StartDate: 2022-08-07 14:10:16+00:00 CpuId: 32x AMD (unknown model) [Zen 3], 7nm (SMT disabled) CommitSHA: 14402e66624c2ff441df3af4793c978de29437a6 CommitTime: 2022-08-07 15:23:43 +0200 CommitAuthor: Ole Schütt CommitSubject: DBM: Towards better OpenMP of dbm_multiply Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=14402e66624c2ff441df3af4793c978de29437a6 Sending build context to Docker daemon 364.2MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu d19f32bd9e41: Already exists Digest: sha256:34fea4f31bf187bc915536831fd0afc9d214755bf700b5cdb1336c82516d154e Status: Downloaded newer image for ubuntu:22.04 ---> df5de72bdb3b Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 026e35f2a85c Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 61e4cd54df66 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 9302e3cfee49 Step 5/42 : RUN mkdir scripts ---> Using cache ---> ba1db08844ca 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 ---> fab809594389 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 4d9201c3671f Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --mpi-mode=mpich --with-gcc=system --dry-run ---> Using cache ---> e53a0293c6df Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> afb35bc0a424 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 4c2119bc983f Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 75b88bb2fdee Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> bb728cfea322 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> a7418910bfb8 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 349b536fddcb Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 4721383cd370 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> b2f7aa0207f5 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 2c92f4cedb8b Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 13a4fc9928ac Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 85b7dda30a09 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 5b212bad722c Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 43c357bcdbd3 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 026c21581960 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 90ed63e9a45c Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 52136d723933 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 453df275a902 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> d8381a55c4b6 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> a05e67db0553 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 3e4785a034ba Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> e8796bfcc61b Step 30/42 : COPY ./Makefile . ---> Using cache ---> dd99b80c56c3 Step 31/42 : COPY ./src ./src ---> 15ffb616b032 Step 32/42 : COPY ./exts ./exts ---> 123251c0d7d8 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> 5bd37e850aa8 Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/ && echo 'Compiling cp2k...' && source /opt/cp2k-toolchain/install/setup && ( make -j ARCH=local VERSION=psmp &> /dev/null || true ) && ( [ ! -f ./exe/local/cp2k.psmp ] || ldd ./exe/local/cp2k.psmp | grep -q libmpi )" ---> Running in f445c7072cfd './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container f445c7072cfd ---> bfcc1d732ee0 Step 35/42 : COPY ./data ./data ---> 8dfc48619940 Step 36/42 : COPY ./tests ./tests ---> 420511e7538d Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> bac46df29ee2 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 9fdeb7f4037b Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> adf03f3ae4ac Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 98ad1b2ac190 ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 60 input files and 0 errors. ========== Running Performance Test ========== Running H2O-64.inp with 1 threads and 32 ranks... done. Running H2O-64.