002 0.002 5.955 5.955 fft_wrap_pw1pw2_140 439 12.2 1.017 1.017 5.940 5.940 multiply_cannon_loop 1966 14.4 0.052 0.052 5.684 5.684 multiply_cannon_multrec 1966 15.4 5.582 5.582 5.631 5.631 ot_diis_step 96 11.5 0.003 0.003 5.583 5.583 make_images 3932 14.4 2.160 2.160 5.520 5.520 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 5.284 5.284 apply_single 107 13.6 0.000 0.000 5.284 5.284 dbcsr_make_dense_low 4961 15.5 0.072 0.072 5.283 5.283 wfi_extrapolate 11 7.9 0.001 0.001 5.202 5.202 make_dense_data 4961 16.5 4.726 4.726 5.198 5.198 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.632 4.632 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.584 4.584 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.215 4.215 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.947 3.947 density_rs2pw 107 9.7 0.004 0.004 3.943 3.943 dbcsr_copy 1855 11.9 0.244 0.244 3.918 3.918 dbcsr_complete_redistribute 317 12.2 1.833 1.833 3.798 3.798 qs_create_task_list 11 7.9 0.000 0.000 3.739 3.739 generate_qs_task_list 11 8.9 2.396 2.396 3.739 3.739 qs_ot_get_p 107 10.4 0.001 0.001 3.661 3.661 dbcsr_copy_into_existing 22 7.9 3.617 3.617 3.617 3.617 copy_dbcsr_to_fm 147 11.2 0.003 0.003 3.180 3.180 cp_fm_cholesky_decompose 22 10.9 3.058 3.058 3.058 3.058 cp_fm_cholesky_invert 11 10.9 2.975 2.975 2.975 2.975 fft3d_s 1082 13.6 2.926 2.926 2.932 2.932 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.604 2.604 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.493 2.493 qs_ot_p2m_diag 44 11.0 0.136 0.136 2.397 2.397 ------------------------------------------------------------------------------- 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 0.009 0.034 80.587 80.604 qs_mol_dyn_low 1 2.0 0.003 0.005 80.443 80.447 qs_forces 11 3.9 0.002 0.002 80.391 80.392 qs_energies 11 4.9 0.001 0.001 75.054 75.057 scf_env_do_scf 11 5.9 0.001 0.002 69.374 69.374 scf_env_do_scf_inner_loop 96 6.5 0.003 0.023 64.028 64.029 velocity_verlet 10 3.0 0.001 0.003 48.915 48.917 rebuild_ks_matrix 107 8.3 0.001 0.001 34.539 34.620 qs_ks_build_kohn_sham_matrix 107 9.3 0.016 0.018 34.538 34.620 qs_ks_update_qs_env 107 7.6 0.001 0.005 30.431 30.510 sum_up_and_integrate 107 10.3 0.002 0.002 29.704 29.753 integrate_v_rspace 107 11.3 0.004 0.005 29.678 29.727 qs_rho_update_rho_low 107 7.7 0.001 0.001 27.876 27.884 calculate_rho_elec 107 8.7 0.027 0.029 27.876 27.883 grid_integrate_task_list 107 12.3 23.661 24.833 23.661 24.833 grid_collocate_task_list 107 9.7 22.836 23.463 22.836 23.463 dbcsr_multiply_generic 1966 12.4 0.073 0.079 15.093 15.249 qs_scf_new_mos 96 7.5 0.001 0.001 12.136 12.258 qs_scf_loop_do_ot 96 8.5 0.001 0.001 12.135 12.258 ot_scf_mini 96 9.5 0.002 0.003 11.479 11.592 multiply_cannon 1966 13.4 0.136 0.152 11.018 11.431 multiply_cannon_loop 1966 14.4 0.098 0.103 10.340 10.736 mp_waitall_1 136719 16.5 8.262 8.718 8.262 8.718 ot_mini 96 10.5 0.001 0.001 6.715 6.832 multiply_cannon_metrocomm3 15728 15.4 0.044 0.050 6.316 6.697 init_scf_loop 11 6.9 0.000 0.000 5.324 5.325 density_rs2pw 107 9.7 0.005 0.005 4.589 5.290 init_scf_run 11 5.9 0.000 0.006 4.479 4.479 scf_env_initial_rho_setup 11 6.9 0.000 0.005 4.479 4.479 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.270 4.287 wfi_extrapolate 11 7.9 0.001 0.001 4.105 4.105 multiply_cannon_multrec 15728 15.4 3.633 3.762 3.645 3.774 potential_pw2rs 107 12.3 0.006 0.007 3.686 3.698 transfer_rs2pw 439 10.6 0.007 0.008 2.973 3.690 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.452 3.557 apply_single 107 13.6 0.000 0.000 3.451 3.557 fft_wrap_pw1pw2 1081 11.6 0.016 0.019 3.425 3.500 ot_diis_step 96 11.5 0.003 0.003 3.484 3.496 mp_waitany 8968 13.7 2.645 3.455 2.645 3.455 mp_alltoall_d11v 1998 13.7 2.650 3.383 2.650 3.383 qs_ot_get_derivative 96 11.5 0.001 0.001 3.200 3.313 rs_gather_matrices 107 12.3 0.085 0.097 2.279 3.005 fft_wrap_pw1pw2_140 439 12.2 0.160 0.169 2.873 2.965 make_m2s 3932 13.4 0.044 0.054 2.793 2.885 transfer_rs2pw_140 118 11.5 0.186 0.208 2.085 2.805 transfer_pw2rs 439 13.2 0.006 0.007 2.746 2.750 make_images 3932 14.4 0.109 0.113 2.465 2.560 fft3d_ps 1081 13.6 1.260 1.339 2.468 2.557 qs_ot_get_p 107 10.4 0.001 0.001 1.637 1.757 ------------------------------------------------------------------------------- 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=49.39399999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=29.721, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.623, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.582, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.726, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=3.617, 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=19.545, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.836, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=23.661, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.633, 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="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=2.65, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.262, 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 0.224 0.224 141.775 141.775 qs_energies 1 2.0 0.000 0.000 140.937 140.937 scf_env_do_scf 1 3.0 0.000 0.000 139.687 139.687 qs_ks_update_qs_env 8 5.0 0.000 0.000 134.589 134.589 rebuild_ks_matrix 7 6.0 0.000 0.000 134.529 134.529 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 134.529 134.529 hfx_ks_matrix 7 8.0 0.000 0.000 125.304 125.304 integrate_four_center 7 9.0 1.616 