StartDate: 2024-03-20 09:03:15+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: aa4adac34cf79714cddcdea931a90aba3810da90 CommitTime: 2024-03-15 16:41:35 +0100 CommitAuthor: Hans Pabst CommitSubject: DBM: introduced OpenCL support (#3321) #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=aa4adac34cf79714cddcdea931a90aba3810da90 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 394.1MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu bccd10f490ab: Pulling fs layer bccd10f490ab: Verifying Checksum bccd10f490ab: Download complete bccd10f490ab: Pull complete Digest: sha256:77906da86b60585ce12215807090eb327e7386c8fafb5402369e421f44eff17e Status: Downloaded newer image for ubuntu:22.04 ---> ca2b0f26964c Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 03d16d9e2c6a Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 72223eb0b8d0 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 432bb79a897a Step 5/42 : RUN mkdir scripts ---> Using cache ---> 1bac2e842a38 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 ---> 94fa08efe2f0 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> a9437683062a Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 12ff9cf83aed Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 6e9f97374a01 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> a08edad7e3e5 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 63778cccdf7f Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> e538b9780c22 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 0e32b0cd01a2 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> a06fd154f6ad Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 7db7df61870f Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 77a4daa79489 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 4a309c10153c Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 75034c85a6d6 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> c60a8852e081 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 0b1a3154e422 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> ebc0b9070a55 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> f9e582c35689 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 513b1c38b831 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 3fb00d8c4d90 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> f81cc7aac257 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 0288ff6de7ea Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 2544cd32f598 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 73aee77da4e1 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> c097e852b95a Step 30/42 : COPY ./Makefile . ---> Using cache ---> b55183bac6f1 Step 31/42 : COPY ./src ./src ---> Using cache ---> 9174ec705efd Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 33185b0be570 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 3f36bf3a73a6 Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/" ---> Running in 0e41f7c4a38f './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Removing intermediate container 0e41f7c4a38f ---> d067a3319f50 Step 35/42 : COPY ./data ./data ---> 1b27f7dbc124 Step 36/42 : COPY ./tests ./tests ---> c023f2ac3f40 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> d2484a5d0945 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 1f5c0ab71cb3 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> d7e028fddc22 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 2ccdfeb6f559 ========== 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 0.033 0.033 92.545 92.545 qs_mol_dyn_low 1 2.0 0.003 0.003 91.933 91.933 qs_forces 11 3.9 0.001 0.001 91.892 91.892 qs_energies 11 4.9 0.001 0.001 85.337 85.337 scf_env_do_scf 11 5.9 0.001 0.001 74.003 74.003 scf_env_do_scf_inner_loop 108 6.5 0.012 0.012 59.934 59.934 velocity_verlet 10 3.0 0.002 0.002 59.508 59.508 dbcsr_multiply_generic 2286 12.5 0.194 0.194 22.969 22.969 rebuild_ks_matrix 119 8.3 0.001 0.001 22.376 22.376 qs_ks_build_kohn_sham_matrix 119 9.3 0.014 0.014 22.375 22.375 qs_scf_new_mos 108 7.5 0.001 0.001 22.352 22.352 qs_scf_loop_do_ot 108 8.5 0.001 0.001 22.351 22.351 qs_rho_update_rho_low 119 7.7 0.001 0.001 21.287 21.287 calculate_rho_elec 119 8.7 0.991 0.991 21.286 21.286 ot_scf_mini 108 9.5 0.002 0.002 20.889 20.889 qs_ks_update_qs_env 119 7.6 0.001 0.001 20.431 20.431 grid_collocate_task_list 119 9.7 16.237 16.237 16.237 16.237 sum_up_and_integrate 119 10.3 0.001 0.001 14.423 14.423 integrate_v_rspace 119 11.3 0.128 0.128 14.344 14.344 init_scf_loop 11 6.9 0.000 0.000 13.938 13.938 ot_mini 108 10.5 0.001 0.001 13.480 13.480 make_m2s 4572 13.5 0.047 0.047 11.750 11.750 grid_integrate_task_list 119 12.3 11.545 11.545 11.545 11.545 prepare_preconditioner 11 7.9 0.000 0.000 11.300 11.300 make_preconditioner 11 8.9 0.000 0.000 11.300 11.300 make_full_inverse_cholesky 11 9.9 0.023 0.023 10.152 10.152 fft_wrap_pw1pw2 1201 11.6 0.011 0.011 7.344 7.344 qs_ot_get_derivative 108 11.5 0.001 0.001 7.110 7.110 multiply_cannon 2286 13.5 0.293 0.293 7.040 7.040 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.668 6.668 ot_diis_step 108 11.5 0.003 0.003 6.367 6.367 fft_wrap_pw1pw2_140 487 12.2 1.146 1.146 6.263 6.263 multiply_cannon_loop 2286 14.5 0.060 0.060 6.256 6.256 multiply_cannon_multrec 2286 15.5 6.139 6.139 6.194 6.194 dbcsr_make_dense_low 5837 15.5 0.111 0.111 6.057 6.057 make_images 4572 14.5 2.391 2.391 5.966 5.966 make_dense_data 5837 16.5 5.289 5.289 5.932 5.932 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.921 5.921 apply_single 119 13.6 0.000 0.000 5.921 5.921 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.295 5.295 init_scf_run 11 5.9 0.003 0.003 4.068 4.068 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.065 4.065 density_rs2pw 119 9.7 0.004 0.004 4.059 4.059 dbcsr_copy 2102 12.0 0.266 0.266 3.706 3.706 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.699 3.699 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.623 3.623 wfi_extrapolate 11 7.9 0.001 0.001 3.517 3.517 dbcsr_complete_redistribute 329 12.2 1.813 1.813 3.496 3.496 dbcsr_copy_into_existing 22 7.9 3.356 3.356 3.356 3.356 qs_ot_get_p 119 10.4 0.001 0.001 3.307 3.307 qs_create_task_list 11 7.9 0.000 0.000 3.270 3.270 generate_qs_task_list 11 8.9 1.970 1.970 3.270 3.270 fft3d_s 1202 13.6 3.117 3.117 3.123 3.123 cp_fm_cholesky_invert 11 10.9 2.969 2.969 2.969 2.969 cp_fm_cholesky_decompose 22 10.9 2.961 2.961 2.961 2.961 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.930 2.930 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.927 2.927 potential_pw2rs 119 12.3 0.048 0.048 2.670 2.670 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.546 2.546 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.394 2.394 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.314 2.314 pw_poisson_solve 119 10.3 0.002 0.002 2.251 2.251 dbcsr_data_release 279532 16.0 2.157 2.157 2.157 2.157 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 2.089 2.089 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.010 0.035 50.099 50.116 qs_mol_dyn_low 1 2.0 0.003 0.005 49.951 