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.036 0.036 186.187 186.187 qs_mol_dyn_low 1 2.0 0.002 0.002 185.594 185.594 qs_forces 11 3.9 0.001 0.001 185.554 185.554 qs_energies 11 4.9 0.001 0.001 179.565 179.565 scf_env_do_scf 11 5.9 0.001 0.001 167.546 167.546 velocity_verlet 10 3.0 0.002 0.002 129.752 129.752 init_scf_loop 11 6.9 0.000 0.000 92.184 92.184 prepare_preconditioner 11 7.9 0.000 0.000 89.786 89.786 make_preconditioner 11 8.9 0.000 0.000 89.786 89.786 make_full_inverse_cholesky 11 9.9 0.000 0.000 88.654 88.654 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 75.230 75.230 cp_fm_cholesky_invert 11 10.9 62.258 62.258 62.258 62.258 qs_scf_new_mos 108 7.5 0.001 0.001 41.450 41.450 qs_scf_loop_do_ot 108 8.5 0.001 0.001 41.449 41.449 ot_scf_mini 108 9.5 0.002 0.002 39.878 39.878 cp_fm_cholesky_decompose 22 10.9 22.488 22.488 22.488 22.488 qs_ot_get_p 119 10.4 0.001 0.001 22.007 22.007 qs_ot_p2m_diag 50 11.0 0.155 0.155 20.616 20.616 dbcsr_multiply_generic 2286 12.5 0.165 0.165 20.439 20.439 cp_dbcsr_syevd 50 12.0 0.002 0.002 20.168 20.168 rebuild_ks_matrix 119 8.3 0.001 0.001 19.959 19.959 qs_ks_build_kohn_sham_matrix 119 9.3 0.011 0.011 19.958 19.958 cp_fm_diag_elpa 50 13.0 0.000 0.000 19.152 19.152 cp_fm_diag_elpa_base 50 14.0 19.094 19.094 19.152 19.152 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.120 19.120 calculate_rho_elec 119 8.7 0.948 0.948 19.120 19.120 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.353 18.353 grid_collocate_task_list 119 9.7 14.729 14.729 14.729 14.729 ot_mini 108 10.5 0.001 0.001 14.315 14.315 sum_up_and_integrate 119 10.3 0.182 0.182 12.542 12.542 integrate_v_rspace 119 11.3 0.092 0.092 12.360 12.360 make_m2s 4572 13.5 0.045 0.045 11.386 11.386 grid_integrate_task_list 119 12.3 10.464 10.464 10.464 10.464 qs_ot_get_derivative 108 11.5 0.001 0.001 8.745 8.745 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.308 6.308 dbcsr_make_dense_low 5837 15.5 0.096 0.096 6.269 6.269 make_dense_data 5837 16.5 5.183 5.183 6.158 6.158 pw_transfer 1439 11.6 0.055 0.055 5.861 5.861 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.657 5.657 make_images 4572 14.5 2.184 2.184 5.610 5.610 ot_diis_step 108 11.5 0.004 0.004 5.567 5.567 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.358 5.358 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.037 5.037 apply_single 119 13.6 0.000 0.000 5.036 5.036 fft_wrap_pw1pw2_140 487 13.2 0.456 0.456 4.855 4.855 init_scf_run 11 5.9 0.002 0.002 4.840 4.840 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.838 4.838 multiply_cannon 2286 13.5 0.164 0.164 4.780 4.780 multiply_cannon_loop 2286 14.5 0.151 0.151 4.326 4.326 wfi_extrapolate 11 7.9 0.001 0.001 4.276 4.276 multiply_cannon_multrec 2286 15.5 4.121 4.121 4.174 4.174 dbcsr_copy 2102 12.0 0.202 0.202 3.807 3.807 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.021 48.195 48.205 qs_mol_dyn_low 1 2.0 0.004 0.009 48.091 48.095 qs_forces 11 3.9 0.001 0.001 48.029 48.030 qs_energies 11 4.9 0.001 0.001 44.725 44.726 scf_env_do_scf 11 5.9 0.000 0.002 41.063 41.064 scf_env_do_scf_inner_loop 108 6.5 0.002 0.017 37.895 37.896 velocity_verlet 10 3.0 0.001 0.002 28.734 28.736 rebuild_ks_matrix 119 8.3 0.000 0.001 18.472 18.554 qs_ks_build_kohn_sham_matrix 119 9.3 0.013 0.020 18.471 18.553 qs_ks_update_qs_env 119 7.6 0.001 0.001 16.430 16.501 sum_up_and_integrate 119 10.3 0.016 0.018 14.242 14.263 integrate_v_rspace 119 11.3 0.004 0.005 14.226 14.249 qs_rho_update_rho_low 119 7.7 0.000 0.001 14.211 14.223 calculate_rho_elec 119 8.7 0.029 0.031 14.211 14.222 dbcsr_multiply_generic 2286 12.5 0.068 0.083 12.752 12.955 grid_collocate_task_list 119 9.7 8.921 10.813 8.921 10.813 grid_integrate_task_list 119 12.3 8.039 10.634 8.039 10.634 