StartDate: 2024-04-17 08:11:19+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 1a29073fbcb476dc3ab79655744d12eef97a2b59 CommitTime: 2024-04-16 12:53:47 +0200 CommitAuthor: marcella CommitSubject: E-field restart and output (#3354) #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=1a29073fbcb476dc3ab79655744d12eef97a2b59 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 3c645031de29: Pulling fs layer 3c645031de29: Verifying Checksum 3c645031de29: Download complete 3c645031de29: Pull complete Digest: sha256:1b8d8ff4777f36f19bfe73ee4df61e3a0b789caeff29caa019539ec7c9a57f95 Status: Downloaded newer image for ubuntu:22.04 ---> 7af9ba4f0a47 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 9dd3c38d749f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 85614924da4a Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 7aff2b7aa738 Step 5/42 : RUN mkdir scripts ---> Using cache ---> 396b1dbd6ede 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 ---> 647732b64fd5 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 55700dee0a5a Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 53d4008825ec Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> b7ed63d2aec8 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> ba960a28d000 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 5e0dd371d8da Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> b6411bdd5988 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> a337dd578665 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> a805edf5d445 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 89c3fab60b10 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 11ede4addb4c Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 28d01e379245 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 432ae994d46f Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> aa3695fb1a8a Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 2385437ba30d Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 99c9de45acee Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> f51168b70480 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 0d490d89a462 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> bf61ef83c357 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> f54ba4d1feaf Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 65095d18cd26 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 3909634d023e Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 3050171b81d5 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> b59dffc80ca7 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 5dca7b701d23 Step 31/42 : COPY ./src ./src ---> Using cache ---> d0c9c8a14f50 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> f47711eace6e Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 97761cdad3ee Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/" ---> Running in ddadcc8a832b './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Removing intermediate container ddadcc8a832b ---> 59bf6a93802f Step 35/42 : COPY ./data ./data ---> 828c072f0b59 Step 36/42 : COPY ./tests ./tests ---> 295ec45d58e4 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 75b94908fbb7 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 88083dccf257 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 828cee8b4883 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in d051dbcf5960 ========== 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 0.044 0.044 92.416 92.416 qs_mol_dyn_low 1 2.0 0.003 0.003 91.817 91.817 qs_forces 11 3.9 0.001 0.001 91.774 91.774 qs_energies 11 4.9 0.001 0.001 85.293 85.293 scf_env_do_scf 11 5.9 0.002 0.002 73.618 73.618 velocity_verlet 10 3.0 0.002 0.002 60.681 60.681 scf_env_do_scf_inner_loop 108 6.5 0.013 0.013 58.808 58.808 dbcsr_multiply_generic 2286 12.5 0.194 0.194 22.377 22.377 qs_scf_new_mos 108 7.5 0.001 0.001 21.911 21.911 qs_scf_loop_do_ot 108 8.5 0.001 0.001 21.911 21.911 rebuild_ks_matrix 119 8.3 0.001 0.001 21.683 21.683 qs_ks_build_kohn_sham_matrix 119 9.3 0.014 0.014 21.682 21.682 qs_rho_update_rho_low 119 7.7 0.001 0.001 21.247 21.247 calculate_rho_elec 119 8.7 0.966 0.966 21.247 21.247 ot_scf_mini 108 9.5 0.003 0.003 20.475 20.475 qs_ks_update_qs_env 119 7.6 0.001 0.001 19.800 19.800 grid_collocate_task_list 119 9.7 16.130 16.130 16.130 16.130 init_scf_loop 11 6.9 0.000 0.000 14.571 14.571 sum_up_and_integrate 119 10.3 0.002 0.002 13.818 13.818 integrate_v_rspace 119 11.3 0.109 0.109 13.778 13.778 ot_mini 108 10.5 0.001 0.001 13.504 13.504 make_m2s 4572 13.5 0.048 0.048 11.706 11.706 prepare_preconditioner 11 7.9 0.000 0.000 11.634 11.634 make_preconditioner 11 8.9 0.000 0.000 11.634 11.634 grid_integrate_task_list 119 12.3 11.293 11.293 11.293 11.293 make_full_inverse_cholesky 11 9.9 0.020 0.020 10.308 10.308 qs_ot_get_derivative 108 11.5 0.001 0.001 7.600 7.600 fft_wrap_pw1pw2 1201 11.6 0.011 0.011 7.127 7.127 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.816 6.816 multiply_cannon 2286 13.5 0.200 0.200 6.248 6.248 make_images 4572 14.5 2.449 2.449 6.105 6.105 dbcsr_make_dense_low 5837 15.5 0.084 0.084 6.078 6.078 fft_wrap_pw1pw2_140 487 12.2 0.936 0.936 6.066 6.066 make_dense_data 5837 16.5 5.356 5.356 5.980 5.980 ot_diis_step 108 11.5 0.004 0.004 5.901 5.901 multiply_cannon_loop 2286 14.5 0.049 0.049 5.748 5.748 multiply_cannon_multrec 2286 15.5 5.642 5.642 5.698 5.698 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.455 5.455 apply_single 119 13.6 0.000 0.000 5.454 5.454 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.219 5.219 init_scf_run 11 5.9 0.003 0.003 4.208 4.208 scf_env_initial_rho_setup 11 6.9 0.002 0.002 4.206 4.206 density_rs2pw 119 9.7 0.004 0.004 4.151 4.151 dbcsr_complete_redistribute 329 12.2 1.845 1.845 3.926 3.926 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.753 3.753 dbcsr_copy 2102 12.0 0.239 0.239 3.702 3.702 wfi_extrapolate 11 7.9 0.001 0.001 3.696 3.696 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.556 3.556 dbcsr_copy_into_existing 22 7.9 3.428 3.428 3.428 3.428 qs_create_task_list 11 7.9 0.000 0.000 3.287 3.287 generate_qs_task_list 11 8.9 1.964 1.964 3.287 3.287 qs_ot_get_p 119 10.4 0.001 0.001 3.279 3.279 copy_dbcsr_to_fm 153 11.3 0.003 0.003 3.204 3.204 fft3d_s 1202 13.6 3.080 3.080 3.085 3.085 cp_fm_cholesky_decompose 22 10.9 3.009 3.009 3.009 3.009 cp_fm_cholesky_invert 11 10.9 3.007 3.007 3.007 3.007 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.923 2.923 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.617 2.617 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.579 2.579 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.466 2.466 potential_pw2rs 119 12.3 0.050 0.050 2.376 2.376 qs_ot_get_derivative_taylor 59 13.0 0.002 0.002 2.301 2.301 pw_poisson_solve 119 10.3 0.002 0.002 2.295 2.295 copy_fm_to_dbcsr 176 11.2 0.001 0.001 2.253 2.253 dbcsr_data_release 279532 16.0 2.197 2.197 2.197 2.197 dbcsr_finalize 5186 13.8 0.123 0.123 2.043 2.043 ------------------------------------------------------------------------------- 