1.616 125.246 125.246 integrate_four_center_main 7 10.0 0.292 0.292 110.646 110.646 integrate_four_center_bin 448 11.0 110.354 110.354 110.354 110.354 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 79.431 79.431 init_scf_loop 1 4.0 0.000 0.000 60.247 60.247 integrate_four_center_load 7 10.0 0.001 0.001 12.686 12.686 hfx_load_balance 1 11.0 0.013 0.013 12.685 12.685 hfx_load_balance_bin 1 12.0 6.332 6.332 6.332 6.332 hfx_load_balance_count 1 12.0 6.323 6.323 6.323 6.323 qs_vxc_create 14 8.0 0.000 0.000 3.492 3.492 xc_vxc_pw_create 14 9.0 0.120 0.120 3.492 3.492 ------------------------------------------------------------------------------- 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 0.212 0.248 137.811 137.830 qs_energies 1 2.0 0.000 0.000 137.383 137.395 scf_env_do_scf 1 3.0 0.000 0.000 136.947 136.948 qs_ks_update_qs_env 8 5.0 0.000 0.000 134.504 134.505 rebuild_ks_matrix 7 6.0 0.000 0.000 134.490 134.491 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 134.490 134.491 hfx_ks_matrix 7 8.0 0.000 0.000 128.196 128.199 integrate_four_center 7 9.0 0.061 0.352 128.185 128.187 integrate_four_center_main 7 10.0 0.004 0.004 108.073 114.744 integrate_four_center_bin 448 11.0 108.069 114.741 108.069 114.741 scf_env_do_scf_inner_loop 7 4.0 0.000 0.002 81.837 81.838 init_scf_loop 1 4.0 0.000 0.000 55.108 55.108 mp_sync 56 11.2 6.693 13.469 6.693 13.469 integrate_four_center_load 7 10.0 0.000 0.000 12.696 12.698 hfx_load_balance 1 11.0 0.001 0.001 12.696 12.698 hfx_load_balance_bin 1 12.0 6.294 6.390 6.294 6.390 hfx_load_balance_count 1 12.0 6.266 6.326 6.266 6.326 ------------------------------------------------------------------------------- Plot: name="H2O-hyb_timings_32omp", title="Timings of H2O-hyb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32omp", name="rest", label="rest", y=16.634000000000015, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=110.354, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.332, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.323, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.616, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.292, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.224, 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=10.211999999999989, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=108.069, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.294, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.266, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.061, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.004, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.212, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=6.693, yerr=0.0 Running GW_PBE_4benzene.inp with 1 threads and 32 ranks... done. Running GW_PBE_4benzene.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.017 0.017 86.039 86.039 qs_energies 1 2.0 0.000 0.000 85.642 85.642 mp2_main 1 3.0 0.000 0.000 82.590 82.590 mp2_gpw_main 1 4.0 0.000 0.000 82.485 82.485 rpa_ri_compute_en 1 5.0 0.000 0.000 78.908 78.908 rpa_num_int 1 6.0 0.001 0.001 78.902 78.902 compute_mat_P_omega 1 7.0 0.004 0.004 69.288 69.288 compute_mat_P_omega_contract 10 8.0 9.099 9.099 69.085 69.085 dbt_total 2336 9.6 0.015 0.015 55.104 55.104 dbt_contract 787 11.0 0.045 0.045 47.309 47.309 dbt_tas_total 1149 12.2 0.293 0.293 45.777 45.777 dbt_tas_multiply 807 12.1 0.002 0.002 44.427 44.427 dbt_tas_dbm 807 14.1 0.003 0.003 37.302 37.302 dbm_multiply 807 16.1 37.293 37.293 37.293 37.293 dbt_tas_mm_1N 524 15.1 0.002 0.002 29.159 29.159 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 27.443 27.443 compute_mat_P_omega_calc_M_occ 250 9.0 9.126 9.126 18.456 18.456 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.807 7.807 dbt_tas_mm_2 251 15.0 0.002 0.002 6.598 6.598 dbt_copy 1103 10.7 0.135 0.135 6.424 6.424 compute_QP_energies 1 7.0 0.000 0.000 5.348 5.348 compute_self_energy_cubic_gw 1 8.0 0.055 0.055 5.347 5.347 contract_cubic_gw 21 9.0 0.000 0.000 4.264 4.264 dbt_tas_reserve_blocks_index 3261 14.3 0.493 0.493 4.171 4.171 dbm_reserve_blocks 3628 15.3 3.745 3.745 3.745 3.745 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.570 3.570 dbt_reserve_blocks_index 2280 13.1 0.064 0.064 3.161 3.161 dbt_reserve_blocks_index_array 2222 12.2 0.010 0.010 3.104 3.104 scf_env_do_scf 1 3.0 0.000 0.000 2.935 2.935 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.935 2.935 dbt_crop 1042 12.0 1.615 1.615 2.758 2.758 dbt_tas_copy 574 11.4 1.449 1.449 2.531 2.531 convert_to_new_pgrid 2421 14.1 0.142 0.142 2.499 2.499 dbm_copy 1614 15.1 2.357 2.357 2.357 2.357 dbt_tas_reshape 367 15.0 0.033 0.033 2.168 2.168 dbt_reshape 278 11.9 1.210 1.210 2.142 2.142 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.746 1.746 ------------------------------------------------------------------------------- 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 0.008 0.035 39.071 39.083 qs_energies 1 2.0 0.000 0.000 38.914 38.917 mp2_main 1 3.0 0.000 0.000 37.818 37.820 mp2_gpw_main 1 4.0 0.000 0.000 37.655 37.658 rpa_ri_compute_en 1 5.0 0.000 0.000 36.250 36.253 rpa_num_int 1 6.0 0.000 0.002 36.250 36.252 dbt_total 2336 9.6 0.018 0.018 31.969 31.981 compute_mat_P_omega 1 7.0 0.001 0.006 30.838 30.888 compute_mat_P_omega_contract 10 8.0 0.481 0.494 30.668 30.672 dbt_contract 787 11.0 0.045 0.048 23.449 23.454 dbt_tas_total 1149 12.2 0.090 0.097 20.699 20.712 dbt_tas_multiply 807 12.1 0.002 0.004 20.594 20.596 