qs_scf_new_mos 108 7.5 0.001 0.001 10.271 10.364 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.271 10.364 multiply_cannon 2286 13.5 0.111 0.131 9.204 9.794 ot_scf_mini 108 9.5 0.002 0.002 9.648 9.736 multiply_cannon_loop 2286 14.5 0.087 0.127 8.640 9.102 mp_waitall_1 169478 16.3 7.985 8.691 7.985 8.691 rs_pw_transfer 974 11.9 0.010 0.012 5.905 6.397 multiply_cannon_metrocomm3 18288 15.5 0.036 0.052 5.105 5.924 ot_mini 108 10.5 0.001 0.009 5.573 5.669 density_rs2pw 119 9.7 0.005 0.007 4.921 5.392 pw_transfer 1439 11.6 0.071 0.090 3.354 3.435 potential_pw2rs 119 12.3 0.006 0.007 3.396 3.422 mp_alltoall_d11v 2130 13.8 2.989 3.403 2.989 3.403 mp_waitany 9880 13.7 2.777 3.354 2.777 3.354 fft_wrap_pw1pw2 1201 12.6 0.008 0.011 3.221 3.303 multiply_cannon_multrec 18288 15.5 2.725 3.169 2.734 3.180 init_scf_loop 11 6.9 0.000 0.000 3.155 3.156 rs_gather_matrices 119 12.3 0.075 0.091 2.750 3.154 qs_ot_get_derivative 108 11.5 0.001 0.001 2.900 2.992 rs_pw_transfer_RS2PW_140 130 11.5 0.245 0.299 2.487 2.980 fft_wrap_pw1pw2_140 487 13.2 0.238 0.316 2.695 2.835 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.522 2.630 apply_single 119 13.6 0.000 0.000 2.522 2.629 ot_diis_step 108 11.5 0.004 0.013 2.616 2.623 init_scf_run 11 5.9 0.000 0.004 2.531 2.531 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.531 2.531 fft3d_ps 1201 14.6 1.128 1.257 2.380 2.480 make_m2s 4572 13.5 0.044 0.056 2.332 2.417 wfi_extrapolate 11 7.9 0.001 0.001 2.277 2.277 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.183 2.193 make_images 4572 14.5 0.115 0.140 2.017 2.089 qs_ot_get_p 119 10.4 0.001 0.001 1.344 1.453 mp_sum_d 4129 12.0 1.087 1.424 1.087 1.424 rs_pw_transfer_PW2RS_140 130 13.9 0.516 0.656 1.341 1.415 mp_alltoall_z22v 1201 16.6 1.016 1.250 1.016 1.250 make_images_data 4572 15.5 0.034 0.044 1.107 1.228 prepare_preconditioner 11 7.9 0.000 0.000 1.173 1.192 make_preconditioner 11 8.9 0.000 0.000 1.173 1.192 mp_sum_l 11218 13.2 0.788 1.123 0.788 1.123 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.068 1.101 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.859 1.090 hybrid_alltoall_any 4725 16.4 0.061 0.210 0.956 1.081 multiply_cannon_metrocomm1 18288 15.5 0.018 0.029 0.523 1.049 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.939 0.989 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.921 0.969 rs_pw_transfer_PW2RS_50 119 14.3 0.253 0.322 0.843 0.967 ------------------------------------------------------------------------------- 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=57.153999999999996, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=62.258, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=22.488, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.094, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.729, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.464, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=17.483999999999998, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.921, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.039, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=2.989, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.985, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.777, 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 0.030 0.030 207.620 207.620 qs_mol_dyn_low 1 2.0 0.002 0.002 206.998 206.998 qs_forces 11 3.9 0.001 0.001 206.954 206.954 qs_energies 11 4.9 0.001 0.001 199.208 199.208 scf_env_do_scf 11 5.9 0.001 0.001 184.942 184.942 velocity_verlet 10 3.0 0.002 0.002 144.105 144.105 init_scf_loop 11 6.9 0.000 0.000 94.425 94.425 scf_env_do_scf_inner_loop 96 6.5 0.009 0.009 90.387 90.387 prepare_preconditioner 11 7.9 0.000 0.000 90.169 90.169 make_preconditioner 11 8.9 0.000 0.000 90.169 90.169 