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 0.011 0.038 49.510 49.528 qs_mol_dyn_low 1 2.0 0.003 0.005 49.374 49.379 qs_forces 11 3.9 0.001 0.002 49.330 49.331 qs_energies 11 4.9 0.001 0.001 46.254 46.256 scf_env_do_scf 11 5.9 0.000 0.002 42.639 42.640 scf_env_do_scf_inner_loop 108 6.5 0.003 0.022 39.409 39.412 velocity_verlet 10 3.0 0.001 0.003 30.616 30.617 rebuild_ks_matrix 119 8.3 0.000 0.001 17.508 17.593 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.017 17.507 17.593 dbcsr_multiply_generic 2286 12.5 0.074 0.077 16.320 16.479 qs_ks_update_qs_env 119 7.6 0.001 0.001 15.590 15.672 qs_scf_new_mos 108 7.5 0.001 0.001 13.447 13.528 qs_scf_loop_do_ot 108 8.5 0.001 0.001 13.446 13.527 qs_rho_update_rho_low 119 7.7 0.001 0.001 13.141 13.161 calculate_rho_elec 119 8.7 0.030 0.032 13.141 13.161 sum_up_and_integrate 119 10.3 0.002 0.002 12.728 12.760 integrate_v_rspace 119 11.3 0.004 0.005 12.706 12.743 ot_scf_mini 108 9.5 0.002 0.003 12.622 12.724 multiply_cannon 2286 13.5 0.140 0.157 11.083 11.556 multiply_cannon_loop 2286 14.5 0.100 0.120 10.299 10.636 grid_collocate_task_list 119 9.7 8.903 9.208 8.903 9.208 mp_waitall_1 158411 16.6 8.429 9.011 8.429 9.011 grid_integrate_task_list 119 12.3 8.590 8.771 8.590 8.771 ot_mini 108 10.5 0.001 0.001 7.461 7.568 multiply_cannon_metrocomm3 18288 15.5 0.046 0.055 6.411 6.850 qs_ot_get_derivative 108 11.5 0.001 0.001 4.221 4.325 density_rs2pw 119 9.7 0.005 0.006 3.759 4.194 multiply_cannon_multrec 18288 15.5 3.453 3.805 3.464 3.817 potential_pw2rs 119 12.3 0.006 0.007 3.517 3.542 fft_wrap_pw1pw2 1201 11.6 0.015 0.019 3.408 3.501 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.295 3.403 apply_single 119 13.6 0.000 0.000 3.294 3.402 ot_diis_step 108 11.5 0.003 0.003 3.216 3.216 init_scf_loop 11 6.9 0.000 0.000 3.210 3.210 make_m2s 4572 13.5 0.046 0.058 2.908 3.023 fft_wrap_pw1pw2_140 487 12.2 0.128 0.153 2.786 2.873 make_images 4572 14.5 0.117 0.127 2.577 2.701 fft3d_ps 1201 13.6 1.159 1.280 2.517 2.671 transfer_pw2rs 487 13.2 0.005 0.007 2.598 2.616 transfer_rs2pw 487 10.6 0.006 0.008 2.135 2.602 init_scf_run 11 5.9 0.000 0.006 2.555 2.555 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.555 2.555 wfi_extrapolate 11 7.9 0.001 0.001 2.328 2.328 mp_waitany 9880 13.7 1.673 2.218 1.673 2.218 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.091 2.101 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 2.018 2.067 qs_ot_get_p 119 10.4 0.001 0.001 1.847 1.982 mp_sum_l 11298 13.2 1.551 1.958 1.551 1.958 transfer_rs2pw_140 130 11.5 0.180 0.211 1.146 1.617 make_images_data 4572 15.5 0.037 0.048 1.318 1.485 transfer_pw2rs_140 130 13.9 0.372 0.480 1.330 1.382 mp_alltoall_z22v 1201 15.6 1.087 1.364 1.087 1.364 prepare_preconditioner 11 7.9 0.000 0.000 1.292 1.310 make_preconditioner 11 8.9 0.000 0.000 1.292 1.310 hybrid_alltoall_any 4725 16.4 0.066 0.214 1.115 1.281 mp_alltoall_d11v 2130 13.8 0.939 1.209 0.939 1.209 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.187 1.201 transfer_pw2rs_50 119 14.3 0.348 0.408 0.955 1.038 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.965 1.018 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 1.007 1.008 mp_sum_d 4139 12.0 0.705 0.993 0.705 0.993 ------------------------------------------------------------------------------- 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=50.567, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=16.13, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=11.293, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.642, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.356, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=3.428, 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=18.461999999999996, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.903, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.59, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.453, 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=1.673, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.429, 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 0.051 0.051 124.351 124.351 qs_mol_dyn_low 1 2.0 0.003 0.003 123.387 123.387 qs_forces 11 3.9 0.001 0.001 123.344 123.344 qs_energies 11 4.9 0.001 0.001 115.092 115.092 scf_env_do_scf 11 5.9 0.002 0.002 100.746 100.746 scf_env_do_scf_inner_loop 96 6.5 0.013 0.013 83.476 83.476 velocity_verlet 10 3.0 0.002 0.002 77.675 77.675 rebuild_ks_matrix 107 8.3 0.001 0.001 37.334 37.334 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.014 37.333 37.333 qs_rho_update_rho_low 107 7.7 0.001 0.001 36.010 36.010 calculate_rho_elec 107 8.7 0.916 0.916 36.009 36.009 qs_ks_update_qs_env 107 7.6 0.001 0.001 34.199 34.199 grid_collocate_task_list 107 9.7 30.868 30.868 30.868 30.868 sum_up_and_integrate 107 10.3 0.002 0.002 28.405 28.405 integrate_v_rspace 107 11.3 0.114 0.114 28.312 28.312 grid_integrate_task_list 107 12.3 25.753 25.753 25.753 25.753 dbcsr_multiply_generic 1966 12.4 0.151 0.151 21.176 21.176 qs_scf_new_mos 96 7.5 0.001 0.001 20.946 20.946 qs_scf_loop_do_ot 96 8.5 0.001 0.001 20.945 20.945 ot_scf_mini 96 9.5 0.003 0.003 19.487 19.487 init_scf_loop 11 6.9 0.000 0.000 16.931 16.931 ot_mini 96 10.5 0.001 0.001 12.573 12.573 prepare_preconditioner 11 7.9 0.000 0.000 12.280 12.280 make_preconditioner 11 8.9 0.000 0.000 12.280 12.280 make_full_inverse_cholesky 11 9.9 0.025 0.025 10.967 10.967 make_m2s 3932 13.4 0.045 0.045 10.948 10.948 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.534 7.534 fft_wrap_pw1pw2 1081 11.6 0.011 0.011 7.404 7.404 qs_ot_get_derivative 96 11.5 0.001 0.001 6.764 6.764 multiply_cannon 1966 13.4 0.195 0.195 6.412 6.412 fft_wrap_pw1pw2_140 439 12.2 0.966 0.966 6.309 6.309 init_scf_run 11 5.9 0.003 0.003 6.072 6.072 scf_env_initial_rho_setup 11 6.9 0.002 0.002 6.070 6.070 multiply_cannon_loop 1966 14.4 0.040 0.040 5.930 5.930 multiply_cannon_multrec 1966 15.4 5.832 5.832 5.889 5.889 make_images 3932 14.4 2.307 2.307 5.860 5.860 ot_diis_step 96 11.5 0.003 0.003 5.805 5.805 dbcsr_make_dense_low 4961 15.5 0.069 0.069 5.385 5.385 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 5.356 5.356 apply_single 107 13.6 0.000 0.000 5.356 5.356 make_dense_data 4961 16.5 4.868 4.868 5.303 5.303 wfi_extrapolate 11 7.9 0.001 0.001 5.269 5.269 dbcsr_make_images_dense 3386 14.7 0.016 0.016 4.762 4.762 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.513 4.513 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.421 4.421 density_rs2pw 107 9.7 0.004 0.004 4.225 4.225 dbcsr_complete_redistribute 317 12.2 1.976 1.976 4.121 4.121 qs_create_task_list 11 7.9 0.000 0.000 3.950 3.950 generate_qs_task_list 11 8.9 2.445 2.445 3.950 3.950 dbcsr_copy 1855 11.9 0.283 0.283 3.869 3.869 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.736 3.736 copy_dbcsr_to_fm 147 11.2 0.003 0.003 3.579 3.579 dbcsr_copy_into_existing 22 7.9 3.528 3.528 3.529 3.529 cp_fm_cholesky_invert 11 10.9 3.262 3.262 3.262 3.262 qs_ot_get_p 