49.956 qs_forces 11 3.9 0.002 0.002 49.906 49.907 qs_energies 11 4.9 0.001 0.001 46.626 46.629 scf_env_do_scf 11 5.9 0.001 0.003 42.867 42.868 scf_env_do_scf_inner_loop 108 6.5 0.003 0.024 39.312 39.313 velocity_verlet 10 3.0 0.001 0.003 29.951 29.952 rebuild_ks_matrix 119 8.3 0.001 0.001 18.242 18.334 qs_ks_build_kohn_sham_matrix 119 9.3 0.016 0.018 18.241 18.333 qs_ks_update_qs_env 119 7.6 0.001 0.001 16.180 16.264 dbcsr_multiply_generic 2286 12.5 0.078 0.080 15.157 15.342 qs_rho_update_rho_low 119 7.7 0.001 0.001 13.673 13.683 calculate_rho_elec 119 8.7 0.031 0.033 13.672 13.682 sum_up_and_integrate 119 10.3 0.002 0.002 13.404 13.434 integrate_v_rspace 119 11.3 0.004 0.005 13.380 13.412 qs_scf_new_mos 108 7.5 0.001 0.001 12.378 12.522 qs_scf_loop_do_ot 108 8.5 0.001 0.001 12.377 12.521 ot_scf_mini 108 9.5 0.002 0.003 11.666 11.813 multiply_cannon 2286 13.5 0.146 0.158 11.012 11.393 multiply_cannon_loop 2286 14.5 0.100 0.114 10.343 10.753 grid_collocate_task_list 119 9.7 9.394 9.643 9.394 9.643 grid_integrate_task_list 119 12.3 8.873 9.046 8.873 9.046 mp_waitall_1 158411 16.6 7.987 8.823 7.987 8.823 ot_mini 108 10.5 0.001 0.001 6.899 7.055 multiply_cannon_metrocomm3 18288 15.5 0.045 0.051 6.016 6.742 density_rs2pw 119 9.7 0.005 0.006 3.811 4.174 multiply_cannon_multrec 18288 15.5 3.889 4.157 3.901 4.169 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.548 3.701 apply_single 119 13.6 0.000 0.001 3.547 3.701 potential_pw2rs 119 12.3 0.007 0.008 3.663 3.689 fft_wrap_pw1pw2 1201 11.6 0.015 0.018 3.547 3.635 ot_diis_step 108 11.5 0.003 0.004 3.553 3.565 init_scf_loop 11 6.9 0.000 0.000 3.536 3.537 qs_ot_get_derivative 108 11.5 0.001 0.001 3.325 3.471 fft_wrap_pw1pw2_140 487 12.2 0.147 0.172 2.932 3.004 make_m2s 4572 13.5 0.047 0.057 2.802 2.897 fft3d_ps 1201 13.6 1.249 1.366 2.568 2.743 transfer_pw2rs 487 13.2 0.006 0.008 2.651 2.666 init_scf_run 11 5.9 0.000 0.006 2.657 2.658 scf_env_initial_rho_setup 11 6.9 0.000 0.005 2.657 2.657 make_images 4572 14.5 0.119 0.124 2.456 2.552 transfer_rs2pw 487 10.6 0.007 0.008 2.144 2.521 wfi_extrapolate 11 7.9 0.001 0.001 2.418 2.418 mp_waitany 9880 13.7 1.776 2.270 1.776 2.270 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.222 2.233 qs_ot_get_p 119 10.4 0.001 0.001 1.586 1.749 transfer_rs2pw_140 130 11.5 0.213 0.247 1.239 1.619 prepare_preconditioner 11 7.9 0.000 0.000 1.519 1.545 make_preconditioner 11 8.9 0.000 0.000 1.519 1.545 transfer_pw2rs_140 130 13.9 0.410 0.510 1.444 1.496 mp_alltoall_d11v 2130 13.8 1.173 1.476 1.173 1.476 make_images_data 4572 15.5 0.037 0.045 1.336 1.461 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.376 1.404 mp_alltoall_z22v 1201 15.6 1.037 1.318 1.037 1.318 hybrid_alltoall_any 4725 16.4 0.071 0.244 1.138 1.311 mp_sum_l 11298 13.2 0.860 1.267 0.860 1.267 mp_sum_d 4139 12.0 0.792 1.150 0.792 1.150 rs_gather_matrices 119 12.3 0.079 0.089 0.799 1.108 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.994 1.072 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.981 1.048 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 1.020 1.023 transfer_pw2rs_50 119 14.3 0.351 0.394 0.941 1.005 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.920 1.003 ------------------------------------------------------------------------------- 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=49.979, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=16.237, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=11.545, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=6.139, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.289, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=3.356, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=18.18, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.394, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.873, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.889, 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_waitany", label="mp_waitany", y=1.776, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.987, 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 0.038 0.038 117.114 117.114 qs_mol_dyn_low 1 2.0 0.003 0.003 116.437 116.437 qs_forces 11 3.9 0.001 0.001 116.394 116.394 qs_energies 11 4.9 0.001 0.001 108.452 108.452 scf_env_do_scf 11 5.9 0.002 0.002 94.887 94.887 scf_env_do_scf_inner_loop 96 6.5 0.012 0.012 78.597 78.597 velocity_verlet 10 3.0 0.002 0.002 73.900 73.900 rebuild_ks_matrix 107 8.3 0.001 0.001 35.365 35.365 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.013 35.365 35.365 qs_rho_update_rho_low 107 7.7 0.001 0.001 33.903 33.903 calculate_rho_elec 107 8.7 0.869 0.869 33.902 33.902 qs_ks_update_qs_env 107 7.6 0.001 0.001 31.802 31.802 grid_collocate_task_list 107 9.7 29.254 29.254 29.254 29.254 sum_up_and_integrate 107 10.3 0.001 0.001 28.008 28.008 integrate_v_rspace 107 11.3 0.096 0.096 27.933 27.933 grid_integrate_task_list 107 12.3 25.608 25.608 25.608 25.608 dbcsr_multiply_generic 1966 12.4 0.152 0.152 20.163 20.163 qs_scf_new_mos 96 7.5 0.001 0.001 20.159 20.159 qs_scf_loop_do_ot 96 8.5 0.001 0.001 20.159 20.159 ot_scf_mini 96 9.5 0.002 0.002 18.850 18.850 init_scf_loop 11 6.9 0.000 0.000 16.108 16.108 ot_mini 96 10.5 0.001 0.001 11.809 11.809 prepare_preconditioner 11 7.9 0.000 0.000 11.795 11.795 make_preconditioner 11 8.9 0.000 0.000 11.795 11.795 make_full_inverse_cholesky 11 9.9 0.023 0.023 10.634 10.634 make_m2s 3932 13.4 0.042 0.042 10.363 10.363 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.108 7.108 fft_wrap_pw1pw2 1081 11.6 0.009 0.009 6.614 6.614 qs_ot_get_derivative 96 11.5 0.001 0.001 6.411 6.411 multiply_cannon 1966 13.4 0.169 0.169 6.093 6.093 init_scf_run 11 5.9 0.003 0.003 5.725 5.725 scf_env_initial_rho_setup 11 6.9 0.002 0.002 5.722 5.722 fft_wrap_pw1pw2_140 439 12.2 0.938 0.938 5.717 5.717 multiply_cannon_loop 1966 14.4 0.047 0.047 5.646 5.646 multiply_cannon_multrec 1966 15.4 5.549 5.549 5.598 5.598 dbcsr_make_dense_low 4961 15.5 0.078 0.078 5.424 5.424 make_images 3932 14.4 2.125 2.125 5.407 5.407 ot_diis_step 96 11.5 0.003 0.003 5.396 5.396 make_dense_data 4961 16.5 4.828 4.828 5.333 5.333 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 5.193 5.193 apply_single 107 13.6 0.000 0.000 5.193 5.193 wfi_extrapolate 11 7.9 0.001 0.001 5.069 5.069 dbcsr_make_images_dense 3386 14.7 0.016 0.016 4.685 4.685 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.463 4.463 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.120 4.120 density_rs2pw 107 9.7 0.004 0.004 3.780 3.780 dbcsr_complete_redistribute 317 12.2 1.812 1.812 3.682 3.682 dbcsr_copy 1855 11.9 0.281 0.281 3.680 3.680 qs_create_task_list 11 7.9 0.000 0.000 3.675 3.675 generate_qs_task_list 11 8.9 2.392 2.392 3.675 3.675 qs_ot_get_p 107 10.4 0.001 0.001 3.635 3.635 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.476 3.476 dbcsr_copy_into_existing 22 7.9 3.329 3.329 3.329 3.329 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.264 3.264 cp_fm_cholesky_decompose 22 10.9 3.189 3.189 3.189 3.189 cp_fm_cholesky_invert 11 10.9 3.031 3.031 3.031 3.031 fft3d_s 