dbt_tas_dbm 807 14.1 0.003 0.004 15.034 15.045 dbm_multiply 807 16.1 12.175 13.011 12.175 13.011 compute_mat_P_omega_calc_M_occ 250 9.0 0.451 0.464 9.020 9.021 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.913 8.914 dbt_copy 1149 10.8 0.016 0.017 7.348 7.556 dbt_reshape 1136 11.8 2.994 3.167 7.009 7.221 dbt_tas_mm_2 251 15.0 0.001 0.002 7.095 7.096 mp_sync 8688 11.6 5.414 6.466 5.414 6.466 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 6.211 6.211 dbt_tas_mm_1N 524 15.1 0.002 0.002 5.557 5.937 compute_QP_energies 1 7.0 0.000 0.000 3.426 3.427 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 3.426 3.426 mp_waitall_2 3812 15.3 2.971 3.238 2.971 3.238 dbt_communicate_buffer 1136 12.8 0.053 0.057 2.961 3.135 contract_cubic_gw 21 9.0 0.000 0.000 2.711 2.712 dbt_reserve_blocks_index 2887 13.1 0.082 0.088 2.199 2.380 dbt_reserve_blocks_index_array 2829 12.2 0.009 0.009 2.188 2.367 dbt_tas_reserve_blocks_index 3347 14.5 0.437 0.473 2.172 2.350 dbm_reserve_blocks 3752 15.4 1.844 1.989 1.844 1.989 dbt_crop 1042 12.0 1.044 1.145 1.736 1.919 mp2_ri_gpw_compute_in 1 5.0 0.004 0.006 1.392 1.392 dbt_tas_replicate 405 14.1 0.569 0.743 1.227 1.306 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.279 1.282 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.189 1.193 parallel_gemm_fm 105 8.4 0.000 0.000 1.175 1.189 parallel_gemm_fm_cosma 105 9.4 1.175 1.189 1.175 1.189 convert_to_new_pgrid 2421 14.1 0.030 0.033 1.004 1.110 dbm_copy 1608 15.1 0.968 1.072 0.968 1.072 scf_env_do_scf 1 3.0 0.000 0.000 1.039 1.039 scf_env_do_scf_inner_loop 17 4.0 0.001 0.003 1.039 1.039 mp_max_i 2009 9.8 0.724 0.941 0.724 0.941 compute_W_cubic_GW 10 7.0 0.001 0.001 0.891 0.900 dbm_add 807 14.1 0.734 0.801 0.734 0.801 ------------------------------------------------------------------------------- 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=23.209000000000003, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=37.293, 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=9.126, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=9.099, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.745, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.357, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.21, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=11.773, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=12.175, 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=0.451, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.481, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.844, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.968, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.994, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.414, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.971, 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 0.023 0.023 299.548 299.548 qs_forces 1 2.0 0.000 0.000 298.948 298.948 rebuild_ks_matrix 7 6.6 0.000 0.000 297.393 297.393 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 297.393 297.393 hfx_ks_matrix 7 8.6 0.000 0.000 295.091 295.091 hfx_ri_update_ks 7 9.6 0.000 0.000 250.398 250.398 hfx_ri_update_ks_Pmat 7 10.6 36.017 36.017 250.394 250.394 dbt_total 849 11.0 0.007 0.007 233.969 233.969 qs_energies 1 3.0 0.000 0.000 224.035 224.035 scf_env_do_scf 1 4.0 0.001 0.001 223.676 223.676 qs_ks_update_qs_env 8 6.0 0.000 0.000 222.535 222.535 dbt_contract 207 12.4 0.051 0.051 212.373 212.373 dbt_tas_total 369 13.4 1.669 1.669 211.137 211.137 dbt_tas_multiply 216 13.5 0.001 0.001 206.654 206.654 dbt_tas_dbm 216 15.5 0.001 0.001 194.151 194.151 dbm_multiply 216 17.5 194.147 194.147 194.147 194.147 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 186.475 186.475 dbt_tas_mm_2 91 16.5 0.001 0.001 177.763 177.763 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 135.666 135.666 init_scf_loop 2 5.0 0.000 0.000 88.008 88.008 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 74.862 74.862 hfx_ri_update_forces 1 7.0 1.674 1.674 44.689 44.689 hfx_ri_forces_Pmat_3c 1 8.0 5.088 5.088 26.377 26.377 dbt_copy 423 11.8 0.078 0.078 17.105 17.105 precalc_derivatives 1 8.0 2.332 2.332 13.969 13.969 dbt_reshape 132 13.2 7.424 7.424 11.603 11.603 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 11.488 11.488 dbt_tas_mm_3T 77 17.1 0.000 0.000 11.293 11.293 dbt_tas_reserve_blocks_index 1323 15.4 1.031 1.031 8.319 8.319 build_3c_derivatives 3 9.0 2.878 2.878 7.752 7.752 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.530 7.530 dbm_reserve_blocks 1491 16.2 7.516 7.516 7.516 7.516 dbt_reserve_blocks_index 846 14.4 0.117 0.117 6.400 6.400 dbt_reserve_blocks_index_array 816 13.5 0.008 0.008 6.305 6.305 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-HFX_H2O-32_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.041 59.460 59.473 qs_forces 1 2.0 0.000 0.000 59.252 59.253 rebuild_ks_matrix 7 6.6 0.000 0.000 58.366 58.367 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 58.366 58.367 hfx_ks_matrix 7 8.6 0.000 0.000 57.186 57.193 dbt_total 849 11.0 0.007 0.007 50.874 50.899 dbt_contract 207 12.4 0.029 0.031 37.854 37.863 dbt_tas_total 369 13.4 0.063 0.151 33.696 33.710 dbt_tas_multiply 216 13.5 0.001 0.001 33.147 33.155 hfx_ri_update_ks 7 9.6 0.000 0.000 31.279 31.279 hfx_ri_update_ks_Pmat 7 10.6 1.461 1.522 31.273 31.274 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 29.802 29.803 qs_energies 1 3.0 0.000 0.000 29.440 29.440 scf_env_do_scf 1 4.0 0.000 0.001 