107 10.4 0.001 0.001 3.259 3.259 cp_fm_cholesky_decompose 22 10.9 3.241 3.241 3.241 3.241 fft3d_s 1082 13.6 3.175 3.175 3.182 3.182 pw_poisson_solve 107 10.3 0.002 0.002 2.934 2.934 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.660 2.660 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.653 2.653 ------------------------------------------------------------------------------- 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 0.030 83.664 83.676 qs_mol_dyn_low 1 2.0 0.003 0.005 83.508 83.513 qs_forces 11 3.9 0.002 0.003 83.460 83.461 qs_energies 11 4.9 0.001 0.001 77.942 77.948 scf_env_do_scf 11 5.9 0.001 0.002 72.165 72.167 scf_env_do_scf_inner_loop 96 6.5 0.003 0.022 66.420 66.421 velocity_verlet 10 3.0 0.001 0.003 49.370 49.371 rebuild_ks_matrix 107 8.3 0.001 0.001 35.869 35.961 qs_ks_build_kohn_sham_matrix 107 9.3 0.015 0.017 35.868 35.960 qs_ks_update_qs_env 107 7.6 0.001 0.001 31.634 31.721 sum_up_and_integrate 107 10.3 0.002 0.002 30.615 30.665 integrate_v_rspace 107 11.3 0.004 0.005 30.566 30.616 qs_rho_update_rho_low 107 7.7 0.001 0.001 29.160 29.169 calculate_rho_elec 107 8.7 0.029 0.030 29.159 29.168 grid_integrate_task_list 107 12.3 24.280 24.776 24.280 24.776 grid_collocate_task_list 107 9.7 23.123 23.575 23.123 23.575 dbcsr_multiply_generic 1966 12.4 0.077 0.082 15.138 15.282 qs_scf_new_mos 96 7.5 0.001 0.001 12.198 12.318 qs_scf_loop_do_ot 96 8.5 0.001 0.001 12.198 12.317 ot_scf_mini 96 9.5 0.002 0.003 11.450 11.538 multiply_cannon 1966 13.4 0.135 0.148 10.711 10.966 multiply_cannon_loop 1966 14.4 0.086 0.091 10.023 10.324 mp_waitall_1 136719 16.5 7.941 8.338 7.941 8.338 ot_mini 96 10.5 0.001 0.001 6.759 6.849 density_rs2pw 107 9.7 0.004 0.004 5.520 6.331 multiply_cannon_metrocomm3 15728 15.4 0.036 0.039 5.888 6.174 init_scf_loop 11 6.9 0.000 0.000 5.723 5.724 init_scf_run 11 5.9 0.000 0.006 4.456 4.460 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.456 4.460 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.442 4.451 fft_wrap_pw1pw2 1081 11.6 0.012 0.013 4.274 4.337 transfer_rs2pw 439 10.6 0.007 0.007 3.461 4.295 potential_pw2rs 107 12.3 0.006 0.006 4.085 4.094 wfi_extrapolate 11 7.9 0.001 0.001 4.030 4.030 multiply_cannon_multrec 15728 15.4 3.760 3.946 3.773 3.957 mp_waitany 8968 13.7 2.902 3.801 2.902 3.801 fft_wrap_pw1pw2_140 439 12.2 0.178 0.186 3.619 3.690 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.550 3.637 apply_single 107 13.6 0.000 0.000 3.550 3.637 ot_diis_step 96 11.5 0.003 0.003 3.508 3.508 transfer_rs2pw_140 118 11.5 0.342 0.365 2.469 3.317 qs_ot_get_derivative 96 11.5 0.001 0.001 3.225 3.310 mp_alltoall_d11v 1998 13.7 2.529 3.166 2.529 3.166 make_m2s 3932 13.4 0.044 0.048 3.008 3.084 transfer_pw2rs 439 13.2 0.006 0.009 2.919 2.925 fft3d_ps 1081 13.6 1.395 1.496 2.756 2.810 rs_gather_matrices 107 12.3 0.117 0.133 2.147 2.776 make_images 3932 14.4 0.117 0.124 2.637 2.703 transfer_pw2rs_140 118 13.9 0.594 0.651 1.695 1.754 qs_ot_get_p 107 10.4 0.001 0.001 1.567 1.692 prepare_preconditioner 11 7.9 0.000 0.000 1.669 1.689 make_preconditioner 11 8.9 0.000 0.000 1.669 1.689 ------------------------------------------------------------------------------- Plot: name="H2O-64_nonortho_timings_32omp", title="Timings of H2O-64_nonortho with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="rest", label="rest", y=53.501999999999995, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=30.868, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.753, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.832, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.868, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=3.528, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_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=21.657999999999994, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=23.123, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.28, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.76, 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_waitany", label="mp_waitany", y=2.902, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.941, 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 0.237 0.237 144.019 144.019 qs_energies 1 2.0 0.000 0.000 142.977 142.977 scf_env_do_scf 1 3.0 0.000 0.000 141.474 141.474 qs_ks_update_qs_env 8 5.0 0.000 0.000 136.092 136.092 rebuild_ks_matrix 7 6.0 0.000 0.000 135.999 135.999 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 135.998 135.998 hfx_ks_matrix 7 8.0 0.000 0.000 126.136 126.136 integrate_four_center 7 9.0 1.867 1.867 126.082 126.082 integrate_four_center_main 7 10.0 0.777 0.777 111.638 111.638 integrate_four_center_bin 446 11.0 110.861 110.861 110.861 110.861 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 81.432 81.432 init_scf_loop 1 4.0 0.000 0.000 60.033 60.033 integrate_four_center_load 7 10.0 0.001 0.001 12.253 12.253 hfx_load_balance 1 11.0 0.013 0.013 12.252 12.252 hfx_load_balance_count 1 12.0 6.136 6.136 6.136 6.136 hfx_load_balance_bin 1 12.0 6.086 6.086 6.086 6.086 qs_vxc_create 14 8.0 0.000 0.000 3.788 3.788 xc_vxc_pw_create 14 9.0 0.126 0.126 3.787 3.787 ------------------------------------------------------------------------------- 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 0.199 0.227 141.475 141.487 qs_energies 1 2.0 0.000 0.000 141.055 141.066 scf_env_do_scf 1 3.0 0.000 0.000 140.633 140.633 qs_ks_update_qs_env 8 5.0 0.000 0.000 138.107 138.108 rebuild_ks_matrix 7 6.0 0.000 0.000 138.094 138.095 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 138.094 138.095 hfx_ks_matrix 7 8.0 0.000 0.000 131.451 131.452 integrate_four_center 7 9.0 0.070 0.365 131.438 131.439 integrate_four_center_main 7 10.0 0.004 0.004 111.220 117.610 integrate_four_center_bin 448 11.0 111.217 117.606 111.217 117.606 scf_env_do_scf_inner_loop 7 4.0 0.000 0.002 84.109 84.109 init_scf_loop 1 4.0 0.000 0.000 56.522 56.522 mp_sync 56 11.2 6.907 13.486 6.907 13.486 integrate_four_center_load 7 10.0 0.000 0.000 12.566 12.568 hfx_load_balance 1 11.0 0.001 0.001 12.566 12.568 hfx_load_balance_bin 1 12.0 6.212 6.302 6.212 6.302 hfx_load_balance_count 1 12.0 6.182 6.260 6.182 6.260 ------------------------------------------------------------------------------- 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=18.055000000000007, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=110.861, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.136, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.086, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.867, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.777, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.237, 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=10.683999999999997, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=111.217, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.182, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.212, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.07, 