make_full_inverse_cholesky 11 9.9 0.000 0.000 89.033 89.033 cp_fm_cholesky_invert 11 10.9 61.456 61.456 61.456 61.456 qs_scf_new_mos 96 7.5 0.000 0.000 35.795 35.795 qs_scf_loop_do_ot 96 8.5 0.001 0.001 35.795 35.795 ot_scf_mini 96 9.5 0.002 0.002 34.591 34.591 rebuild_ks_matrix 107 8.3 0.000 0.000 33.694 33.694 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.694 33.694 qs_rho_update_rho_low 107 7.7 0.000 0.000 31.145 31.145 calculate_rho_elec 107 8.7 0.861 0.861 31.144 31.144 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.334 30.334 grid_collocate_task_list 107 9.7 27.199 27.199 27.199 27.199 sum_up_and_integrate 107 10.3 0.163 0.163 26.626 26.626 integrate_v_rspace 107 11.3 0.086 0.086 26.463 26.463 grid_integrate_task_list 107 12.3 24.645 24.645 24.645 24.645 cp_fm_cholesky_decompose 22 10.9 23.705 23.705 23.705 23.705 qs_ot_get_p 107 10.4 0.001 0.001 19.280 19.280 qs_ot_p2m_diag 44 11.0 0.138 0.138 18.201 18.201 cp_dbcsr_syevd 44 12.0 0.002 0.002 17.829 17.829 dbcsr_multiply_generic 1966 12.4 0.142 0.142 17.232 17.232 cp_fm_diag_elpa 44 13.0 0.000 0.000 16.366 16.366 cp_fm_diag_elpa_base 44 14.0 16.316 16.316 16.366 16.366 ot_mini 96 10.5 0.001 0.001 12.333 12.333 make_m2s 3932 13.4 0.040 0.040 9.454 9.454 qs_ot_get_derivative 96 11.5 0.001 0.001 7.715 7.715 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.815 6.815 init_scf_run 11 5.9 0.002 0.002 6.400 6.400 scf_env_initial_rho_setup 11 6.9 0.001 0.001 6.398 6.398 wfi_extrapolate 11 7.9 0.001 0.001 5.606 5.606 pw_transfer 1295 11.6 0.051 0.051 5.516 5.516 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.326 5.326 dbcsr_make_dense_low 4961 15.5 0.071 0.071 5.011 5.011 make_dense_data 4961 16.5 4.401 4.401 4.928 4.928 make_images 3932 14.4 1.850 1.850 4.702 4.702 ot_diis_step 96 11.5 0.003 0.003 4.615 4.615 fft_wrap_pw1pw2_140 439 13.2 0.462 0.462 4.589 4.589 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.423 4.423 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.270 4.270 apply_single 107 13.6 0.000 0.000 4.270 4.270 multiply_cannon 1966 13.4 0.161 0.161 4.269 4.269 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.205 4.205 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_nonortho_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.020 82.476 82.487 qs_mol_dyn_low 1 2.0 0.003 0.004 82.370 82.374 qs_forces 11 3.9 0.001 0.001 82.326 82.327 qs_energies 11 4.9 0.001 0.001 76.732 76.736 scf_env_do_scf 11 5.9 0.000 0.002 71.185 71.185 scf_env_do_scf_inner_loop 96 6.5 0.002 0.016 65.960 65.961 velocity_verlet 10 3.0 0.001 0.003 49.014 49.015 rebuild_ks_matrix 107 8.3 0.000 0.000 36.670 36.743 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.019 36.670 36.743 sum_up_and_integrate 107 10.3 0.016 0.018 32.681 32.875 integrate_v_rspace 107 11.3 0.004 0.005 32.665 32.861 qs_ks_update_qs_env 107 7.6 0.001 0.001 32.393 32.454 qs_rho_update_rho_low 107 7.7 0.000 0.001 31.332 31.343 calculate_rho_elec 107 8.7 0.027 0.034 31.332 31.343 grid_integrate_task_list 107 12.3 22.924 26.282 22.924 26.282 grid_collocate_task_list 107 9.7 21.918 25.154 21.918 25.154 dbcsr_multiply_generic 1966 12.4 0.061 0.070 11.730 14.467 rs_pw_transfer 878 11.9 0.009 0.012 10.072 10.987 density_rs2pw 107 9.7 0.004 0.006 9.062 9.973 qs_scf_new_mos 96 7.5 0.000 0.001 9.115 9.180 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.114 9.180 multiply_cannon 1966 13.4 0.101 0.116 8.372 8.739 ot_scf_mini 96 9.5 0.002 0.002 8.559 8.612 multiply_cannon_loop 1966 14.4 0.084 0.103 7.877 8.285 mp_waitany 8968 13.7 7.316 8.280 7.316 8.280 mp_alltoall_d11v 1998 13.7 6.909 7.993 6.909 7.993 rs_pw_transfer_RS2PW_140 118 11.5 0.211 0.240 7.014 7.931 mp_waitall_1 146670 16.2 7.032 7.741 7.032 7.741 rs_gather_matrices 107 12.3 0.065 0.072 6.675 