1082 13.6 2.876 2.876 2.882 2.882 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.574 2.574 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.530 2.530 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_nonortho_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.010 0.036 77.417 77.436 qs_mol_dyn_low 1 2.0 0.003 0.004 77.279 77.284 qs_forces 11 3.9 0.002 0.002 77.235 77.235 qs_energies 11 4.9 0.001 0.001 72.095 72.097 scf_env_do_scf 11 5.9 0.001 0.002 66.746 66.747 scf_env_do_scf_inner_loop 96 6.5 0.003 0.020 61.605 61.605 velocity_verlet 10 3.0 0.001 0.003 46.298 46.299 rebuild_ks_matrix 107 8.3 0.001 0.001 32.848 32.912 qs_ks_build_kohn_sham_matrix 107 9.3 0.016 0.019 32.847 32.911 qs_ks_update_qs_env 107 7.6 0.001 0.001 28.922 28.978 sum_up_and_integrate 107 10.3 0.002 0.002 28.289 28.323 integrate_v_rspace 107 11.3 0.004 0.005 28.266 28.302 qs_rho_update_rho_low 107 7.7 0.001 0.001 27.198 27.209 calculate_rho_elec 107 8.7 0.028 0.032 27.198 27.209 grid_integrate_task_list 107 12.3 23.534 23.889 23.534 23.889 grid_collocate_task_list 107 9.7 22.797 23.133 22.797 23.133 dbcsr_multiply_generic 1966 12.4 0.070 0.074 14.422 14.564 qs_scf_new_mos 96 7.5 0.001 0.001 11.572 11.608 qs_scf_loop_do_ot 96 8.5 0.001 0.001 11.572 11.607 ot_scf_mini 96 9.5 0.002 0.002 10.928 10.966 multiply_cannon 1966 13.4 0.133 0.140 10.664 10.914 multiply_cannon_loop 1966 14.4 0.092 0.105 10.095 10.387 mp_waitall_1 136719 16.5 7.869 8.535 7.869 8.535 ot_mini 96 10.5 0.001 0.001 6.537 6.578 multiply_cannon_metrocomm3 15728 15.4 0.041 0.046 5.981 6.427 init_scf_loop 11 6.9 0.000 0.000 5.122 5.123 density_rs2pw 107 9.7 0.005 0.005 3.975 4.645 init_scf_run 11 5.9 0.000 0.005 4.198 4.199 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.198 4.198 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.077 4.087 multiply_cannon_multrec 15728 15.4 3.724 4.015 3.736 4.026 wfi_extrapolate 11 7.9 0.001 0.001 3.837 3.837 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.462 3.576 apply_single 107 13.6 0.000 0.001 3.461 3.576 potential_pw2rs 107 12.3 0.006 0.009 3.545 3.574 ot_diis_step 96 11.5 0.003 0.003 3.378 3.378 fft_wrap_pw1pw2 1081 11.6 0.014 0.017 3.247 3.341 qs_ot_get_derivative 96 11.5 0.001 0.001 3.139 3.174 transfer_rs2pw 439 10.6 0.007 0.007 2.453 3.142 mp_waitany 8968 13.7 2.163 2.985 2.163 2.985 fft_wrap_pw1pw2_140 439 12.2 0.138 0.159 2.674 2.730 transfer_pw2rs 439 13.2 0.006 0.008 2.661 2.666 make_m2s 3932 13.4 0.042 0.046 2.557 2.633 fft3d_ps 1081 13.6 1.143 1.259 2.342 2.503 make_images 3932 14.4 0.108 0.115 2.246 2.329 transfer_rs2pw_140 118 11.5 0.206 0.244 1.579 2.271 mp_alltoall_d11v 1998 13.7 1.473 2.236 1.473 2.236 rs_gather_matrices 107 12.3 0.089 0.101 1.140 1.866 ------------------------------------------------------------------------------- Plot: name="H2O-64_nonortho_timings_32omp", title="Timings of H2O-64_nonortho with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="rest", label="rest", y=48.54600000000001, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=29.254, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.608, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.549, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.828, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=3.329, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_nonortho_timings_32mpi", title="Timings of H2O-64_nonortho with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="rest", label="rest", y=17.33, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.797, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=23.534, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.724, 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_waitall_1", label="mp_waitall_1", y=7.869, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.163, 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 0.226 0.226 132.644 132.644 qs_energies 1 2.0 0.000 0.000 131.823 131.823 scf_env_do_scf 1 3.0 0.000 0.000 130.605 130.605 qs_ks_update_qs_env 8 5.0 0.000 0.000 125.769 125.769 rebuild_ks_matrix 7 6.0 0.000 0.000 125.715 125.715 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 125.715 125.715 hfx_ks_matrix 7 8.0 0.000 0.000 117.174 117.174 integrate_four_center 7 9.0 1.613 1.613 116.957 116.957 integrate_four_center_main 7 10.0 0.576 0.576 103.375 103.375 integrate_four_center_bin 444 11.0 102.799 102.799 102.799 102.799 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 74.764 74.764 init_scf_loop 1 4.0 0.000 0.000 55.832 55.832 integrate_four_center_load 7 10.0 0.001 0.001 11.686 11.686 hfx_load_balance 1 11.0 0.003 0.003 11.685 11.685 hfx_load_balance_count 1 12.0 5.833 5.833 5.833 5.833 hfx_load_balance_bin 1 12.0 5.833 5.833 5.833 5.833 qs_vxc_create 14 8.0 0.000 0.000 3.222 3.222 xc_vxc_pw_create 14 9.0 0.117 0.117 3.221 3.221 ------------------------------------------------------------------------------- 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 0.207 0.234 134.749 134.762 qs_energies 1 2.0 0.000 0.000 134.342 134.353 scf_env_do_scf 1 3.0 0.000 0.000 133.979 133.980 qs_ks_update_qs_env 8 5.0 0.000 0.000 131.477 131.481 rebuild_ks_matrix 7 6.0 0.000 0.000 131.468 131.471 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 131.468 131.471 hfx_ks_matrix 7 8.0 0.000 0.000 125.613 125.616 integrate_four_center 7 9.0 0.051 0.335 125.603 125.606 integrate_four_center_main 7 10.0 0.003 0.004 105.076 111.799 integrate_four_center_bin 448 11.0 105.072 111.795 105.072 111.795 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 78.420 78.420 init_scf_loop 1 4.0 0.000 0.000 55.558 55.558 mp_sync 56 11.2 7.096 13.640 7.096 13.640 integrate_four_center_load 7 10.0 0.000 0.000 12.716 12.717 hfx_load_balance 1 11.0 0.001 0.001 12.716 12.717 hfx_load_balance_bin 1 12.0 6.147 6.366 6.147 6.366 hfx_load_balance_count 1 12.0 6.076 6.331 6.076 6.331 ------------------------------------------------------------------------------- Plot: name="H2O-hyb_timings_32omp", title="Timings of H2O-hyb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32omp", name="rest", label="rest", y=15.76400000000001, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=102.799, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.833, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.833, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.613, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.576, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.226, 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=10.096999999999994, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=105.072, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.076, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.147, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.051, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.207, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=7.096, 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 0.016 0.016 77.495 77.495 qs_energies 1 2.0 0.000 0.000 77.120 77.120 mp2_main 1 3.0 0.000 0.000 73.705 73.705 