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=0.199, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=6.907, 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 0.018 0.018 99.235 99.235 qs_energies 1 2.0 0.000 0.000 98.647 98.647 mp2_main 1 3.0 0.000 0.000 95.364 95.364 mp2_gpw_main 1 4.0 0.000 0.000 95.244 95.244 rpa_ri_compute_en 1 5.0 0.000 0.000 91.284 91.284 rpa_num_int 1 6.0 0.002 0.002 91.276 91.276 compute_mat_P_omega 1 7.0 0.004 0.004 80.291 80.291 compute_mat_P_omega_contract 10 8.0 14.180 14.180 80.041 80.041 dbt_total 2336 9.6 0.020 0.020 56.127 56.127 dbt_contract 787 11.0 0.103 0.103 47.213 47.213 dbt_tas_total 1149 12.2 0.342 0.342 45.206 45.206 dbt_tas_multiply 807 12.1 0.003 0.003 43.723 43.723 dbt_tas_dbm 807 14.1 0.004 0.004 36.288 36.288 dbm_multiply 807 16.1 36.277 36.277 36.277 36.277 dbt_tas_mm_1N 524 15.1 0.002 0.002 26.710 26.710 compute_mat_P_omega_calc_M_occ 250 9.0 14.234 14.234 25.016 25.016 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 24.528 24.528 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 9.096 9.096 dbt_tas_mm_2 251 15.0 0.002 0.002 7.832 7.832 dbt_copy 1103 10.7 0.176 0.176 7.404 7.404 compute_QP_energies 1 7.0 0.000 0.000 6.032 6.032 compute_self_energy_cubic_gw 1 8.0 0.053 0.053 6.030 6.030 dbt_tas_reserve_blocks_index 3261 14.3 0.500 0.500 4.675 4.675 contract_cubic_gw 21 9.0 0.000 0.000 4.551 4.551 dbm_reserve_blocks 3628 15.3 4.247 4.247 4.247 4.247 mp2_ri_gpw_compute_in 1 5.0 0.002 0.002 3.951 3.951 dbt_reserve_blocks_index 2280 13.1 0.078 0.078 3.520 3.520 dbt_reserve_blocks_index_array 2222 12.2 0.010 0.010 3.458 3.458 dbt_crop 1042 12.0 1.926 1.926 3.285 3.285 scf_env_do_scf 1 3.0 0.000 0.000 3.112 3.112 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 3.111 3.111 dbt_tas_copy 574 11.4 1.685 1.685 2.950 2.950 dbt_reshape 278 11.9 1.452 1.452 2.494 2.494 convert_to_new_pgrid 2421 14.1 0.161 0.161 2.351 2.351 dbt_tas_reshape 367 15.0 0.018 0.018 2.240 2.240 dbm_copy 1614 15.1 2.191 2.191 2.191 2.191 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 2.022 2.022 ------------------------------------------------------------------------------- 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 0.010 0.034 47.010 47.021 qs_energies 1 2.0 0.000 0.000 46.815 46.819 mp2_main 1 3.0 0.000 0.001 45.580 45.584 mp2_gpw_main 1 4.0 0.000 0.001 45.437 45.442 rpa_ri_compute_en 1 5.0 0.000 0.001 43.951 43.955 rpa_num_int 1 6.0 0.000 0.003 43.950 43.954 dbt_total 2336 9.6 0.022 0.024 38.938 38.947 compute_mat_P_omega 1 7.0 0.001 0.006 37.706 37.744 compute_mat_P_omega_contract 10 8.0 0.557 0.590 37.487 37.491 dbt_contract 787 11.0 0.055 0.056 28.212 28.220 dbt_tas_total 1149 12.2 0.106 0.110 24.625 24.628 dbt_tas_multiply 807 12.1 0.003 0.003 24.556 24.559 dbt_tas_dbm 807 14.1 0.004 0.005 17.836 17.841 dbm_multiply 807 16.1 14.251 15.215 14.251 15.215 compute_mat_P_omega_calc_M_occ 250 9.0 0.522 0.560 11.199 11.200 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 10.911 10.920 dbt_copy 1149 10.8 0.020 0.023 8.807 9.285 dbt_reshape 1136 11.8 3.510 3.727 8.403 8.872 dbt_tas_mm_2 251 15.0 0.002 0.002 8.428 8.431 mp_sync 8688 11.6 7.106 8.390 7.106 8.390 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 7.457 7.457 dbt_tas_mm_1N 524 15.1 0.002 0.002 6.434 7.039 mp_waitall_2 3812 15.3 3.668 4.067 3.668 4.067 dbt_communicate_buffer 1136 12.8 0.056 0.066 3.661 3.965 compute_QP_energies 1 7.0 0.000 0.000 3.937 3.939 compute_self_energy_cubic_gw 1 8.0 0.003 0.004 3.936 3.937 contract_cubic_gw 21 9.0 0.000 0.000 3.058 3.059 dbt_reserve_blocks_index 2887 13.1 0.086 0.093 2.585 2.895 dbt_reserve_blocks_index_array 2829 12.2 0.011 0.012 2.571 2.880 dbt_tas_reserve_blocks_index 3347 14.5 0.445 0.478 2.562 2.866 dbm_reserve_blocks 3752 15.4 2.244 2.517 2.244 2.517 dbt_crop 1042 12.0 1.206 1.325 2.030 2.295 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.002 1.624 1.631 mp2_ri_gpw_compute_in 1 5.0 0.004 0.006 1.476 1.477 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.449 1.454 dbt_tas_replicate 405 14.1 0.614 0.797 1.343 1.442 parallel_gemm_fm 105 8.4 0.000 0.000 1.365 1.386 parallel_gemm_fm_cosma 105 9.4 1.365 1.385 1.365 1.385 mp_max_i 2009 9.8 1.126 1.380 1.126 1.380 convert_to_new_pgrid 2421 14.1 0.031 0.035 1.205 1.364 dbm_copy 1608 15.1 1.166 1.326 1.166 1.326 scf_env_do_scf 1 3.0 0.000 0.000 1.176 1.176 scf_env_do_scf_inner_loop 17 4.0 0.001 0.003 1.176 1.176 compute_W_cubic_GW 10 7.0 0.001 0.001 1.040 1.052 ------------------------------------------------------------------------------- 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=26.653999999999996, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=36.277, 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=14.234, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=14.18, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=4.247, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.191, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.452, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=13.985999999999997, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=14.251, 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=0.522, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.557, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.244, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=1.166, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.51, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.668, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=7.106, 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 0.022 0.022 244.950 244.950 qs_forces 1 2.0 0.000 0.000 244.401 244.401 rebuild_ks_matrix 7 6.6 0.000 0.000 242.749 242.749 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 242.749 242.749 hfx_ks_matrix 7 8.6 0.000 0.000 240.533 240.533 hfx_ri_update_ks 7 9.6 0.000 0.000 195.346 195.346 hfx_ri_update_ks_Pmat 7 10.6 37.412 37.412 195.341 195.341 dbt_total 849 11.0 0.008 0.008 177.673 177.673 qs_energies 1 3.0 0.000 0.000 174.590 174.590 scf_env_do_scf 1 4.0 0.001 0.001 174.227 174.227 qs_ks_update_qs_env 8 6.0 0.000 0.000 172.992 172.992 dbt_contract 207 12.4 0.081 0.081 154.947 154.947 dbt_tas_total 369 13.4 1.752 1.752 153.020 153.020 dbt_tas_multiply 216 13.5 0.001 0.001 148.637 148.637 dbt_tas_dbm 216 15.5 0.001 0.001 136.111 136.111 dbm_multiply 216 17.5 136.108 136.108 136.108 136.108 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 127.758 127.758 dbt_tas_mm_2 91 16.5 0.001 0.001 118.409 118.409 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 103.561 103.561 init_scf_loop 2 5.0 0.000 0.000 70.664 70.664 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 69.762 69.762 hfx_ri_update_forces 1 7.0 1.679 1.679 45.184 45.184 hfx_ri_forces_Pmat_3c 1 8.0 4.902 4.902 26.445 26.445 dbt_copy 423 11.8 0.138 0.138 18.333 18.333 precalc_derivatives 1 8.0 2.386 2.386 14.718 14.718 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 12.404 12.404 dbt_reshape 132 13.2 7.937 7.937 12.348 12.348 