7.717 multiply_cannon_metrocomm3 15728 15.4 0.034 0.043 4.561 5.447 init_scf_loop 11 6.9 0.000 0.000 5.212 5.212 ot_mini 96 10.5 0.001 0.001 5.063 5.134 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.400 4.418 init_scf_run 11 5.9 0.000 0.004 4.373 4.375 scf_env_initial_rho_setup 11 6.9 0.000 0.003 4.372 4.375 wfi_extrapolate 11 7.9 0.001 0.001 3.980 3.980 mp_sum_l 9666 13.1 0.920 3.676 0.920 3.676 potential_pw2rs 107 12.3 0.005 0.006 3.025 3.044 pw_transfer 1295 11.6 0.067 0.076 2.956 3.009 fft_wrap_pw1pw2 1081 12.6 0.008 0.010 2.834 2.880 multiply_cannon_multrec 15728 15.4 2.555 2.797 2.564 2.807 qs_ot_get_derivative 96 11.5 0.001 0.001 2.707 2.766 fft_wrap_pw1pw2_140 439 13.2 0.222 0.273 2.396 2.480 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.271 2.375 apply_single 107 13.6 0.000 0.000 2.271 2.375 ot_diis_step 96 11.5 0.003 0.003 2.337 2.337 fft3d_ps 1081 14.6 1.026 1.126 2.051 2.133 make_m2s 3932 13.4 0.040 0.048 2.045 2.104 make_images 3932 14.4 0.103 0.115 1.759 1.833 ------------------------------------------------------------------------------- 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=54.29900000000001, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=61.456, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.199, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.645, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=23.705, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=16.316, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_nonortho_timings_32mpi", title="Timings of H2O-64_nonortho with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="rest", label="rest", y=16.376999999999995, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.918, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.924, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=7.316, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=6.909, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.032, 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 0.176 0.176 149.330 149.330 qs_energies 1 2.0 0.000 0.000 148.541 148.541 scf_env_do_scf 1 3.0 0.000 0.000 147.389 147.389 qs_ks_update_qs_env 8 5.0 0.000 0.000 111.218 111.218 rebuild_ks_matrix 7 6.0 0.000 0.000 111.163 111.163 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 111.163 111.163 hfx_ks_matrix 7 8.0 0.000 0.000 93.989 93.989 integrate_four_center 7 9.0 1.285 1.285 93.964 93.964 init_scf_loop 1 4.0 0.000 0.000 82.700 82.700 integrate_four_center_main 7 10.0 0.864 0.864 81.599 81.599 integrate_four_center_bin 453 11.0 80.735 80.735 80.735 80.735 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 64.678 64.678 prepare_preconditioner 1 5.0 0.000 0.000 30.565 30.565 make_preconditioner 1 6.0 0.000 0.000 30.565 30.565 arnoldi_normal_ev 11 9.3 0.001 0.001 17.724 17.724 estimate_cond_num 1 7.0 0.000 0.000 17.670 17.670 build_subspace 28 9.5 0.008 0.008 17.547 17.547 integrate_four_center_load 7 10.0 0.001 0.001 10.832 10.832 hfx_load_balance 1 11.0 0.001 0.001 10.832 10.832 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 9.129 9.129 dbcsr_sym_m_v_mult 562 10.0 0.014 0.014 8.819 8.819 make_full_inverse_cholesky 1 7.0 0.000 0.000 8.572 8.572 cp_fm_cholesky_invert 2 9.5 8.309 8.309 8.309 8.309 admm_fit_mo_coeffs 7 9.0 0.000 0.000 7.877 7.877 DGKS_ortho_d 673 10.6 6.989 6.989 6.991 6.991 Gram_Schmidt_ortho_d 673 10.6 5.675 5.675 5.676 5.676 hfx_load_balance_count 1 12.0 5.417 5.417 5.417 5.417 hfx_load_balance_bin 1 12.0 5.398 5.398 5.398 5.398 dbcsr_copy 1321 10.8 1.243 1.243 4.693 4.693 purify_mo_diag 7 10.0 0.000 0.000 4.405 4.405 qs_scf_new_mos 7 5.0 0.000 0.000 4.286 4.286 qs_scf_loop_do_ot 7 6.0 0.000 0.000 4.286 4.286 ot_scf_mini 7 7.0 0.000 0.000 4.201 4.201 make_full_single_inverse 1 7.0 0.000 