29.267 29.267 qs_ks_update_qs_env 8 6.0 0.000 0.000 28.565 28.566 dbt_tas_dbm 216 15.5 0.001 0.001 25.937 25.943 hfx_ri_update_forces 1 7.0 0.067 0.070 25.906 25.913 dbm_multiply 216 17.5 23.543 24.495 23.543 24.495 hfx_ri_forces_Pmat_3c 1 8.0 0.196 0.214 18.100 18.125 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 16.467 16.467 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 13.586 13.587 init_scf_loop 2 5.0 0.000 0.000 12.798 12.798 dbt_copy 539 12.5 0.014 0.017 11.610 11.871 dbt_tas_mm_2 91 16.5 0.001 0.001 11.141 11.147 dbt_reshape 393 13.9 3.994 4.082 8.139 8.374 dbt_tas_mm_3T 77 17.1 0.000 0.000 7.415 7.981 mp_sync 2901 12.8 5.818 6.831 5.818 6.831 precalc_derivatives 1 8.0 0.099 0.108 6.333 6.333 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.850 5.850 dbt_tas_mm_3N 37 15.4 0.000 0.000 5.447 5.557 dbt_tas_reserve_blocks_index 1471 15.8 0.895 0.922 3.790 4.058 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 4.050 4.050 mp_waitall_2 1318 16.2 3.677 3.849 3.677 3.849 dbm_reserve_blocks 1641 16.6 3.158 3.422 3.158 3.422 dbt_reserve_blocks_index 1107 14.8 0.129 0.134 3.117 3.338 dbt_reserve_blocks_index_array 1077 13.9 0.006 0.006 3.086 3.309 build_3c_derivatives 3 9.0 0.238 0.398 3.151 3.159 dbt_crop 372 13.7 2.039 2.086 2.977 3.086 dbt_communicate_buffer 393 14.9 0.013 0.014 2.584 2.732 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 2.202 2.205 dbt_tas_replicate 170 15.1 0.777 0.812 2.011 2.069 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.958 1.960 convert_to_new_pgrid 648 15.5 0.043 0.089 1.660 1.883 dbt_tas_copy 146 12.6 0.840 0.873 1.576 1.736 dbm_copy 452 16.3 1.454 1.694 1.454 1.694 dbt_split_blocks_generic 104 12.7 0.204 0.231 1.567 1.605 mp_cart_create 2034 16.9 1.254 1.361 1.256 1.363 dbt_distribution_new_expert 535 14.4 0.006 0.006 1.283 1.336 dbt_tas_communicate_buffer 370 16.3 0.012 0.013 1.241 1.309 dbt_pgrid_create_expert 659 15.3 0.002 0.002 1.177 1.291 ------------------------------------------------------------------------------- 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=49.35600000000002, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=194.147, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=36.017, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.516, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=7.424, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=5.088, 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=17.613000000000007, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=23.543, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.461, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.158, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.994, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.196, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=5.818, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.677, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.018 0.018 217.073 217.073 qs_energies 1 2.0 0.000 0.000 216.805 216.805 mp2_main 1 3.0 0.000 0.000 211.429 211.429 mp2_gpw_main 1 4.0 0.002 0.002 210.961 210.961 mp2_ri_gpw_compute_in 1 5.0 0.483 0.483 161.733 161.733 mp2_ri_gpw_compute_in_loop 1 6.0 0.013 0.013 153.637 153.637 mp2_eri_3c_integrate_gpw 2656 7.0 0.016 0.016 123.275 123.275 integrate_v_rspace 2666 8.0 0.775 0.775 110.239 110.239 grid_integrate_task_list 2666 9.0 107.305 107.305 107.305 107.305 mp2_ri_gpw_compute_en 1 5.0 0.085 0.085 49.201 49.201 mp2_ri_gpw_compute_en_RI_loop 1 6.0 11.021 11.021 47.161 47.161 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.206 2.206 27.977 27.977 local_gemm 2080 8.0 25.771 25.771 25.771 25.771 dbcsr_multiply_generic 5322 8.0 0.210 0.210 22.916 22.916 ao_to_mo_and_store_B_mult_1 2656 7.0 0.012 0.012 22.892 22.892 multiply_cannon 5322 9.0 0.568 0.568 11.870 11.870 calculate_wavefunction 2656 8.0 8.061 8.061 11.793 11.793 fft_wrap_pw1pw2 53228 10.4 0.110 0.110 10.625 10.625 multiply_cannon_loop 5322 10.0 0.221 0.221 10.293 10.293 multiply_cannon_multrec 5322 11.0 8.530 8.530 8.571 8.571 make_m2s 10644 9.0 0.064 0.064 8.541 8.541 make_images 10644 10.0 3.244 3.244 8.110 8.110 get_2c_integrals 1 6.0 0.000 0.000 7.612 7.612 fft_wrap_pw1pw2_20 21271 11.4 0.626 0.626 7.493 7.493 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.764 2.764 7.311 7.311 compute_2c_integrals 1 7.0 0.028 0.028 7.122 7.122 compute_2c_integrals_loop_lm 1 8.0 0.013 0.013 7.079 7.079 mp2_eri_2c_integrate_gpw 1 9.0 0.884 0.884 7.066 7.066 fft3d_s 53229 12.4 6.034 6.034 6.067 6.067 mp2_ri_gpw_compute_en_ener 2080 7.0 5.910 5.910 5.910 5.910 copy_dbcsr_to_fm 2679 8.0 0.031 0.031 5.352 5.352 scf_env_do_scf 1 3.0 0.000 0.000 4.890 4.890 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.890 4.890 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.035 41.648 41.661 qs_energies 1 2.0 0.000 0.000 41.483 41.484 mp2_main 1 3.0 0.000 0.001 39.248 39.248 mp2_gpw_main 1 4.0 0.001 0.003 39.134 39.134 mp2_ri_gpw_compute_in 1 5.0 0.044 0.046 20.136 20.359 mp2_ri_gpw_compute_en 1 5.0 0.265 0.272 18.920 19.219 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 18.634 18.858 mp2_ri_gpw_compute_en_RI_loop 1 6.0 2.773 3.089 17.777 17.790 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 16.115 16.281 integrate_v_rspace 93 8.1 0.126 0.138 15.998 16.154 grid_integrate_task_list 93 9.1 15.645 15.802 15.645 15.802 mp2_ri_gpw_compute_en_expansio 65 7.0 0.124 0.137 11.799 12.004 local_gemm 65 8.0 