mp2_gpw_main 1 4.0 0.000 0.000 73.598 73.598 rpa_ri_compute_en 1 5.0 0.000 0.000 70.033 70.033 rpa_num_int 1 6.0 0.001 0.001 70.027 70.027 compute_mat_P_omega 1 7.0 0.004 0.004 60.808 60.808 compute_mat_P_omega_contract 10 8.0 8.842 8.842 60.609 60.609 dbt_total 2336 9.6 0.014 0.014 47.102 47.102 dbt_contract 787 11.0 0.042 0.042 39.940 39.940 dbt_tas_total 1149 12.2 0.287 0.287 38.485 38.485 dbt_tas_multiply 807 12.1 0.002 0.002 37.299 37.299 dbt_tas_dbm 807 14.1 0.003 0.003 30.736 30.736 dbm_multiply 807 16.1 30.728 30.728 30.728 30.728 dbt_tas_mm_1N 524 15.1 0.001 0.001 23.539 23.539 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 22.443 22.443 compute_mat_P_omega_calc_M_occ 250 9.0 8.873 8.873 17.108 17.108 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.685 6.685 dbt_copy 1103 10.7 0.140 0.140 5.958 5.958 dbt_tas_mm_2 251 15.0 0.001 0.001 5.699 5.699 compute_QP_energies 1 7.0 0.000 0.000 5.192 5.192 compute_self_energy_cubic_gw 1 8.0 0.055 0.055 5.190 5.190 contract_cubic_gw 21 9.0 0.000 0.000 4.068 4.068 dbt_tas_reserve_blocks_index 3261 14.3 0.482 0.482 3.767 3.767 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.558 3.558 dbm_reserve_blocks 3628 15.3 3.350 3.350 3.350 3.350 scf_env_do_scf 1 3.0 0.000 0.000 3.085 3.085 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 3.085 3.085 dbt_reserve_blocks_index 2280 13.1 0.054 0.054 2.869 2.869 dbt_reserve_blocks_index_array 2222 12.2 0.010 0.010 2.811 2.811 dbt_crop 1042 12.0 1.473 1.473 2.517 2.517 convert_to_new_pgrid 2421 14.1 0.115 0.115 2.371 2.371 dbt_tas_copy 574 11.4 1.312 1.312 2.293 2.293 dbm_copy 1614 15.1 2.256 2.256 2.256 2.256 dbt_reshape 278 11.9 1.157 1.157 2.043 2.043 dbt_tas_reshape 367 15.0 0.034 0.034 1.918 1.918 get_2c_integrals 1 6.0 0.000 0.000 1.613 1.613 compute_W_cubic_GW 10 7.0 0.003 0.003 1.606 1.606 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.592 1.592 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.550 1.550 ------------------------------------------------------------------------------- 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 0.007 0.031 33.846 33.859 qs_energies 1 2.0 0.000 0.000 33.680 33.682 mp2_main 1 3.0 0.000 0.000 32.652 32.654 mp2_gpw_main 1 4.0 0.000 0.000 32.563 32.565 rpa_ri_compute_en 1 5.0 0.000 0.000 31.284 31.286 rpa_num_int 1 6.0 0.000 0.002 31.284 31.286 dbt_total 2336 9.6 0.015 0.016 27.869 27.880 compute_mat_P_omega 1 7.0 0.001 0.006 26.894 26.918 compute_mat_P_omega_contract 10 8.0 0.394 0.422 26.745 26.750 dbt_contract 787 11.0 0.040 0.041 20.683 20.689 dbt_tas_total 1149 12.2 0.080 0.089 18.371 18.372 dbt_tas_multiply 807 12.1 0.002 0.002 18.293 18.296 dbt_tas_dbm 807 14.1 0.003 0.003 12.778 12.785 dbm_multiply 807 16.1 10.210 11.078 10.210 11.078 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.174 8.187 compute_mat_P_omega_calc_M_occ 250 9.0 0.383 0.411 8.081 8.082 dbt_copy 1149 10.8 0.013 0.014 6.138 6.437 dbt_tas_mm_2 251 15.0 0.001 0.002 6.205 6.211 dbt_reshape 1136 11.8 2.637 2.808 5.848 6.146 mp_sync 8688 11.6 4.640 5.866 4.640 5.866 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.234 5.234 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.477 4.870 compute_QP_energies 1 7.0 0.000 0.000 2.742 2.743 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 2.740 2.742 mp_waitall_2 3812 15.3 2.393 2.734 2.393 2.734 dbt_communicate_buffer 1136 12.8 0.051 0.056 2.367 2.630 contract_cubic_gw 21 9.0 0.000 0.000 2.148 2.148 dbt_reserve_blocks_index 2887 13.1 0.066 0.072 1.717 1.938 dbt_reserve_blocks_index_array 2829 12.2 0.008 0.010 1.709 1.930 dbt_tas_reserve_blocks_index 3347 14.5 0.434 0.465 1.699 1.917 dbt_crop 1042 12.0 0.885 0.980 1.427 1.584 dbm_reserve_blocks 3752 15.4 1.354 1.565 1.354 1.565 mp2_ri_gpw_compute_in 1 5.0 0.003 0.004 1.277 1.278 mp_sum_l 6165 12.9 1.100 1.220 1.100 1.220 dbt_tas_replicate 405 14.1 0.536 0.721 1.119 1.199 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.088 1.092 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.028 1.030 parallel_gemm_fm 105 8.4 0.000 0.000 0.985 0.999 parallel_gemm_fm_cosma 105 9.4 0.984 0.999 0.984 0.999 scf_env_do_scf 1 3.0 0.000 0.000 0.976 0.976 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.976 0.976 convert_to_new_pgrid 2421 14.1 0.026 0.031 0.787 0.942 dbm_copy 1608 15.1 0.756 0.913 0.756 0.913 mp_max_i 2009 9.8 0.621 0.772 0.621 0.772 compute_W_cubic_GW 10 7.0 0.001 0.001 0.752 0.761 ------------------------------------------------------------------------------- Plot: name="GW_PBE_4benzene_timings_32omp", title="Timings of GW_PBE_4benzene with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="rest", label="rest", y=22.289, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=30.728, 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=8.873, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.842, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.35, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.256, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.157, 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=11.078999999999994, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.21, 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=0.383, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.394, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.354, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.756, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.637, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.64, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.393, 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 0.044 0.044 238.150 238.150 qs_forces 1 2.0 0.000 0.000 237.599 237.599 rebuild_ks_matrix 7 6.6 0.000 0.000 236.122 236.122 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 236.121 236.121 hfx_ks_matrix 7 8.6 0.000 0.000 233.740 233.740 hfx_ri_update_ks 7 9.6 0.000 0.000 192.908 192.908 hfx_ri_update_ks_Pmat 7 10.6 32.365 32.365 192.897 192.897 dbt_total 849 11.0 0.006 0.006 178.148 178.148 qs_energies 1 3.0 0.000 0.000 170.169 170.169 scf_env_do_scf 1 4.0 0.001 0.001 169.850 169.850 qs_ks_update_qs_env 8 6.0 0.000 0.000 168.742 168.742 dbt_contract 207 12.4 0.030 0.030 158.465 158.465 dbt_tas_total 369 13.4 1.506 1.506 157.013 157.013 dbt_tas_multiply 216 13.5 0.001 0.001 153.103 153.103 dbt_tas_dbm 216 15.5 0.001 0.001 141.758 141.758 dbm_multiply 216 17.5 141.755 141.755 141.755 141.755 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.000 135.927 135.927 dbt_tas_mm_2 91 16.5 0.001 0.001 127.637 127.637 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 107.293 107.293 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 67.383 67.383 init_scf_loop 2 5.0 0.000 0.000 62.555 62.555 hfx_ri_update_forces 1 7.0 1.622 1.622 40.829 40.829 hfx_ri_forces_Pmat_3c 1 8.0 4.900 4.900 23.094 23.094 dbt_copy 423 11.8 0.064 0.064 15.764 15.764 precalc_derivatives 1 8.0 2.211 2.211 13.441 13.441 dbt_reshape 132 13.2 6.672 6.672 10.870 10.870 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.616 9.616 