0.000 4.149 4.149 arnoldi_generalized_ev 1 8.0 0.000 0.000 4.038 4.038 gev_build_subspace 4 9.0 0.004 0.004 3.929 3.929 cp_fm_syevd 7 11.0 0.000 0.000 3.914 3.914 cp_fm_syevd_base 7 12.0 3.913 3.913 3.913 3.913 qs_vxc_create 14 8.0 0.000 0.000 3.761 3.761 xc_vxc_pw_create 14 9.0 0.118 0.118 3.761 3.761 dbcsr_create_new 3179 12.1 2.230 2.230 3.581 3.581 fit_mo_coeffs 7 10.0 0.000 0.000 3.472 3.472 dbcsr_set 2825 11.8 0.003 0.003 3.248 3.248 dbcsr_zero 2837 12.8 3.246 3.246 3.246 3.246 cp_fm_cholesky_decompose 3 8.7 3.005 3.005 3.005 3.005 xc_rho_set_and_dset_create 14 10.0 0.094 0.094 3.004 3.004 ------------------------------------------------------------------------------- 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 0.202 0.226 132.101 132.115 qs_energies 1 2.0 0.000 0.001 131.784 131.785 scf_env_do_scf 1 3.0 0.000 0.000 131.407 131.407 qs_ks_update_qs_env 8 5.0 0.000 0.000 129.281 129.281 rebuild_ks_matrix 7 6.0 0.000 0.000 129.273 129.273 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 129.273 129.273 hfx_ks_matrix 7 8.0 0.000 0.000 123.149 123.152 integrate_four_center 7 9.0 0.051 0.333 123.141 123.143 integrate_four_center_main 7 10.0 0.003 0.003 79.578 111.234 integrate_four_center_bin 448 11.0 79.575 111.231 79.575 111.231 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 74.949 74.949 init_scf_loop 1 4.0 0.000 0.000 56.457 56.457 mp_sync 70 11.3 31.672 33.986 31.672 33.986 integrate_four_center_load 7 10.0 0.000 0.000 11.212 11.215 hfx_load_balance 1 11.0 0.001 0.001 11.212 11.215 mp_sum_l 1135 8.3 5.569 5.868 5.569 5.868 hfx_load_balance_dist 1 12.0 0.000 0.000 5.412 5.672 hfx_load_balance_bin 1 12.0 2.862 5.574 2.862 5.574 hfx_load_balance_count 1 12.0 2.860 5.560 2.860 5.560 qs_vxc_create 14 8.0 0.000 0.000 2.903 2.904 xc_vxc_pw_create 14 9.0 0.008 0.009 2.903 2.903 ------------------------------------------------------------------------------- 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=36.807000000000016, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.735, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=8.309, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="DGKS_ortho_d", label="DGKS_ortho_d", y=6.989, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="Gram_Schmidt_ortho_d", label="Gram_Schmidt_ortho_d", y=5.675, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.417, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.398, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="H2O-hyb_timings_32mpi", title="Timings of H2O-hyb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32mpi", name="rest", label="rest", y=9.563000000000002, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=79.575, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="DGKS_ortho_d", label="DGKS_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="Gram_Schmidt_ortho_d", label="Gram_Schmidt_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.86, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.862, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=31.672, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=5.569, 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 0.012 0.012 149.585 149.585 qs_energies 1 2.0 0.000 0.000 149.220 149.220 mp2_main 1 3.0 0.000 0.000 123.900 123.900 mp2_gpw_main 1 4.0 0.000 0.000 122.916 122.916 rpa_ri_compute_en 1 5.0 0.000 0.000 115.907 115.907 rpa_num_int 1 6.0 0.001 0.001 115.901 115.901 compute_mat_P_omega 1 7.0 0.003 0.003 65.431 65.431 compute_mat_P_omega_contract 10 8.0 8.375 8.375 65.244 65.244 dbt_total 2336 9.6 0.011 0.011 53.183 53.183 dbt_contract 787 11.0 0.033 0.033 46.809 46.809 dbt_tas_total 1149 12.2 0.241 0.241 45.570 45.570 dbt_tas_multiply 807 12.1 0.002 0.002 44.285 44.285 dbt_tas_dbm 807 