dbt_tas_mm_3T 77 17.1 0.000 0.000 11.927 11.927 dbt_tas_reserve_blocks_index 1323 15.4 1.017 1.017 8.811 8.811 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 8.310 8.310 build_3c_derivatives 3 9.0 2.515 2.515 8.179 8.179 dbm_reserve_blocks 1491 16.2 8.011 8.011 8.011 8.011 dbt_reserve_blocks_index 846 14.4 0.124 0.124 6.782 6.782 dbt_reserve_blocks_index_array 816 13.5 0.009 0.009 6.669 6.669 dbt_crop 372 13.7 3.460 3.460 5.811 5.811 dbt_tas_mm_3N 37 15.4 0.000 0.000 5.287 5.287 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 5.281 5.281 ------------------------------------------------------------------------------- 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 0.009 0.051 58.693 58.712 qs_forces 1 2.0 0.000 0.000 58.469 58.470 rebuild_ks_matrix 7 6.6 0.000 0.000 57.658 57.659 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.002 57.658 57.659 hfx_ks_matrix 7 8.6 0.000 0.000 56.281 56.290 dbt_total 849 11.0 0.007 0.007 50.467 50.502 dbt_contract 207 12.4 0.027 0.029 39.207 39.228 dbt_tas_total 369 13.4 0.073 0.186 35.407 35.419 dbt_tas_multiply 216 13.5 0.001 0.001 34.766 34.780 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 33.237 33.238 hfx_ri_update_forces 1 7.0 0.078 0.083 29.303 29.312 hfx_ri_update_ks 7 9.6 0.000 0.000 26.978 26.978 hfx_ri_update_ks_Pmat 7 10.6 1.231 1.293 26.974 26.974 dbt_tas_dbm 216 15.5 0.001 0.001 25.527 25.538 qs_energies 1 3.0 0.000 0.000 25.222 25.222 scf_env_do_scf 1 4.0 0.000 0.001 25.049 25.049 qs_ks_update_qs_env 8 6.0 0.000 0.000 24.423 24.423 dbm_multiply 216 17.5 23.203 23.882 23.203 23.882 hfx_ri_forces_Pmat_3c 1 8.0 0.231 0.258 22.668 22.683 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 14.024 14.024 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 12.275 12.275 init_scf_loop 2 5.0 0.000 0.000 11.024 11.024 dbt_tas_mm_2 91 16.5 0.001 0.001 10.162 10.172 dbt_copy 539 12.5 0.014 0.016 9.820 10.076 dbt_tas_mm_3T 77 17.1 0.000 0.000 7.563 7.963 dbt_reshape 393 13.9 3.859 4.113 7.427 7.631 mp_sync 2901 12.8 5.683 7.044 5.683 7.044 dbt_tas_mm_3N 37 15.4 0.000 0.000 5.774 5.967 precalc_derivatives 1 8.0 0.103 0.113 5.013 5.013 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.835 4.836 mp_waitall_2 1318 16.2 3.549 3.735 3.549 3.735 dbt_tas_reserve_blocks_index 1471 15.8 0.900 0.930 3.417 3.689 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.439 3.439 dbm_reserve_blocks 1641 16.6 2.809 3.064 2.809 3.064 dbt_reserve_blocks_index 1107 14.8 0.116 0.122 2.801 3.018 dbt_reserve_blocks_index_array 1077 13.9 0.006 0.006 2.768 2.982 build_3c_derivatives 3 9.0 0.241 0.304 2.842 2.848 dbt_crop 372 13.7 1.788 1.836 2.582 2.665 dbt_communicate_buffer 393 14.9 0.014 0.015 2.301 2.436 dbt_tas_replicate 170 15.1 0.868 0.911 2.281 2.349 convert_to_new_pgrid 648 15.5 0.051 0.099 1.652 1.911 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.702 1.706 dbm_copy 452 16.3 1.417 1.675 1.417 1.675 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.624 1.625 dbt_tas_copy 146 12.6 0.763 0.804 1.424 1.533 dbt_tas_communicate_buffer 370 16.3 0.012 0.013 1.393 1.456 mp_sum_l 6385 13.7 1.221 1.314 1.221 1.314 ------------------------------------------------------------------------------- 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=50.579999999999984, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=136.108, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=37.412, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=8.011, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=7.937, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.902, 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=18.127999999999993, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=23.203, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.231, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.809, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.859, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.231, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=5.683, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.549, 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 0.017 188.257 188.257 qs_energies 1 2.0 0.000 0.000 188.023 188.023 mp2_main 1 3.0 0.000 0.000 182.285 182.285 mp2_gpw_main 1 4.0 0.002 0.002 181.882 181.882 mp2_ri_gpw_compute_in 1 5.0 0.491 0.491 127.688 127.688 mp2_ri_gpw_compute_in_loop 1 6.0 0.016 0.016 119.128 119.128 mp2_eri_3c_integrate_gpw 2656 7.0 0.020 0.020 87.116 87.116 integrate_v_rspace 2666 8.0 0.728 0.728 73.568 73.568 grid_integrate_task_list 2666 9.0 70.393 70.393 70.393 70.393 mp2_ri_gpw_compute_en 1 5.0 0.096 0.096 54.167 54.167 mp2_ri_gpw_compute_en_RI_loop 1 6.0 11.523 11.523 51.688 51.688 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.578 2.578 31.135 31.135 local_gemm 2080 8.0 28.557 28.557 28.557 28.557 dbcsr_multiply_generic 5322 8.0 0.241 0.241 24.678 24.678 ao_to_mo_and_store_B_mult_1 2656 7.0 0.015 0.015 24.657 24.657 multiply_cannon 5322 9.0 0.627 0.627 12.761 12.761 calculate_wavefunction 2656 8.0 8.146 8.146 12.090 12.090 fft_wrap_pw1pw2 53228 10.4 0.128 0.128 11.553 11.553 multiply_cannon_loop 5322 10.0 0.260 0.260 11.070 11.070 make_m2s 10644 9.0 0.076 0.076 9.238 9.238 multiply_cannon_multrec 5322 11.0 8.884 8.884 8.934 8.934 make_images 10644 10.0 3.460 3.460 8.854 8.854 fft_wrap_pw1pw2_20 21271 11.4 0.728 0.728 8.304 8.304 get_2c_integrals 1 6.0 0.000 0.000 8.068 8.068 compute_2c_integrals 1 7.0 0.027 0.027 7.500 7.500 compute_2c_integrals_loop_lm 1 8.0 0.016 0.016 7.458 7.458 mp2_eri_2c_integrate_gpw 1 9.0 0.893 0.893 7.442 7.442 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 3.201 3.201 7.193 7.193 mp2_ri_gpw_compute_en_ener 2080 7.0 6.564 6.564 6.564 6.564 fft3d_s 53229 12.4 6.463 6.463 6.501 6.501 scf_env_do_scf 1 3.0 0.000 0.000 5.243 5.243 scf_env_do_scf_inner_loop 10 4.0 0.002 0.002 5.243 5.243 copy_dbcsr_to_fm 2679 8.0 0.036 0.036 4.799 4.799 potential_pw2rs 5322 10.0 0.187 0.187 4.384 4.384 ------------------------------------------------------------------------------- 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 45.225 45.236 qs_energies 1 2.0 0.000 0.000 45.066 45.067 mp2_main 1 3.0 0.000 0.001 42.827 42.827 mp2_gpw_main 1 4.0 0.002 0.002 42.710 42.710 mp2_ri_gpw_compute_in 1 5.0 0.045 0.046 22.664 23.119 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 20.982 21.421 mp2_ri_gpw_compute_en 1 5.0 0.262 0.271 19.968 20.236 mp2_ri_gpw_compute_en_RI_loop 1 6.0 2.867 3.293 18.640 18.645 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 17.576 17.793 integrate_v_rspace 93 8.1 0.311 0.332 17.193 17.390 grid_integrate_task_list 93 9.1 16.624 16.829 16.624 16.829 mp2_ri_gpw_compute_en_expansio 65 7.0 0.126 0.140 12.036 12.223 local_gemm 65 8.0 11.910 12.092 11.910 12.092 dbcsr_multiply_generic 176 8.0 0.009 0.010 2.962 3.289 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 2.943 3.269 mp2_ri_gpw_compute_en_comm 17 7.0 0.091 0.116 2.856 3.238 mp_sendrecv_dm3 1054 8.0 2.309 2.743 2.309 