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.487 9.487 dbt_tas_reserve_blocks_index 1323 15.4 0.995 0.995 8.142 8.142 build_3c_derivatives 3 9.0 2.410 2.410 7.588 7.588 dbm_reserve_blocks 1491 16.2 7.340 7.340 7.340 7.340 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.043 7.043 dbt_reserve_blocks_index 846 14.4 0.097 0.097 6.335 6.335 dbt_reserve_blocks_index_array 816 13.5 0.007 0.007 6.223 6.223 dbt_crop 372 13.7 2.796 2.796 4.891 4.891 ------------------------------------------------------------------------------- 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 0.036 46.863 46.875 qs_forces 1 2.0 0.000 0.000 46.670 46.670 rebuild_ks_matrix 7 6.6 0.000 0.000 45.919 45.920 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 45.919 45.920 hfx_ks_matrix 7 8.6 0.000 0.000 44.948 44.953 dbt_total 849 11.0 0.006 0.006 40.009 40.022 dbt_contract 207 12.4 0.024 0.026 30.877 30.888 dbt_tas_total 369 13.4 0.057 0.159 27.236 27.240 dbt_tas_multiply 216 13.5 0.001 0.001 26.785 26.786 hfx_ri_update_ks 7 9.6 0.000 0.000 26.411 26.411 hfx_ri_update_ks_Pmat 7 10.6 1.205 1.274 26.407 26.408 qs_energies 1 3.0 0.000 0.000 24.899 24.899 scf_env_do_scf 1 4.0 0.000 0.001 24.744 24.744 qs_ks_update_qs_env 8 6.0 0.000 0.000 24.162 24.163 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 21.758 21.759 dbt_tas_dbm 216 15.5 0.001 0.003 20.579 20.584 dbm_multiply 216 17.5 18.328 19.124 18.328 19.124 hfx_ri_update_forces 1 7.0 0.057 0.063 18.536 18.541 hfx_ri_forces_Pmat_3c 1 8.0 0.160 0.173 13.661 13.679 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 13.615 13.615 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 11.578 11.591 init_scf_loop 2 5.0 0.000 0.000 11.128 11.128 dbt_tas_mm_2 91 16.5 0.001 0.001 9.346 9.352 dbt_copy 539 12.5 0.011 0.013 8.101 8.520 mp_sync 2901 12.8 4.902 6.980 4.902 6.980 dbt_reshape 393 13.9 3.338 3.471 6.189 6.506 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.149 5.905 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.330 5.330 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.184 4.330 precalc_derivatives 1 8.0 0.084 0.090 3.498 3.498 dbt_tas_reserve_blocks_index 1471 15.8 0.890 0.916 2.955 3.349 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.240 3.240 mp_waitall_2 1318 16.2 2.715 2.912 2.715 2.912 dbt_reserve_blocks_index 1107 14.8 0.103 0.111 2.422 2.713 dbt_reserve_blocks_index_array 1077 13.9 0.005 0.006 2.396 2.686 dbm_reserve_blocks 1641 16.6 2.251 2.649 2.251 2.649 dbt_crop 372 13.7 1.677 1.719 2.420 2.525 dbt_communicate_buffer 393 14.9 0.012 0.013 1.877 2.043 build_3c_derivatives 3 9.0 0.222 0.240 1.924 1.933 dbt_tas_replicate 170 15.1 0.626 0.667 1.592 1.689 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.644 1.647 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.592 1.595 convert_to_new_pgrid 648 15.5 0.036 0.075 1.196 1.529 dbm_copy 452 16.3 1.052 1.378 1.052 1.378 dbt_tas_copy 146 12.6 0.608 0.657 1.191 1.324 mp_sum_l 6385 13.7 0.870 1.152 0.870 1.152 dbt_tas_communicate_buffer 370 16.3 0.012 0.013 0.956 1.024 ------------------------------------------------------------------------------- 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=45.117999999999995, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=141.755, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=32.365, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.34, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.672, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.9, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=13.963999999999999, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=18.328, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.205, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.251, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.338, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.16, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.902, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.715, 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 0.017 0.017 180.472 180.472 qs_energies 1 2.0 0.000 0.000 180.285 180.285 mp2_main 1 3.0 0.000 0.000 174.940 174.940 mp2_gpw_main 1 4.0 0.001 0.001 174.533 174.533 mp2_ri_gpw_compute_in 1 5.0 0.401 0.401 127.538 127.538 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 118.192 118.192 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 89.855 89.855 integrate_v_rspace 2666 8.0 0.692 0.692 76.804 76.804 grid_integrate_task_list 2666 9.0 73.864 73.864 73.864 73.864 mp2_ri_gpw_compute_en 1 5.0 0.087 0.087 46.972 46.972 mp2_ri_gpw_compute_en_RI_loop 1 6.0 10.176 10.176 45.060 45.060 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.078 2.078 27.124 27.124 local_gemm 2080 8.0 25.046 25.046 25.046 25.046 dbcsr_multiply_generic 5322 8.0 0.211 0.211 22.171 22.171 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 22.148 22.148 fft_wrap_pw1pw2 53228 10.4 0.136 0.136 12.057 12.057 calculate_wavefunction 2656 8.0 8.242 8.242 11.754 11.754 multiply_cannon 5322 9.0 0.513 0.513 11.460 11.460 multiply_cannon_loop 5322 10.0 0.146 0.146 9.956 9.956 get_2c_integrals 1 6.0 0.000 0.000 8.832 8.832 fft_wrap_pw1pw2_20 21271 11.4 1.029 1.029 8.683 8.683 make_m2s 10644 9.0 0.063 0.063 8.524 8.524 multiply_cannon_multrec 5322 11.0 8.377 8.377 8.418 8.418 compute_2c_integrals 1 7.0 0.006 0.006 8.246 8.246 compute_2c_integrals_loop_lm 1 8.0 0.011 0.011 8.233 8.233 mp2_eri_2c_integrate_gpw 1 9.0 0.875 0.875 8.222 8.222 make_images 10644 10.0 3.215 3.215 8.150 8.150 fft3d_s 53229 12.4 6.557 6.557 6.598 6.598 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.338 2.338 6.075 6.075 mp2_ri_gpw_compute_en_ener 2080 7.0 5.747 5.747 5.747 5.747 scf_env_do_scf 1 3.0 0.000 0.000 4.935 4.935 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.935 4.935 potential_pw2rs 5322 10.0 0.147 0.147 4.436 4.436 copy_dbcsr_to_fm 2679 8.0 0.027 0.027 4.339 4.339 mp2_eri_2c_integrate_gpw_pot_l 2656 10.0 0.005 0.005 3.616 3.616 collocate_single_gaussian 2656 10.0 0.136 0.136 3.614 3.614 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.035 38.036 38.049 qs_energies 1 2.0 0.000 0.000 37.888 37.889 mp2_main 1 3.0 0.000 0.001 35.834 35.835 mp2_gpw_main 1 4.0 0.001 0.001 35.717 35.718 mp2_ri_gpw_compute_in 1 5.0 0.043 0.045 18.383 18.758 mp2_ri_gpw_compute_en 1 5.0 0.289 0.293 17.270 17.477 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 17.088 17.465 mp2_ri_gpw_compute_en_RI_loop 1 6.0 2.370 2.652 16.003 16.010 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 14.980 15.136 integrate_v_rspace 93 8.1 0.103 0.114 14.874 15.036 grid_integrate_task_list 93 9.1 14.578 14.726 14.578 14.726 mp2_ri_gpw_compute_en_expansio 65 7.0 0.099 0.113 10.950 11.100 local_gemm 65 8.0 10.850 11.000 10.850 11.000 mp2_ri_gpw_compute_en_comm 17 7.0 0.085 0.117 2.353 3.205 mp_sendrecv_dm3 1054 8.0 1.807 2.809 1.807 2.809 dbcsr_multiply_generic 176 8.0 0.008 0.009 1.786 2.083 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.770 2.065 scf_env_do_scf 1 3.0 0.000 0.000 1.913 1.914 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 