14.1 0.003 0.003 37.590 37.590 dbm_multiply 807 16.1 37.582 37.582 37.582 37.582 compute_W_cubic_GW 10 7.0 0.004 0.004 32.582 32.582 cp_fm_cholesky_invert 10 8.0 31.775 31.775 31.775 31.775 dbt_tas_mm_1N 524 15.1 0.001 0.001 26.606 26.606 scf_env_do_scf 1 3.0 0.000 0.000 25.083 25.083 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 25.083 25.083 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 24.065 24.065 qs_scf_new_mos 17 5.0 0.000 0.000 23.485 23.485 eigensolver 18 5.9 0.001 0.001 21.478 21.478 compute_mat_P_omega_calc_M_occ 250 9.0 8.375 8.375 17.544 17.544 cp_fm_diag_elpa 18 6.9 0.000 0.000 14.537 14.537 cp_fm_diag_elpa_base 18 7.9 14.500 14.500 14.537 14.537 cp_fm_cholesky_decompose 14 8.1 12.644 12.644 12.644 12.644 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 11.380 11.380 compute_Erpa_by_freq_int 10 8.0 0.001 0.001 10.565 10.565 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 10.128 10.128 dbt_tas_mm_2 251 15.0 0.001 0.001 9.056 9.056 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 7.003 7.003 cp_fm_cholesky_restore 51 7.0 6.891 6.891 6.891 6.891 compute_QP_energies 1 7.0 0.000 0.000 5.575 5.575 compute_self_energy_cubic_gw 1 8.0 0.046 0.046 5.575 5.575 get_2c_integrals 1 6.0 0.000 0.000 5.485 5.485 dbt_copy 1103 10.7 0.103 0.103 5.073 5.073 contract_cubic_gw 21 9.0 0.000 0.000 4.614 4.614 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.024 31.314 31.326 qs_energies 1 2.0 0.000 0.000 31.211 31.212 mp2_main 1 3.0 0.000 0.001 30.253 30.254 mp2_gpw_main 1 4.0 0.000 0.000 30.218 30.219 rpa_ri_compute_en 1 5.0 0.000 0.000 28.984 28.985 rpa_num_int 1 6.0 0.000 0.002 28.984 28.984 dbt_total 2336 9.6 0.011 0.017 25.745 25.766 compute_mat_P_omega 1 7.0 0.001 0.005 24.624 24.648 compute_mat_P_omega_contract 10 8.0 0.387 0.431 24.491 24.497 dbt_contract 787 11.0 0.024 0.028 19.414 19.422 dbt_tas_total 1149 12.2 0.049 0.067 17.413 17.413 dbt_tas_multiply 807 12.1 0.002 0.002 17.357 17.359 dbt_tas_dbm 807 14.1 0.003 0.003 12.564 12.577 dbm_multiply 807 16.1 9.654 10.407 9.654 10.407 compute_mat_P_omega_calc_M_occ 250 9.0 0.368 0.412 7.325 7.325 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.221 7.222 mp_sync 8706 11.6 4.916 6.200 4.916 6.200 dbt_tas_mm_2 251 15.0 0.001 0.001 5.944 5.950 dbt_copy 1111 10.7 0.011 0.012 5.409 5.828 dbt_reshape 1098 11.7 2.054 2.687 5.142 5.518 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.180 5.188 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.433 4.724 compute_QP_energies 1 7.0 0.000 0.000 2.800 2.801 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 2.799 2.800 mp_waitall_2 3776 15.3 2.579 2.787 2.579 2.787 dbt_communicate_buffer 1098 12.7 0.054 0.079 2.445 2.590 contract_cubic_gw 21 9.0 0.000 0.000 2.224 2.224 dbt_reserve_blocks_index_array 2791 12.2 0.009 0.011 1.454 1.674 dbt_reserve_blocks_index 2849 13.1 0.060 0.072 1.453 1.673 dbt_tas_reserve_blocks_index 3300 14.5 0.115 0.151 1.426 1.646 dbt_crop 1042 12.0 0.860 1.108 1.312 1.621 dbm_reserve_blocks 3696 15.4 1.397 1.619 1.397 1.619 dbt_tas_replicate 396 14.1 0.528 0.915 1.407 1.556 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.231 1.232 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.990 0.995 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.925 0.931 cp_gemm 105 8.4 0.000 0.000 0.912 0.923 cp_gemm_cosma 105 9.4 0.911 0.923 0.911 0.923 scf_env_do_scf 1 3.0 0.000 0.000 0.920 0.920 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.920 0.920 convert_to_new_pgrid 2421 14.1 0.026 0.039 0.764 0.891 dbm_copy 1608 15.1 0.734 0.858 0.734 0.858 mp_max_i 1992 9.8 0.627 0.835 0.627 0.835 compute_W_cubic_GW 10 7.0 0.001 0.001 0.716 0.720 dbm_add 807 14.1 0.588 0.695 0.588 0.695 dbt_tas_communicate_buffer 792 16.5 0.024 0.032 0.560 