2.743 scf_env_do_scf 1 3.0 0.000 0.000 2.086 2.087 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 2.086 2.087 get_2c_integrals 1 6.0 0.005 0.012 1.615 1.641 make_m2s 352 9.0 0.003 0.004 1.464 1.634 make_images 352 10.0 0.063 0.067 1.450 1.620 multiply_cannon 176 9.0 0.020 0.021 1.443 1.596 multiply_cannon_loop 176 10.0 0.002 0.003 1.376 1.529 compute_2c_integrals 1 7.0 0.003 0.004 1.223 1.237 multiply_cannon_multrec 246 11.0 1.083 1.174 1.090 1.182 compute_2c_integrals_loop_lm 1 8.0 0.001 0.002 1.086 1.141 mp2_eri_2c_integrate_gpw 1 9.0 0.224 0.241 1.085 1.141 fft_wrap_pw1pw2 1768 10.4 0.005 0.020 1.037 1.083 qs_scf_new_mos 10 5.0 0.000 0.000 0.989 0.995 mp2_ri_gpw_compute_en_ener 65 7.0 0.849 0.919 0.849 0.919 eigensolver 11 5.8 0.001 0.001 0.916 0.918 ------------------------------------------------------------------------------- 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=60.754000000000005, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=70.393, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=28.557, 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=11.523, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.884, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.146, 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=10.432000000000002, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=16.624, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=11.91, 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=2.867, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=1.083, 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=2.309, 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 0.135 0.135 132.631 132.631 qs_energies 1 2.0 0.000 0.000 130.700 130.700 scf_env_do_scf 1 3.0 0.000 0.000 123.396 123.396 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 123.396 123.396 qs_ks_update_qs_env 15 5.0 0.000 0.000 55.705 55.705 rebuild_ks_matrix 15 6.0 0.000 0.000 55.491 55.491 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 55.491 55.491 qs_scf_new_mos 15 5.0 0.000 0.000 43.054 43.054 qs_vxc_create 15 8.0 0.019 0.019 39.348 39.348 eigensolver 15 6.0 0.002 0.002 35.555 35.555 calculate_dispersion_nonloc 15 9.0 6.941 6.941 34.082 34.082 fft_wrap_pw1pw2 1086 10.0 0.016 0.016 29.482 29.482 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.636 22.636 cp_fm_diag_elpa_base 15 8.0 20.074 20.074 22.636 22.636 fft_wrap_pw1pw2_150 765 11.0 6.868 6.868 21.302 21.302 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.149 21.149 calculate_rho_elec 16 6.0 0.234 0.234 21.149 21.149 grid_collocate_task_list 16 7.0 19.002 19.002 19.002 19.002 sum_up_and_integrate 15 8.0 0.000 0.000 15.071 15.071 integrate_v_rspace 15 9.0 0.020 0.020 15.060 15.060 grid_integrate_task_list 15 10.0 14.338 14.338 14.338 14.338 fft3d_s 1087 12.0 11.233 11.233 11.241 11.241 cp_fm_cholesky_restore 45 7.0 10.616 10.616 10.616 10.616 fft_wrap_pw1pw2_200 197 11.3 1.762 1.762 7.730 7.730 pw_scatter_s 585 12.1 7.522 7.522 7.522 7.522 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.384 5.384 dbcsr_complete_redistribute 46 8.3 1.987 1.987 5.250 5.250 xc_vxc_pw_create 15 9.0 0.206 0.206 5.247 5.247 cp_fm_upper_to_full 30 8.0 4.863 4.863 4.863 4.863 gspace_mixing 14 5.0 0.171 0.171 4.674 4.674 vdW_energy 15 10.0 4.431 4.431 4.431 4.431 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.138 4.138 broyden_mixing 14 6.0 4.014 4.014 4.014 4.014 xc_pw_derive 90 11.0 0.001 0.001 3.814 3.814 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.898 2.898 ------------------------------------------------------------------------------- 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 0.016 0.042 66.150 66.169 qs_energies 1 2.0 0.000 0.000 65.789 65.798 scf_env_do_scf 1 3.0 0.000 0.001 61.283 61.284 scf_env_do_scf_inner_loop 15 4.0 0.001 0.004 61.283 61.284 qs_ks_update_qs_env 15 5.0 0.000 0.000 27.890 27.900 rebuild_ks_matrix 15 6.0 0.000 0.000 27.840 27.850 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 27.840 27.850 qs_rho_update_rho_low 16 5.0 0.000 0.000 19.120 19.127 calculate_rho_elec 16 6.0 0.007 0.011 19.120 19.126 grid_collocate_task_list 16 7.0 17.872 18.087 17.872 18.087 sum_up_and_integrate 15 8.0 0.000 0.000 15.118 15.149 integrate_v_rspace 15 9.0 0.000 0.001 15.102 15.133 qs_scf_new_mos 15 5.0 0.000 0.000 14.624 14.661 grid_integrate_task_list 15 10.0 14.108 14.392 14.108 14.392 eigensolver 15 6.0 0.001 0.002 13.411 13.425 qs_vxc_create 15 8.0 0.000 0.000 12.260 12.269 calculate_dispersion_nonloc 15 9.0 1.400 1.440 9.982 9.995 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.069 9.073 cp_fm_diag_elpa_base 15 8.0 8.912 8.935 9.061 9.063 fft_wrap_pw1pw2 1086 10.0 0.013 0.015 8.940 9.002 fft3d_ps 1086 12.0 3.011 3.203 5.856 6.092 fft_wrap_pw1pw2_150 765 11.0 0.166 0.195 6.047 6.085 cp_fm_cholesky_restore 45 7.0 4.170 4.209 4.170 4.209 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.845 2.845 fft_wrap_pw1pw2_200 197 11.3 0.110 0.113 2.765 2.799 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.529 2.742 mp_alltoall_z22v 1086 14.0 2.131 2.640 2.131 2.640 xc_vxc_pw_create 15 9.0 0.034 0.038 2.277 2.294 build_core_ppnl 1 5.0 1.567 1.699 1.567 1.699 x_to_yz 585 13.1 0.404 0.431 1.451 1.663 yz_to_x 501 12.9 0.291 0.347 1.376 1.596 pw_scatter_p 585 12.1 1.498 1.560 1.498 1.560 xc_pw_derive 90 11.0 0.001 0.001 1.499 1.556 vdW_energy 15 10.0 1.476 1.533 1.476 1.533 init_scf_run 1 3.0 0.000 0.001 1.430 1.431 ------------------------------------------------------------------------------- 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=57.367999999999995, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.074, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.002, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.338, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=11.233, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.616, 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=18.077000000000005, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.912, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=17.872, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.108, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=4.17, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=3.011, 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 0.081 0.081 277.345 277.345 qs_energies 1 2.0 0.000 0.000 277.198 277.198 ls_scf 1 3.0 0.000 0.000 275.753 275.753 ls_scf_main 1 4.0 0.002 0.002 264.521 264.521 density_matrix_trs4 11 5.0 0.014 0.014 167.618 167.618 ls_scf_dm_to_ks 11 5.0 0.000 0.000 90.988 90.988 matrix_ls_to_qs 11 6.0 0.000 0.000 87.597 87.597 dbcsr_multiply_generic 185 6.1 0.904 0.904 84.801 84.801 arnoldi_extremal 12 6.1 0.000 0.000 68.168 68.168 arnoldi_normal_ev 12 7.1 0.050 0.050 68.168 68.168 build_subspace 23 8.1 0.084 0.084 66.836 66.836 dbcsr_matrix_vector_mult 652 9.0 0.220 0.220 66.592 66.592 dbcsr_matrix_vector_mult_local 652 10.0 65.067 65.067 65.076 65.076 multiply_cannon 185 