1.913 1.914 get_2c_integrals 1 6.0 0.005 0.012 1.237 1.256 multiply_cannon 176 9.0 0.018 0.021 1.075 1.203 multiply_cannon_loop 176 10.0 0.002 0.002 1.016 1.142 multiply_cannon_multrec 246 11.0 0.880 0.962 0.886 0.969 compute_2c_integrals 1 7.0 0.003 0.004 0.902 0.911 qs_scf_new_mos 10 5.0 0.000 0.000 0.890 0.897 eigensolver 11 5.8 0.001 0.001 0.860 0.861 make_m2s 352 9.0 0.003 0.003 0.675 0.841 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 0.798 0.834 mp2_eri_2c_integrate_gpw 1 9.0 0.217 0.226 0.798 0.832 make_images 352 10.0 0.051 0.055 0.663 0.827 ------------------------------------------------------------------------------- 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=54.76700000000001, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=73.864, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=25.046, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=10.176, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.377, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.242, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 Plot: name="RI-MP2_ammonia_timings_32mpi", title="Timings of RI-MP2_ammonia with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="rest", label="rest", y=7.5510000000000055, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.578, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.85, 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=2.37, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.88, 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=1.807, 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 0.100 0.100 135.518 135.518 qs_energies 1 2.0 0.000 0.000 134.140 134.140 scf_env_do_scf 1 3.0 0.000 0.000 126.538 126.538 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 126.538 126.538 qs_ks_update_qs_env 15 5.0 0.000 0.000 56.874 56.874 rebuild_ks_matrix 15 6.0 0.000 0.000 56.656 56.656 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 56.656 56.656 qs_scf_new_mos 15 5.0 0.000 0.000 44.927 44.927 qs_vxc_create 15 8.0 0.000 0.000 40.056 40.056 eigensolver 15 6.0 0.002 0.002 37.182 37.182 calculate_dispersion_nonloc 15 9.0 7.116 7.116 34.868 34.868 fft_wrap_pw1pw2 1086 10.0 0.019 0.019 29.659 29.659 cp_fm_diag_elpa 15 7.0 0.000 0.000 23.697 23.697 cp_fm_diag_elpa_base 15 8.0 21.061 21.061 23.697 23.697 fft_wrap_pw1pw2_150 765 11.0 7.173 7.173 21.800 21.800 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.069 21.069 calculate_rho_elec 16 6.0 0.217 0.217 21.069 21.069 grid_collocate_task_list 16 7.0 19.239 19.239 19.239 19.239 sum_up_and_integrate 15 8.0 0.000 0.000 15.516 15.516 integrate_v_rspace 15 9.0 0.021 0.021 15.504 15.504 grid_integrate_task_list 15 10.0 14.780 14.780 14.780 14.780 fft3d_s 1087 12.0 11.056 11.056 11.066 11.066 cp_fm_cholesky_restore 45 7.0 11.049 11.049 11.049 11.049 pw_scatter_s 585 12.1 7.780 7.780 7.780 7.780 fft_wrap_pw1pw2_200 197 11.3 1.729 1.729 7.575 7.575 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.483 5.483 dbcsr_complete_redistribute 46 8.3 2.067 2.067 5.337 5.337 xc_vxc_pw_create 15 9.0 0.206 0.206 5.187 5.187 cp_fm_upper_to_full 30 8.0 5.069 5.069 5.069 5.069 gspace_mixing 14 5.0 0.171 0.171 4.804 4.804 vdW_energy 15 10.0 4.443 4.443 4.443 4.443 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.439 4.439 broyden_mixing 14 6.0 4.149 4.149 4.150 4.150 xc_pw_derive 90 11.0 0.001 0.001 3.650 3.650 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 3.201 3.201 ------------------------------------------------------------------------------- From /workspace/artifacts/diag_cu144_broy_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.015 0.041 63.611 63.629 qs_energies 1 2.0 0.000 0.000 63.268 63.276 scf_env_do_scf 1 3.0 0.000 0.001 58.903 58.903 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 58.903 58.903 qs_ks_update_qs_env 15 5.0 0.000 0.000 25.786 25.796 rebuild_ks_matrix 15 6.0 0.000 0.000 25.750 25.760 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.005 25.750 25.760 qs_rho_update_rho_low 16 5.0 0.000 0.000 19.607 19.612 calculate_rho_elec 16 6.0 0.007 0.007 19.607 19.612 grid_collocate_task_list 16 7.0 18.262 18.401 18.262 18.401 sum_up_and_integrate 15 8.0 0.000 0.000 15.826 15.876 integrate_v_rspace 15 9.0 0.001 0.001 15.817 15.872 grid_integrate_task_list 15 10.0 14.588 14.808 14.588 14.808 qs_scf_new_mos 15 5.0 0.000 0.000 14.083 14.150 eigensolver 15 6.0 0.001 0.002 12.993 13.029 qs_vxc_create 15 8.0 0.001 0.001 9.504 9.516 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.049 9.055 cp_fm_diag_elpa_base 15 8.0 8.911 8.934 9.045 9.047 calculate_dispersion_nonloc 15 9.0 0.920 0.943 7.644 7.667 fft_wrap_pw1pw2 1086 10.0 0.019 0.021 7.142 7.280 fft3d_ps 1086 12.0 2.655 2.931 5.287 5.498 fft_wrap_pw1pw2_150 765 11.0 0.124 0.139 4.613 4.663 cp_fm_cholesky_restore 45 7.0 3.791 3.850 3.791 3.850 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.774 2.775 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.438 2.672 mp_alltoall_z22v 1086 14.0 2.003 2.658 2.003 2.658 fft_wrap_pw1pw2_200 197 11.3 0.095 0.115 2.392 2.482 xc_vxc_pw_create 15 9.0 0.015 0.020 1.860 1.886 build_core_ppnl 1 5.0 1.528 1.674 1.528 1.674 x_to_yz 585 13.1 0.363 0.388 1.367 1.644 yz_to_x 501 12.9 0.243 0.326 1.241 1.534 vdW_energy 15 10.0 1.336 1.379 1.336 1.379 density_rs2pw 16 7.0 0.001 0.001 1.197 1.361 init_scf_run 1 3.0 0.000 0.001 1.355 1.357 xc_pw_derive 90 11.0 0.001 0.001 1.237 1.320 transfer_rs2pw 82 8.0 0.001 0.001 0.943 1.318 ------------------------------------------------------------------------------- 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=58.333, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=21.061, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.239, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.78, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=11.056, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=11.049, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=15.403999999999996, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.911, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=18.262, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.588, 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=3.791, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.655, 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 0.088 286.311 286.311 qs_energies 1 2.0 0.000 0.000 286.153 286.153 ls_scf 1 3.0 0.000 0.000 284.618 284.618 ls_scf_main 1 4.0 0.002 0.002 273.374 273.374 density_matrix_trs4 11 5.0 0.013 0.013 175.841 175.841 ls_scf_dm_to_ks 11 5.0 0.000 0.000 91.544 91.544 matrix_ls_to_qs 11 6.0 0.000 0.000 88.157 88.157 dbcsr_multiply_generic 185 6.1 0.924 0.924 81.032 81.032 arnoldi_extremal 12 6.1 0.000 0.000 80.876 80.876 arnoldi_normal_ev 12 7.1 0.058 0.058 80.875 80.875 build_subspace 23 8.1 0.089 0.089 79.043 79.043 dbcsr_matrix_vector_mult 652 9.0 0.263 0.263 78.891 78.891 dbcsr_matrix_vector_mult_local 652 10.0 77.229 77.229 77.239 77.239 multiply_cannon 185 7.1 0.456 0.456 47.312 47.312 dbcsr_copy_into_existing 11 7.0 46.878 