11.675 11.885 11.675 11.885 mp2_ri_gpw_compute_en_comm 17 7.0 0.084 0.106 2.709 3.424 mp_sendrecv_dm3 1054 8.0 2.132 2.876 2.132 2.876 dbcsr_multiply_generic 176 8.0 0.009 0.010 2.142 2.381 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 2.124 2.361 scf_env_do_scf 1 3.0 0.000 0.001 2.087 2.088 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 2.087 2.087 get_2c_integrals 1 6.0 0.005 0.014 1.440 1.457 multiply_cannon 176 9.0 0.021 0.022 1.222 1.290 multiply_cannon_loop 176 10.0 0.002 0.002 1.157 1.224 compute_2c_integrals 1 7.0 0.003 0.006 1.052 1.067 make_m2s 352 9.0 0.003 0.004 0.877 1.050 make_images 352 10.0 0.055 0.056 0.863 1.037 multiply_cannon_multrec 246 11.0 0.979 1.022 0.985 1.028 qs_scf_new_mos 10 5.0 0.000 0.000 0.992 1.002 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 0.921 0.958 mp2_eri_2c_integrate_gpw 1 9.0 0.235 0.245 0.920 0.957 eigensolver 11 5.8 0.001 0.001 0.929 0.930 ------------------------------------------------------------------------------- Plot: name="RI-MP2_ammonia_timings_32omp", title="Timings of RI-MP2_ammonia with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="rest", label="rest", y=56.38499999999996, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=107.305, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=25.771, 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=11.021, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.53, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.061, 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=8.444000000000003, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=15.645, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=11.675, 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=2.773, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.979, 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="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=2.132, 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 0.128 0.128 141.152 141.152 qs_energies 1 2.0 0.000 0.000 139.725 139.725 scf_env_do_scf 1 3.0 0.000 0.000 131.520 131.520 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 131.520 131.520 qs_ks_update_qs_env 15 5.0 0.000 0.000 57.929 57.929 rebuild_ks_matrix 15 6.0 0.000 0.000 57.304 57.304 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 57.304 57.304 qs_scf_new_mos 15 5.0 0.000 0.000 45.094 45.094 qs_vxc_create 15 8.0 0.000 0.000 40.085 40.085 eigensolver 15 6.0 0.002 0.002 36.254 36.254 calculate_dispersion_nonloc 15 9.0 7.162 7.162 34.351 34.351 fft_wrap_pw1pw2 1086 10.0 0.014 0.014 29.015 29.015 cp_fm_diag_elpa 15 7.0 0.000 0.000 24.263 24.263 cp_fm_diag_elpa_base 15 8.0 21.473 21.473 24.262 24.262 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.483 21.483 calculate_rho_elec 16 6.0 0.273 0.273 21.483 21.483 fft_wrap_pw1pw2_150 765 11.0 6.945 6.945 20.814 20.814 grid_collocate_task_list 16 7.0 19.541 19.541 19.541 19.541 sum_up_and_integrate 15 8.0 0.000 0.000 15.734 15.734 integrate_v_rspace 15 9.0 0.030 0.030 15.718 15.718 grid_integrate_task_list 15 10.0 14.922 14.922 14.922 14.922 fft3d_s 1087 12.0 10.244 10.244 10.253 10.253 cp_fm_cholesky_restore 45 7.0 9.320 9.320 9.320 9.320 gspace_mixing 14 5.0 0.192 0.192 8.001 8.001 fft_wrap_pw1pw2_200 197 11.3 1.945 1.945 7.953 7.953 pw_scatter_s 585 12.1 7.603 7.603 7.603 7.603 broyden_mixing 14 6.0 7.283 7.283 7.284 7.284 copy_dbcsr_to_fm 16 5.9 0.001 0.001 6.413 6.413 dbcsr_complete_redistribute 46 8.3 2.451 2.451 5.999 5.999 xc_vxc_pw_create 15 9.0 0.251 0.251 5.733 5.733 cp_fm_upper_to_full 30 8.0 5.458 5.458 5.458 5.458 vdW_energy 15 10.0 4.818 4.818 4.818 4.818 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.778 4.778 xc_pw_derive 90 11.0 0.001 0.001 3.902 3.902 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 3.259 3.259 init_scf_run 1 3.0 0.000 0.000 2.910 2.910 calculate_dm_sparse 15 6.0 0.023 0.023 2.905 2.905 ------------------------------------------------------------------------------- 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 0.033 67.729 67.742 qs_energies 1 2.0 0.000 0.000 67.381 67.389 scf_env_do_scf 1 3.0 0.000 0.001 62.812 62.812 scf_env_do_scf_inner_loop 15 4.0 0.001 0.004 62.812 62.812 qs_ks_update_qs_env 15 5.0 0.000 0.000 27.839 27.851 rebuild_ks_matrix 15 6.0 0.000 0.000 27.792 27.804 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 27.792 27.804 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.394 20.401 calculate_rho_elec 16 6.0 0.007 0.007 20.394 20.401 grid_collocate_task_list 16 7.0 19.021 19.237 19.021 19.237 sum_up_and_integrate 15 8.0 0.000 0.001 16.372 16.422 integrate_v_rspace 15 9.0 0.001 0.001 16.361 16.413 grid_integrate_task_list 15 10.0 15.128 15.295 15.128 15.295 qs_scf_new_mos 15 5.0 0.000 0.001 15.016 15.043 eigensolver 15 6.0 0.002 0.002 13.726 13.750 qs_vxc_create 15 8.0 0.001 0.001 10.926 10.941 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.669 9.676 cp_fm_diag_elpa_base 15 8.0 9.505 9.535 9.665 9.667 calculate_dispersion_nonloc 15 9.0 0.964 1.065 8.721 8.741 fft_wrap_pw1pw2 1086 10.0 0.022 0.024 8.256 8.329 fft3d_ps 1086 12.0 3.070 3.283 6.149 6.332 fft_wrap_pw1pw2_150 765 11.0 0.157 0.177 5.310 5.351 cp_fm_cholesky_restore 45 7.0 3.872 3.928 3.872 3.928 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.930 2.931 fft_wrap_pw1pw2_200 197 11.3 0.127 0.138 2.799 2.877 mp_alltoall_z22v 1086 14.0 2.333 2.858 2.333 2.858 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.552 