7.1 0.537 0.537 49.622 49.622 dbcsr_copy_into_existing 11 7.0 46.271 46.271 46.271 46.271 dbcsr_complete_redistribute 23 7.5 33.337 33.337 45.572 45.572 matrix_decluster 11 7.0 0.000 0.000 41.324 41.324 multiply_cannon_loop 185 8.1 0.264 0.264 36.362 36.362 make_m2s 370 7.1 0.040 0.040 29.793 29.793 make_images 370 8.1 13.083 13.083 27.159 27.159 multiply_cannon_multrec 185 9.1 26.581 26.581 26.633 26.633 dbcsr_finalize 646 7.5 0.318 0.318 16.781 16.781 dbcsr_merge_all 597 8.5 2.701 2.701 15.277 15.277 setup_rec_index_2d 370 8.1 12.459 12.459 12.459 12.459 dbcsr_sort_indices 805 10.1 11.629 11.629 11.629 11.629 tree_to_linear_d 110 9.4 11.106 11.106 11.106 11.106 ls_scf_init_scf 1 4.0 0.000 0.000 10.543 10.543 quick_finalize 395 10.0 0.441 0.441 10.100 10.100 ls_scf_init_matrix_S 1 5.0 0.000 0.000 10.077 10.077 calculate_norms 370 9.1 9.465 9.465 9.465 9.465 dbcsr_special_finalize 370 9.1 0.002 0.002 9.329 9.329 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 9.201 9.201 dbcsr_dot_sd 144 6.3 7.027 7.027 7.028 7.028 matrix_qs_to_ls 12 5.1 0.000 0.000 6.270 6.270 matrix_cluster 12 6.1 0.000 0.000 6.270 6.270 dbcsr_frobenius_norm 142 6.1 5.776 5.776 5.777 5.777 ------------------------------------------------------------------------------- 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 0.016 0.040 72.954 72.973 qs_energies 1 2.0 0.000 0.000 72.826 72.827 ls_scf 1 3.0 0.000 0.000 72.775 72.776 ls_scf_main 1 4.0 0.001 0.010 69.610 69.611 density_matrix_trs4 11 5.0 0.007 0.020 66.867 66.915 dbcsr_multiply_generic 185 6.1 0.063 0.078 63.717 63.959 multiply_cannon 185 7.1 0.036 0.039 52.630 53.171 multiply_cannon_loop 185 8.1 0.120 0.128 50.029 51.142 multiply_cannon_multrec 1480 9.1 30.320 31.877 30.643 32.203 mp_waitall_1 11936 10.3 16.956 19.179 16.956 19.179 multiply_cannon_metrocomm3 1480 9.1 0.015 0.017 12.885 14.878 make_m2s 370 7.1 0.037 0.039 7.315 7.384 make_images 370 8.1 0.652 0.692 7.178 7.235 calculate_norms 2960 9.1 5.245 5.579 5.245 5.579 make_images_data 370 9.1 0.011 0.011 3.270 3.499 mp_sum_l 1199 5.3 2.884 3.259 2.884 3.259 hybrid_alltoall_any 393 9.9 0.246 1.417 2.870 3.035 arnoldi_extremal 12 6.1 0.000 0.001 2.520 2.529 arnoldi_normal_ev 12 7.1 0.002 0.008 2.520 2.529 build_subspace 23 8.1 0.021 0.026 2.423 2.425 ls_scf_init_scf 1 4.0 0.000 0.000 2.425 2.425 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.357 2.414 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 2.040 2.382 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.269 2.298 dbcsr_complete_redistribute 23 7.5 1.286 1.387 2.122 2.233 matrix_ls_to_qs 11 6.0 0.000 0.000 2.050 2.162 dbcsr_matrix_vector_mult 652 9.0 0.014 0.052 2.021 2.159 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.002 2.061 2.064 matrix_decluster 11 7.0 0.000 0.000 1.911 2.026 make_images_pack 370 9.1 1.798 1.895 1.802 1.899 dbcsr_matrix_vector_mult_local 652 10.0 1.640 1.749 1.642 1.751 multiply_cannon_metrocomm1 1480 9.1 0.006 0.007 1.099 1.645 buffer_matrices_ensure_size 370 8.1 1.464 1.592 1.464 1.592 ------------------------------------------------------------------------------- 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=83.54100000000003, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=65.067, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=46.271, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=33.337, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=26.581, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images", label="make_images", y=13.083, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.465, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", 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=12.172999999999988, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.64, 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=1.286, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=30.32, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images", label="make_images", y=0.652, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.245, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.884, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=16.956, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.798, 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 73.387 73.387 lib_test 1 2.0 0.000 0.000 73.373 73.373 dbcsr_run_tests 3 3.0 0.041 0.041 73.373 73.373 test_multiplies_multiproc 3 4.0 0.001 0.001 56.724 56.724 dbcsr_redistribute 9 5.0 37.673 37.673 39.264 39.264 dbcsr_make_random_matrix 9 4.0 12.961 12.961 16.500 16.500 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.091 16.091 multiply_cannon 9 6.0 0.002 0.002 11.213 11.213 multiply_cannon_loop 9 7.0 0.014 0.014 10.851 10.851 multiply_cannon_multrec 9 8.0 10.837 10.837 10.838 10.838 dbcsr_finalize 27 5.7 0.016 0.016 6.109 6.109 dbcsr_merge_all 18 6.5 2.032 2.032 5.387 5.387 dbcsr_data_release 975 7.6 2.726 2.726 2.726 2.726 tree_to_linear_d 9 7.0 1.911 1.911 1.911 1.911 make_m2s 18 6.0 0.001 0.001 1.710 1.710 make_images 18 7.0 0.620 0.620 1.664 1.664 ------------------------------------------------------------------------------- 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 18.428 18.434 lib_test 1 2.0 0.000 0.000 18.388 18.410 dbcsr_run_tests 3 3.0 0.000 0.001 18.383 18.405 test_multiplies_multiproc 3 4.0 0.000 0.002 17.543 17.623 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.817 15.900 multiply_cannon 9 6.0 0.001 0.002 13.858 14.219 multiply_cannon_loop 9 7.0 0.002 0.002 13.586 13.957 multiply_cannon_multrec 72 8.0 10.291 10.754 10.292 10.755 mp_waitall_1 576 9.2 3.604 4.393 3.604 4.393 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 3.179 3.903 mp_sum_l 470 2.5 0.827 1.138 0.827 1.138 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.815 1.125 dbcsr_make_random_matrix 9 4.0 0.672 0.970 0.800 1.097 dbcsr_data_release 444 7.6 0.600 0.714 0.600 0.714 make_m2s 18 6.0 0.001 0.001 0.660 0.705 make_images 18 7.0 0.021 0.024 0.657 0.701 dbcsr_finalize 27 5.7 0.000 0.000 0.503 0.622 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.110 0.614 dbcsr_destroy 111 5.9 0.004 0.063 0.527 0.608 dbcsr_redistribute 9 5.0 0.230 0.269 0.524 0.562 dbcsr_merge_all 18 6.5 0.076 0.093 0.426 0.535 mp_cart_create 9 5.7 0.355 0.426 0.355 0.426 make_images_data 18 8.0 0.000 0.001 0.349 0.425 dbcsr_mp_make_env 6 4.5 0.000 0.000 0.344 0.406 ------------------------------------------------------------------------------- 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=7.158000000000001, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=37.673, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.961, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.837, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.726, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.032, 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=2.128, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.23, 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=10.291, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.6, 