46.878 46.878 46.878 dbcsr_complete_redistribute 23 7.5 33.406 33.406 45.632 45.632 matrix_decluster 11 7.0 0.000 0.000 41.277 41.277 multiply_cannon_loop 185 8.1 0.270 0.270 34.294 34.294 make_m2s 370 7.1 0.040 0.040 28.528 28.528 make_images 370 8.1 12.531 12.531 26.062 26.062 multiply_cannon_multrec 185 9.1 24.195 24.195 24.422 24.422 dbcsr_finalize 646 7.5 0.255 0.255 16.542 16.542 dbcsr_merge_all 597 8.5 2.508 2.508 15.185 15.185 setup_rec_index_2d 370 8.1 12.346 12.346 12.346 12.346 dbcsr_sort_indices 805 10.1 11.409 11.409 11.409 11.409 tree_to_linear_d 110 9.4 11.177 11.177 11.177 11.177 ls_scf_init_scf 1 4.0 0.000 0.000 10.538 10.538 ls_scf_init_matrix_S 1 5.0 0.000 0.000 10.025 10.025 quick_finalize 395 10.0 0.431 0.431 9.888 9.888 calculate_norms 370 9.1 9.603 9.603 9.603 9.603 dbcsr_special_finalize 370 9.1 0.002 0.002 9.079 9.079 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 9.075 9.075 dbcsr_dot_sd 144 6.3 6.772 6.772 6.773 6.773 matrix_qs_to_ls 12 5.1 0.000 0.000 6.420 6.420 matrix_cluster 12 6.1 0.000 0.000 6.420 6.420 ------------------------------------------------------------------------------- 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 0.033 74.177 74.189 qs_energies 1 2.0 0.000 0.000 74.044 74.044 ls_scf 1 3.0 0.000 0.000 73.990 73.991 ls_scf_main 1 4.0 0.000 0.008 71.179 71.179 density_matrix_trs4 11 5.0 0.007 0.020 68.418 68.481 dbcsr_multiply_generic 185 6.1 0.064 0.082 64.816 65.085 multiply_cannon 185 7.1 0.035 0.041 53.505 54.540 multiply_cannon_loop 185 8.1 0.115 0.124 50.977 51.891 multiply_cannon_multrec 1480 9.1 30.869 33.062 31.194 33.395 mp_waitall_1 11936 10.3 17.413 20.626 17.413 20.626 multiply_cannon_metrocomm3 1480 9.1 0.014 0.017 13.162 16.838 make_m2s 370 7.1 0.038 0.040 7.450 7.521 make_images 370 8.1 0.663 0.702 7.310 7.383 calculate_norms 2960 9.1 5.256 5.581 5.256 5.581 mp_sum_l 1199 5.3 2.894 4.067 2.894 4.067 make_images_data 370 9.1 0.010 0.011 3.322 3.550 multiply_cannon_metrocomm1 1480 9.1 0.006 0.007 1.215 3.534 hybrid_alltoall_any 393 9.9 0.238 1.130 2.876 3.184 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.997 2.863 arnoldi_extremal 12 6.1 0.000 0.001 2.661 2.683 arnoldi_normal_ev 12 7.1 0.001 0.008 2.661 2.682 build_subspace 23 8.1 0.021 0.026 2.558 2.560 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.370 2.429 dbcsr_complete_redistribute 23 7.5 1.306 1.419 2.140 2.254 dbcsr_matrix_vector_mult 652 9.0 0.014 0.052 2.142 2.200 matrix_ls_to_qs 11 6.0 0.000 0.000 2.069 2.182 ls_scf_init_scf 1 4.0 0.000 0.000 2.110 2.111 make_images_pack 370 9.1 1.837 2.099 1.840 2.103 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.080 2.089 matrix_decluster 11 7.0 0.000 0.000 1.926 2.040 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.002 1.891 1.892 dbcsr_matrix_vector_mult_local 652 10.0 1.702 1.832 1.704 1.833 buffer_matrices_ensure_size 370 8.1 1.399 1.597 1.399 1.597 ------------------------------------------------------------------------------- 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=82.46899999999997, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=77.229, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=46.878, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=33.406, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=24.195, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images", label="make_images", y=12.531, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.603, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=12.237000000000002, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.702, 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=1.306, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=30.869, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images", label="make_images", y=0.663, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.256, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=17.413, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.837, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.894, 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 0.009 0.009 74.169 74.169 lib_test 1 2.0 0.000 0.000 74.158 74.158 dbcsr_run_tests 3 3.0 0.168 0.168 74.158 74.158 test_multiplies_multiproc 3 4.0 0.001 0.001 57.436 57.436 dbcsr_redistribute 9 5.0 37.620 37.620 39.249 39.249 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.800 16.800 dbcsr_make_random_matrix 9 4.0 13.126 13.126 16.448 16.448 multiply_cannon 9 6.0 0.013 0.013 11.795 11.795 multiply_cannon_loop 9 7.0 0.016 0.016 11.420 11.420 multiply_cannon_multrec 9 8.0 11.404 11.404 11.404 11.404 dbcsr_finalize 27 5.7 0.014 0.014 5.923 5.923 dbcsr_merge_all 18 6.5 2.029 2.029 5.177 5.177 dbcsr_data_release 975 7.6 2.781 2.781 2.781 2.781 tree_to_linear_d 9 7.0 1.951 1.951 1.951 1.951 make_m2s 18 6.0 0.001 0.001 1.795 1.795 make_images 18 7.0 0.635 0.635 1.719 1.719 ------------------------------------------------------------------------------- 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 0.018 19.151 19.157 lib_test 1 2.0 0.000 0.000 19.117 19.135 dbcsr_run_tests 3 3.0 0.000 0.001 19.111 19.130 test_multiplies_multiproc 3 4.0 0.000 0.002 18.277 18.323 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.814 16.913 multiply_cannon 9 6.0 0.001 0.002 14.574 15.340 multiply_cannon_loop 9 7.0 0.002 0.002 14.295 14.986 multiply_cannon_multrec 72 8.0 10.857 11.382 10.858 11.383 mp_waitall_1 576 9.2 3.780 4.683 3.780 4.683 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 3.291 4.121 mp_sum_l 470 2.5 1.072 1.755 1.072 1.755 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 1.063 1.746 dbcsr_make_random_matrix 9 4.0 0.672 0.776 0.800 0.891 make_m2s 18 6.0 0.001 0.001 0.705 0.754 make_images 18 7.0 0.021 0.022 0.701 0.751 dbcsr_data_release 444 7.6 0.563 0.650 0.563 0.650 dbcsr_destroy 111 5.9 0.003 0.048 0.503 0.591 dbcsr_redistribute 9 5.0 0.245 0.291 0.547 0.590 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.142 0.588 dbcsr_finalize 27 5.7 0.000 0.000 0.480 0.551 dbcsr_merge_all 18 6.5 0.076 0.090 0.416 0.496 make_images_data 18 8.0 0.000 0.001 0.379 0.450 hybrid_alltoall_any 18 9.0 0.029 0.117 0.321 0.418 ------------------------------------------------------------------------------- Plot: name="dbcsr_timings_32omp", title="Timings of dbcsr with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32omp", name="rest", label="rest", y=7.209000000000003, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=37.62, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.126, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.404, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.781, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.029, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=1.8859999999999992, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.245, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.672, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.857, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.563, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.076, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.072, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.78, 