2.828 xc_vxc_pw_create 15 9.0 0.020 0.027 2.205 2.231 x_to_yz 585 13.1 0.396 0.420 1.629 1.815 build_core_ppnl 1 5.0 1.576 1.764 1.576 1.764 yz_to_x 501 12.9 0.323 0.387 1.423 1.703 xc_pw_derive 90 11.0 0.001 0.001 1.511 1.600 vdW_energy 15 10.0 1.532 1.583 1.532 1.583 init_scf_run 1 3.0 0.000 0.001 1.408 1.408 density_rs2pw 16 7.0 0.001 0.001 1.181 1.387 ------------------------------------------------------------------------------- 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=65.65199999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=21.473, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.541, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.922, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.244, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=9.32, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=17.132999999999996, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=9.505, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.021, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=15.128, 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=3.872, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=3.07, 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 0.088 0.088 334.820 334.820 qs_energies 1 2.0 0.000 0.000 334.667 334.667 ls_scf 1 3.0 0.000 0.000 333.166 333.166 ls_scf_main 1 4.0 0.003 0.003 321.926 321.926 density_matrix_trs4 11 5.0 0.015 0.015 217.490 217.490 arnoldi_extremal 12 6.1 0.000 0.000 107.598 107.598 arnoldi_normal_ev 12 7.1 0.064 0.064 107.598 107.598 build_subspace 23 8.1 0.097 0.097 105.362 105.362 dbcsr_matrix_vector_mult 652 9.0 0.311 0.311 105.222 105.222 dbcsr_matrix_vector_mult_local 652 10.0 103.182 103.182 103.191 103.191 ls_scf_dm_to_ks 11 5.0 0.000 0.000 97.696 97.696 matrix_ls_to_qs 11 6.0 0.000 0.000 93.994 93.994 dbcsr_multiply_generic 185 6.1 0.973 0.973 90.336 90.336 multiply_cannon 185 7.1 0.529 0.529 50.482 50.482 dbcsr_complete_redistribute 23 7.5 35.329 35.329 50.452 50.452 dbcsr_copy_into_existing 11 7.0 48.355 48.355 48.355 48.355 matrix_decluster 11 7.0 0.000 0.000 45.637 45.637 multiply_cannon_loop 185 8.1 0.281 0.281 37.013 37.013 make_m2s 370 7.1 0.041 0.041 33.909 33.909 make_images 370 8.1 14.842 14.842 30.656 30.656 multiply_cannon_multrec 185 9.1 27.904 27.904 27.988 27.988 dbcsr_finalize 646 7.5 0.426 0.426 20.048 20.048 dbcsr_merge_all 597 8.5 2.952 2.952 18.372 18.372 tree_to_linear_d 110 9.4 13.597 13.597 13.597 13.597 dbcsr_sort_indices 804 10.1 13.250 13.250 13.250 13.250 setup_rec_index_2d 370 8.1 12.724 12.724 12.724 12.724 quick_finalize 395 10.0 0.481 0.481 11.436 11.436 dbcsr_special_finalize 370 9.1 0.002 0.002 10.548 10.548 ls_scf_init_scf 1 4.0 0.000 0.000 10.437 10.437 ls_scf_init_matrix_S 1 5.0 0.000 0.000 9.958 9.958 dbcsr_dot_sd 144 6.3 9.187 9.187 9.188 9.188 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 8.988 8.988 calculate_norms 370 9.1 8.744 8.744 8.744 8.744 dbcsr_frobenius_norm 142 6.1 7.349 7.349 7.350 7.350 matrix_qs_to_ls 12 5.1 0.000 0.000 7.141 7.141 matrix_cluster 12 6.1 0.000 0.000 7.141 7.141 ------------------------------------------------------------------------------- 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 0.015 0.032 86.483 86.495 qs_energies 1 2.0 0.000 0.000 86.356 86.356 ls_scf 1 3.0 0.000 0.000 86.299 86.300 ls_scf_main 1 4.0 0.001 0.009 83.095 83.096 density_matrix_trs4 11 5.0 0.007 0.021 79.933 79.985 dbcsr_multiply_generic 185 6.1 0.073 0.094 75.717 76.010 multiply_cannon 185 7.1 0.039 0.042 62.835 63.484 multiply_cannon_loop 185 8.1 0.148 0.158 59.889 61.337 multiply_cannon_multrec 1480 9.1 35.583 37.266 36.020 37.713 mp_waitall_1 11936 10.3 20.569 23.427 20.569 23.427 multiply_cannon_metrocomm3 1480 9.1 0.016 0.018 15.872 18.733 make_m2s 370 7.1 0.041 0.043 8.601 8.648 make_images 370 8.1 0.691 0.731 8.447 8.491 calculate_norms 2960 9.1 6.653 6.933 6.653 6.933 make_images_data 370 9.1 0.010 0.011 3.898 4.114 mp_sum_l 1199 5.3 3.152 3.789 3.152 3.789 hybrid_alltoall_any 393 9.9 0.302 1.898 3.480 3.703 arnoldi_extremal 12 6.1 0.000 0.000 3.129 3.139 arnoldi_normal_ev 12 7.1 0.002 0.009 3.128 3.139 build_subspace 23 8.1 0.024 0.030 3.012 3.014 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.001 2.286 2.803 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.695 2.763 dbcsr_complete_redistribute 23 7.5 1.432 1.494 2.486 2.600 dbcsr_matrix_vector_mult 652 9.0 0.017 0.067 2.501 2.592 matrix_ls_to_qs 11 6.0 0.000 0.000 2.385 2.508 ls_scf_init_scf 1 4.0 0.000 0.000 2.407 2.408 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.382 2.387 make_images_pack 370 9.1 2.160 2.352 2.163 2.356 matrix_decluster 11 7.0 0.000 0.000 2.237 2.355 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.002 2.170 2.174 dbcsr_matrix_vector_mult_local 652 10.0 1.964 2.084 1.966 2.086 multiply_cannon_metrocomm1 1480 9.1 0.007 0.014 1.155 1.920 buffer_matrices_ensure_size 370 8.1 1.762 1.915 1.762 1.915 ------------------------------------------------------------------------------- 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=96.46399999999997, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=103.182, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=48.355, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=35.329, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=27.904, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images", label="make_images", y=14.842, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.744, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 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=14.278999999999996, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.964, 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=1.432, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=35.583, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images", label="make_images", y=0.691, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=6.653, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=2.16, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=3.152, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=20.569, yerr=0.0 Running dbcsr.inp with 1 threads and 32 ranks... done. Running dbcsr.