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=0.827, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.604, 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 0.061 0.061 134.636 134.636 qs_mol_dyn_low 1 2.0 0.004 0.004 133.230 133.230 velocity_verlet 5 3.0 0.003 0.003 108.709 108.709 qmmm_el_coupling 6 3.8 0.000 0.000 87.879 87.879 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 87.875 87.875 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.251 87.251 qmmm_elec_gaussian_low_G 6 6.8 86.303 86.303 86.303 86.303 qs_forces 6 3.8 0.001 0.001 36.752 36.752 qs_energies 6 4.8 0.000 0.000 32.547 32.547 scf_env_do_scf 6 5.8 0.001 0.001 30.146 30.146 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 26.334 26.334 rebuild_ks_matrix 45 8.4 0.000 0.000 25.312 25.312 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 25.312 25.312 qs_ks_update_qs_env 45 7.8 0.000 0.000 21.661 21.661 fft_wrap_pw1pw2 801 12.6 0.010 0.010 20.869 20.869 fft_wrap_pw1pw2_150 507 14.2 5.509 5.509 20.422 20.422 qs_vxc_create 45 10.4 0.001 0.001 15.655 15.655 xc_vxc_pw_create 45 11.4 0.640 0.640 15.655 15.655 xc_pw_derive 270 13.4 0.002 0.002 11.743 11.743 xc_pw_divergence 45 12.4 0.001 0.001 8.164 8.164 fft3d_s 802 14.6 7.943 7.943 7.951 7.951 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.627 7.627 calculate_rho_elec 45 8.9 0.564 0.564 7.627 7.627 xc_rho_set_and_dset_create 45 12.4 0.574 0.574 6.793 6.793 pw_scatter_s 429 14.8 5.784 5.784 5.784 5.784 qmmm_forces 6 3.8 0.001 0.001 5.335 5.335 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 5.009 5.009 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.125 4.125 sum_up_and_integrate 45 10.4 0.000 0.000 3.895 3.895 density_rs2pw 45 9.9 0.002 0.002 3.885 3.885 integrate_v_rspace 45 11.4 0.007 0.007 3.830 3.830 init_scf_loop 6 6.8 0.000 0.000 3.807 3.807 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.659 3.659 qmmm_forces_gaussian_low_G 6 6.8 3.430 3.430 3.430 3.430 qs_ks_ddapc 45 10.4 0.001 0.001 3.428 3.428 grid_collocate_task_list 45 9.9 3.178 3.178 3.178 3.178 pw_integral_ab 2539 7.4 2.785 2.785 2.785 2.785 ------------------------------------------------------------------------------- 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 0.050 53.974 53.987 qs_mol_dyn_low 1 2.0 0.003 0.005 52.916 52.977 qs_forces 6 3.8 0.001 0.001 38.918 38.918 qs_energies 6 4.8 0.000 0.000 37.144 37.145 scf_env_do_scf 6 5.8 0.000 0.001 36.231 36.231 scf_env_do_scf_inner_loop 113 6.2 0.002 0.020 34.722 34.724 rebuild_ks_matrix 119 8.1 0.000 0.000 25.665 25.674 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.017 25.664 25.674 qs_ks_update_qs_env 119 7.3 0.001 0.001 24.181 24.190 velocity_verlet 5 3.0 0.002 0.003 22.019 22.022 fft_wrap_pw1pw2 2059 12.4 0.032 0.043 15.836 16.338 fft_wrap_pw1pw2_150 1321 13.9 0.521 0.609 15.170 15.601 qs_vxc_create 119 10.1 0.002 0.002 12.714 12.724 xc_vxc_pw_create 119 11.1 0.135 0.202 12.713 12.723 fft3d_ps 2059 14.4 6.129 7.098 11.861 12.712 qs_rho_update_rho_low 119 7.3 0.000 0.001 9.986 9.989 calculate_rho_elec 119 8.3 0.049 0.055 9.986 9.988 xc_pw_derive 714 13.1 0.009 0.012 9.560 9.839 sum_up_and_integrate 119 10.1 0.002 0.002 9.015 9.065 integrate_v_rspace 119 11.1 0.003 0.004 8.965 9.017 qmmm_forces 6 3.8 0.002 0.002 7.138 7.138 qmmm_forces_with_gaussian 6 4.8 0.006 0.006 6.726 6.984 xc_rho_set_and_dset_create 119 12.1 0.340 0.441 6.217 6.430 xc_pw_divergence 119 12.1 0.004 0.005 6.143 6.383 qmmm_el_coupling 6 3.8 0.000 0.000 5.918 6.098 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 5.916 6.097 mp_alltoall_z22v 2059 16.4 4.472 5.811 4.472 5.811 density_rs2pw 119 9.3 0.005 0.007 5.593 5.775 potential_pw2rs 119 12.1 0.005 0.007 5.051 5.074 grid_collocate_task_list 119 9.3 4.208 4.500 4.208 4.500 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.834 3.867 grid_integrate_task_list 119 12.1 3.694 3.796 3.694 3.796 x_to_yz 1095 15.8 0.701 0.820 2.994 3.622 transfer_pw2rs 500 12.8 0.005 0.007 3.541 3.549 yz_to_x 964 15.0 0.515 0.641 2.694 3.545 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.320 3.360 mp_waitany 4028 12.8 2.570 3.269 2.570 3.269 qmmm_forces_gaussian_low_G 6 6.8 3.154 3.187 3.154 3.187 transfer_rs2pw 488 10.2 0.006 0.008 2.727 2.995 qmmm_elec_gaussian_low_G 6 6.8 2.731 2.773 2.731 2.773 pw_restrict_s3 18 5.8 1.301 1.365 2.335 2.565 transfer_pw2rs_150 125 13.9 0.714 0.910 2.356 2.410 qs_scf_new_mos 113 7.2 0.000 0.000 2.317 2.322 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.316 2.322 ot_scf_mini 113 9.2 0.001 0.001 2.229 2.235 transfer_rs2pw_150 125 11.2 0.581 0.762 1.872 2.140 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 1.932 2.115 pw_prolongate_s3 18 6.8 1.096 1.157 1.932 2.115 qs_ks_ddapc 119 10.1 0.002 0.002 1.940 2.082 dbcsr_multiply_generic 2588 12.3 0.057 0.059 1.967 2.020 pw_scatter_p 1095 14.8 1.653 1.712 1.653 1.712 pw_gather_p 964 14.0 1.175 1.644 1.175 1.644 mp_sum_d 5826 12.2 1.066 1.643 1.066 1.643 init_scf_loop 6 6.8 0.000 0.000 1.505 1.505 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.497 1.498 pw_integral_ab 2761 7.7 0.972 1.118 1.297 1.392 pw_copy 2027 12.4 1.097 1.299 1.097 1.299 pw_poisson_solve 125 9.9 0.002 0.003 1.136 1.280 pw_derive 1089 13.4 1.061 1.274 1.061 1.274 ot_mini 113 10.2 0.001 0.001 1.222 1.228 mp_sum_dm3 33 5.7 1.133 1.178 1.133 1.178 mp_waitall_1 177795 16.4 0.973 1.160 0.973 1.160 transfer_pw2rs_40 119 14.1 0.267 0.320 0.976 1.121 ------------------------------------------------------------------------------- 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=22.48899999999999, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.303, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.943, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.784, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=5.509, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.43, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.178, 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=29.064999999999998, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.731, 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=0.521, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.154, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.208, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.694, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.129, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.472, yerr=0.0 Summary: Performance test took 36 minutes. Status: OK Removing intermediate container d051dbcf5960 ---> 904777ec6175 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 787f66938018 Removing intermediate container 787f66938018 ---> 29c3e8a5afac Step 42/42 : ENTRYPOINT [] ---> Running in 75876342b576 Removing intermediate container 75876342b576 ---> 406f2463f251 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 406f2463f251 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: 2024-04-17 09:00:45+00:00