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 0.067 0.067 134.709 134.709 qs_mol_dyn_low 1 2.0 0.004 0.004 133.308 133.308 velocity_verlet 5 3.0 0.003 0.003 108.767 108.767 qmmm_el_coupling 6 3.8 0.000 0.000 88.184 88.184 qmmm_elec_with_gaussian 6 4.8 0.013 0.013 88.174 88.174 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.501 87.501 qmmm_elec_gaussian_low_G 6 6.8 86.559 86.559 86.559 86.559 qs_forces 6 3.8 0.001 0.001 36.774 36.774 qs_energies 6 4.8 0.000 0.000 32.479 32.479 scf_env_do_scf 6 5.8 0.001 0.001 30.058 30.058 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 26.221 26.221 rebuild_ks_matrix 45 8.4 0.000 0.000 25.389 25.389 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 25.389 25.389 qs_ks_update_qs_env 45 7.8 0.000 0.000 21.517 21.517 fft_wrap_pw1pw2 801 12.6 0.011 0.011 20.927 20.927 fft_wrap_pw1pw2_150 507 14.2 5.379 5.379 20.411 20.411 qs_vxc_create 45 10.4 0.001 0.001 15.596 15.596 xc_vxc_pw_create 45 11.4 0.635 0.635 15.596 15.596 xc_pw_derive 270 13.4 0.002 0.002 11.676 11.676 fft3d_s 802 14.6 8.151 8.151 8.159 8.159 xc_pw_divergence 45 12.4 0.001 0.001 8.118 8.118 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.740 7.740 calculate_rho_elec 45 8.9 0.563 0.563 7.740 7.740 xc_rho_set_and_dset_create 45 12.4 0.599 0.599 6.782 6.782 pw_scatter_s 429 14.8 5.663 5.663 5.663 5.663 qmmm_forces 6 3.8 0.002 0.002 5.184 5.184 qmmm_forces_with_gaussian 6 4.8 0.018 0.018 4.862 4.862 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.139 4.139 sum_up_and_integrate 45 10.4 0.000 0.000 4.088 4.088 integrate_v_rspace 45 11.4 0.006 0.006 4.015 4.015 density_rs2pw 45 9.9 0.002 0.002 3.907 3.907 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.879 3.879 init_scf_loop 6 6.8 0.000 0.000 3.832 3.832 qs_ks_ddapc 45 10.4 0.001 0.001 3.444 3.444 qmmm_forces_gaussian_low_G 6 6.8 3.411 3.411 3.411 3.411 grid_collocate_task_list 45 9.9 3.270 3.270 3.270 3.270 pw_integral_ab 2539 7.4 2.817 2.817 2.817 2.817 ------------------------------------------------------------------------------- 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 0.033 0.051 56.350 56.362 qs_mol_dyn_low 1 2.0 0.003 0.006 55.268 55.329 qs_forces 6 3.8 0.001 0.001 40.856 40.856 qs_energies 6 4.8 0.000 0.000 39.059 39.060 scf_env_do_scf 6 5.8 0.000 0.001 38.102 38.103 scf_env_do_scf_inner_loop 113 6.2 0.003 0.019 36.450 36.451 rebuild_ks_matrix 119 8.1 0.000 0.000 26.383 26.411 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.016 26.383 26.411 qs_ks_update_qs_env 119 7.3 0.001 0.001 24.885 24.913 velocity_verlet 5 3.0 0.002 0.004 22.678 22.682 fft_wrap_pw1pw2 2059 12.4 0.033 0.039 16.317 16.817 fft_wrap_pw1pw2_150 1321 13.9 0.544 0.647 15.602 16.026 qs_vxc_create 119 10.1 0.002 0.002 13.074 13.088 xc_vxc_pw_create 119 11.1 0.141 0.219 13.072 13.086 fft3d_ps 2059 14.4 6.380 7.603 12.224 13.051 qs_rho_update_rho_low 119 7.3 0.001 0.001 10.171 10.177 calculate_rho_elec 119 8.3 0.049 0.055 10.171 10.176 xc_pw_derive 714 13.1 0.010 0.012 9.797 10.103 sum_up_and_integrate 119 10.1 0.002 0.002 9.198 9.227 integrate_v_rspace 119 11.1 0.003 0.004 9.146 9.175 qmmm_forces 6 3.8 0.002 0.002 7.333 7.333 qmmm_forces_with_gaussian 6 4.8 0.006 0.006 6.798 7.144 xc_pw_divergence 119 12.1 0.004 0.005 6.375 6.632 xc_rho_set_and_dset_create 119 12.1 0.346 0.454 6.322 6.556 qmmm_el_coupling 6 3.8 0.000 0.000 6.109 6.299 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 6.107 6.297 mp_alltoall_z22v 2059 16.4 4.496 6.252 4.496 6.252 density_rs2pw 119 9.3 0.005 0.006 5.706 5.896 potential_pw2rs 119 12.1 0.006 0.007 5.212 5.232 grid_collocate_task_list 119 9.3 4.263 4.408 4.263 4.408 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.845 3.956 x_to_yz 1095 15.8 0.750 0.883 3.094 3.880 grid_integrate_task_list 119 12.1 3.722 3.852 3.722 3.852 transfer_pw2rs 500 12.8 0.005 0.006 3.607 3.627 yz_to_x 964 15.0 0.552 0.699 2.703 3.622 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.310 3.374 qmmm_forces_gaussian_low_G 6 6.8 3.162 3.241 3.162 3.241 mp_waitany 4028 12.8 2.685 3.233 2.685 3.233 qs_scf_new_mos 113 7.2 0.000 0.001 3.211 3.225 qs_scf_loop_do_ot 113 8.2 0.000 0.001 3.210 3.225 ot_scf_mini 113 9.2 0.001 0.001 3.119 3.129 transfer_rs2pw 488 10.2 0.007 0.009 2.780 2.974 dbcsr_multiply_generic 2588 12.3 0.058 0.060 2.910 2.965 qmmm_elec_gaussian_low_G 6 6.8 2.721 2.789 2.721 2.789 pw_restrict_s3 18 5.8 1.321 1.404 2.388 2.625 transfer_pw2rs_150 125 13.9 0.752 0.960 2.438 2.497 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.011 2.204 pw_prolongate_s3 18 6.8 1.113 1.173 2.011 2.204 transfer_rs2pw_150 125 11.2 0.633 0.839 1.987 2.174 qs_ks_ddapc 119 10.1 0.002 0.002 2.006 2.147 ot_mini 113 10.2 0.001 0.001 2.104 2.119 qs_ot_get_derivative 113 11.2 0.000 0.001 1.846 1.859 mp_sum_d 5826 12.2 1.101 1.751 1.101 1.751 pw_scatter_p 1095 14.8 1.664 1.698 1.664 1.698 init_scf_loop 6 6.8 0.000 0.000 1.649 1.649 pw_gather_p 964 14.0 1.231 1.547 1.231 1.547 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.522 1.522 qs_ot_get_derivative_diag 85 12.0 0.001 0.001 1.461 1.474 pw_integral_ab 2761 7.7 1.012 1.181 1.331 1.416 pw_copy 2027 12.4 1.129 1.358 1.129 1.358 pw_derive 1089 13.4 1.102 1.333 1.102 1.333 mp_sum_dm3 33 5.7 1.263 1.323 1.263 1.323 pw_poisson_solve 125 9.9 0.003 0.003 1.163 1.318 mp_waitall_1 177795 16.4 1.039 1.226 1.039 1.226 ------------------------------------------------------------------------------- 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=22.27600000000001, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.559, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.151, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.663, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=5.379, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.411, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.27, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="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 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=31.062, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.721, 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=0.544, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.162, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.263, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.496, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.38, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.722, yerr=0.0 Summary: Performance test took 34 minutes. Status: OK Removing intermediate container 2ccdfeb6f559 ---> bc7f8091a0ba Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 94d5bf767843 Removing intermediate container 94d5bf767843 ---> 06fcc4c52a8d Step 42/42 : ENTRYPOINT [] ---> Running in 5bf07456c818 Removing intermediate container 5bf07456c818 ---> a7ffbbdbc449 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built a7ffbbdbc449 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: 2024-03-20 09:50:46+00:00