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/dbcsr_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.010 0.010 81.162 81.162 lib_test 1 2.0 0.000 0.000 81.151 81.151 dbcsr_run_tests 3 3.0 0.002 0.002 81.151 81.151 test_multiplies_multiproc 3 4.0 0.001 0.001 63.071 63.071 dbcsr_redistribute 9 5.0 37.005 37.005 39.030 39.030 dbcsr_multiply_generic 9 5.0 0.001 0.001 22.329 22.329 dbcsr_make_random_matrix 9 4.0 13.370 13.370 17.964 17.964 multiply_cannon 9 6.0 0.040 0.040 15.907 15.907 multiply_cannon_loop 9 7.0 0.028 0.028 15.389 15.389 multiply_cannon_multrec 9 8.0 15.360 15.360 15.361 15.361 dbcsr_finalize 27 5.7 0.009 0.009 7.812 7.812 dbcsr_merge_all 18 6.5 2.516 2.516 6.867 6.867 dbcsr_data_release 975 7.6 3.409 3.409 3.409 3.409 tree_to_linear_d 9 7.0 2.755 2.755 2.755 2.755 make_m2s 18 6.0 0.001 0.001 2.424 2.424 make_images 18 7.0 0.870 0.870 2.234 2.234 dbcsr_destroy 93 5.8 0.000 0.000 1.641 1.641 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.005 0.022 23.621 23.628 lib_test 1 2.0 0.000 0.000 23.579 23.600 dbcsr_run_tests 3 3.0 0.000 0.001 23.573 23.593 test_multiplies_multiproc 3 4.0 0.000 0.003 22.662 22.710 dbcsr_multiply_generic 9 5.0 0.001 0.001 20.980 21.069 multiply_cannon 9 6.0 0.002 0.002 18.398 18.974 multiply_cannon_loop 9 7.0 0.002 0.003 18.053 18.648 multiply_cannon_multrec 72 8.0 13.643 14.153 13.644 14.154 mp_waitall_1 576 9.2 4.862 5.753 4.862 5.753 multiply_cannon_metrocomm1 72 8.0 0.001 0.002 4.294 5.196 mp_sum_l 470 2.5 1.027 1.402 1.027 1.402 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.956 1.328 make_m2s 18 6.0 0.001 0.001 0.970 1.003 make_images 18 7.0 0.022 0.023 0.967 0.999 dbcsr_make_random_matrix 9 4.0 0.692 0.709 0.873 0.904 dbcsr_data_release 444 7.6 0.605 0.743 0.605 0.743 dbcsr_redistribute 9 5.0 0.293 0.326 0.703 0.740 dbcsr_finalize 27 5.7 0.000 0.000 0.643 0.720 dbcsr_destroy 111 5.9 0.002 0.057 0.534 0.658 dbcsr_merge_all 18 6.5 0.101 0.119 0.568 0.627 make_images_data 18 8.0 0.001 0.001 0.519 0.599 hybrid_alltoall_any 18 9.0 0.056 0.235 0.448 0.522 ------------------------------------------------------------------------------- Plot: name="dbcsr_timings_32omp", title="Timings of dbcsr with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32omp", name="rest", label="rest", y=9.263000000000005, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=37.005, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=15.36, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.37, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=3.409, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="tree_to_linear_d", label="tree_to_linear_d", y=2.755, 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=2.4989999999999988, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.293, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=13.643, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.692, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.605, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="tree_to_linear_d", label="tree_to_linear_d", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.027, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=4.862, 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 0.062 0.062 141.053 141.053 qs_mol_dyn_low 1 2.0 0.005 0.005 139.350 139.350 velocity_verlet 5 3.0 0.004 0.004 112.813 112.813 qmmm_el_coupling 6 3.8 0.000 0.000 87.693 87.693 qmmm_elec_with_gaussian 6 4.8 0.025 0.025 87.688 87.688 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 86.866 86.866 qmmm_elec_gaussian_low_G 6 6.8 85.937 85.937 85.937 85.937 qs_forces 6 3.8 0.001 0.001 42.473 42.473 qs_energies 6 4.8 0.000 0.000 37.919 37.919 scf_env_do_scf 6 5.8 0.001 0.001 35.261 35.261 scf_env_do_scf_inner_loop 39 6.8 0.005 0.005 30.704 30.704 rebuild_ks_matrix 45 8.4 0.000 0.000 30.018 30.018 qs_ks_build_kohn_sham_matrix 45 9.4 0.006 0.006 30.018 30.018 qs_ks_update_qs_env 45 7.8 0.000 0.000 25.901 25.901 fft_wrap_pw1pw2 801 12.6 0.012 0.012 22.134 22.134 fft_wrap_pw1pw2_150 507 14.2 5.820 5.820 21.628 21.628 qs_vxc_create 45 10.4 0.001 0.001 17.687 17.687 xc_vxc_pw_create 45 11.4 0.727 0.727 17.686 17.686 xc_pw_derive 270 13.4 0.002 0.002 12.512 12.512 qs_rho_update_rho_low 45 7.9 0.000 0.000 8.624 8.624 calculate_rho_elec 45 8.9 0.637 0.637 8.623 8.623 xc_pw_divergence 45 12.4 0.001 0.001 8.482 8.482 xc_rho_set_and_dset_create 45 12.4 1.162 1.162 8.400 8.400 fft3d_s 802 14.6 8.288 8.288 8.297 8.297 pw_scatter_s 429 14.8 6.110 6.110 6.110 6.110 qmmm_forces 6 3.8 0.002 0.002 5.703 5.703 qmmm_forces_with_gaussian 6 4.8 0.031 0.031 5.360 5.360 pw_integral_ab 2539 7.4 4.939 4.939 4.939 4.939 qs_ks_ddapc 45 10.4 0.001 0.001 4.595 4.595 init_scf_loop 6 6.8 0.000 0.000 4.552 4.552 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.397 4.397 sum_up_and_integrate 45 10.4 0.001 0.001 4.280 4.280 density_rs2pw 45 9.9 0.002 0.002 4.268 4.268 integrate_v_rspace 45 11.4 0.017 0.017 4.233 4.233 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 4.132 4.132 grid_collocate_task_list 45 9.9 3.718 3.718 3.718 3.718 qmmm_forces_gaussian_low_G 6 6.8 3.658 3.658 3.658 3.658 fist_calc_energy_force 6 3.8 0.001 0.001 2.852 2.852 ------------------------------------------------------------------------------- From /workspace/artifacts/MQAE_single_node_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.038 0.068 72.530 72.547 qs_mol_dyn_low 1 2.0 0.004 0.006 71.300 71.367 qs_forces 6 3.8 0.001 0.001 51.834 51.834 qs_energies 6 4.8 0.000 0.000 49.608 49.609 scf_env_do_scf 6 5.8 0.000 0.002 48.534 48.534 scf_env_do_scf_inner_loop 113 6.2 0.003 0.024 46.559 46.561 rebuild_ks_matrix 119 8.1 0.000 0.000 35.693 35.702 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.015 35.692 35.702 qs_ks_update_qs_env 119 7.3 0.001 0.001 33.836 33.845 velocity_verlet 5 3.0 0.002 0.004 29.322 29.326 fft_wrap_pw1pw2 2059 12.4 0.024 0.026 22.394 23.041 fft_wrap_pw1pw2_150 1321 13.9 0.795 0.843 21.608 22.239 qs_vxc_create 119 10.1 0.002 0.002 19.746 19.757 xc_vxc_pw_create 119 11.1 0.374 0.437 19.744 19.755 fft3d_ps 2059 14.4 8.030 8.408 14.894 15.698 xc_pw_derive 714 13.1 0.006 0.007 13.965 14.618 qs_rho_update_rho_low 119 7.3 0.001 0.001 12.389 12.402 calculate_rho_elec 119 8.3 0.056 0.068 12.389 12.402 sum_up_and_integrate 119 10.1 0.002 0.002 10.531 10.591 integrate_v_rspace 119 11.1 0.003 0.004 10.394 10.456 xc_rho_set_and_dset_create 119 12.1 0.748 0.892 9.730 10.187 xc_pw_divergence 119 12.1 0.003 0.003 9.313 9.900 qmmm_forces 6 3.8 0.004 0.004 9.849 9.850 qmmm_forces_with_gaussian 6 4.8 0.008 0.012 9.426 9.641 qmmm_el_coupling 6 3.8 0.000 0.000 8.489 8.655 qmmm_elec_with_gaussian 6 4.8 0.005 0.006 8.488 8.653 density_rs2pw 119 9.3 0.005 0.005 7.628 7.947 potential_pw2rs 119 12.1 0.005 0.006 6.259 6.295 mp_alltoall_z22v 2059 16.4 4.874 6.099 4.874 6.099 grid_collocate_task_list 119 9.3 4.582 4.948 4.582 4.948 pw_restrict_s3 18 5.8 2.522 2.612 4.541 4.730 yz_to_x 964 15.0 0.843 1.041 3.411 4.301 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.038 4.143 transfer_pw2rs 500 12.8 0.005 0.006 4.063 4.073 grid_integrate_task_list 119 12.1 3.900 4.016 3.900 4.016 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 3.737 3.899 pw_prolongate_s3 18 6.8 2.060 2.167 3.737 3.899 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.382 3.804 transfer_rs2pw 488 10.2 0.006 0.007 3.391 3.723 x_to_yz 1095 15.8 1.111 1.203 3.417 3.577 qmmm_forces_gaussian_low_G 6 6.8 3.331 3.421 3.331 3.421 pw_scatter_p 1095 14.8 3.204 3.277 3.204 3.277 qmmm_elec_gaussian_low_G 6 6.8 2.783 3.198 2.783 3.198 mp_waitany 4028 12.8 2.609 3.186 2.609 3.186 transfer_pw2rs_150 125 13.9 1.129 1.233 2.867 2.934 transfer_rs2pw_150 125 11.2 1.097 1.308 2.410 2.728 qs_ks_ddapc 119 10.1 0.002 0.002 2.642 2.678 qs_scf_new_mos 113 7.2 0.001 0.001 2.626 2.633 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.625 2.632 ot_scf_mini 113 9.2 0.001 0.002 2.525 2.532 pw_integral_ab 2761 7.7 2.096 2.202 2.369 2.482 pw_gather_p 964 14.0 2.276 2.357 2.276 2.357 mp_sum_dm3 33 5.7 2.097 2.146 2.097 2.146 pw_derive 1089 13.4 2.097 2.145 2.097 2.145 xc_functional_eval 238 13.1 0.002 0.002 1.780 2.129 dbcsr_multiply_generic 2588 12.3 0.063 0.065 2.061 2.116 init_scf_loop 6 6.8 0.000 0.000 1.961 1.961 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.946 1.947 pw_copy 2027 12.4 1.717 1.810 1.717 1.810 pw_axpy 2529 9.3 1.701 1.774 1.701 1.774 pw_poisson_solve 125 9.9 0.002 0.002 1.710 1.752 ------------------------------------------------------------------------------- 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=22.583, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=85.937, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.288, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=6.11, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=5.82, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.939, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.718, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.658, 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=42.13900000000001, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.783, 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="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=0.795, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=2.096, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.582, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.331, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.9, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=8.03, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.874, yerr=0.0 Summary: Performance test took 38 minutes. Status: OK Removing intermediate container 857e6a39718f ---> 4770a3a98aee Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in b0f0e16186bb Removing intermediate container b0f0e16186bb ---> 499065ef95c7 Step 42/42 : ENTRYPOINT [] ---> Running in bd9d36f0ff12 Removing intermediate container bd9d36f0ff12 ---> 4a4d9947fbd5 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 4a4d9947fbd5 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: 2024-05-01 08:56:37+00:00