0.638 ------------------------------------------------------------------------------- Plot: name="GW_PBE_4benzene_timings_32omp", title="Timings of GW_PBE_4benzene with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="rest", label="rest", y=44.709, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=37.582, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=31.775, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=14.5, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=12.644, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.375, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="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=10.326999999999998, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.654, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.387, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.397, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.054, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.916, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.579, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.017 0.017 342.011 342.011 qs_forces 1 2.0 0.000 0.000 341.455 341.455 rebuild_ks_matrix 7 6.6 0.000 0.000 319.559 319.559 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 319.559 319.559 hfx_ks_matrix 7 8.6 0.000 0.000 317.555 317.555 hfx_ri_update_ks 7 9.6 0.000 0.000 265.317 265.317 hfx_ri_update_ks_Pmat 7 10.6 31.472 31.472 265.315 265.315 dbt_total 4861 11.6 0.027 0.027 263.493 263.493 qs_energies 1 3.0 0.000 0.000 255.414 255.414 scf_env_do_scf 1 4.0 0.000 0.000 254.957 254.957 dbt_tas_total 2391 14.1 1.115 1.115 236.327 236.327 qs_ks_update_qs_env 8 6.0 0.000 0.000 233.567 233.567 dbt_contract 1473 13.0 0.112 0.112 217.113 217.113 dbt_tas_multiply 1482 14.0 0.004 0.004 207.141 207.141 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.004 189.069 189.069 dbt_tas_dbm 1482 16.0 0.005 0.005 185.634 185.634 dbm_multiply 1482 18.0 185.617 185.617 185.617 185.617 dbt_tas_mm_2 649 17.1 0.004 0.004 160.272 160.272 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 143.093 143.093 init_scf_loop 2 5.0 0.000 0.000 111.862 111.862 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 85.995 85.995 hfx_ri_update_forces 1 7.0 0.000 0.000 52.236 52.236 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 37.309 37.309 dbt_tas_reshape 906 14.4 0.040 0.040 21.770 21.770 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 20.491 20.491 prepare_preconditioner 2 6.0 0.000 0.000 18.943 18.943 make_preconditioner 2 7.0 0.000 0.000 18.481 18.481 dbt_tas_mm_3T 659 17.1 0.002 0.002 18.325 18.325 cp_fm_syevd 12 10.7 0.000 0.000 18.071 18.071 cp_fm_syevd_base 12 11.7 18.071 18.071 18.071 18.071 make_full_all 2 8.0 0.000 0.000 18.007 18.007 dbt_copy 2331 12.4 0.262 0.262 17.155 17.155 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 15.443 15.443 dbt_tas_merge 649 14.1 12.565 12.565 13.734 13.734 dbt_tas_reshape_buffer_fill 906 15.4 13.166 13.166 13.166 13.166 precalc_derivatives 1 8.0 0.005 0.005 11.988 11.988 dbm_reserve_blocks 8303 16.8 10.881 10.881 10.881 10.881 dbt_tas_reserve_blocks_index 7397 16.0 0.340 0.340 10.339 10.339 dbt_crop 2763 14.2 6.790 6.790 9.776 9.776 dbt_reshape 856 13.9 5.359 5.359 9.468 9.468 hfx_ri_pre_scf_Pmat_2c 1 13.0 0.000 0.000 8.870 8.870 dbt_reserve_blocks_index 4998 15.2 0.117 0.117 7.708 7.708 dbt_reserve_blocks_index_array 4963 14.3 0.017 0.017 7.654 7.654 ------------------------------------------------------------------------------- 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 0.005 0.021 56.202 56.212 qs_forces 1 2.0 0.000 0.000 56.007 56.007 rebuild_ks_matrix 7 6.6 0.000 0.000 55.320 55.323 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 55.320 55.323 hfx_ks_matrix 7 8.6 0.000 0.001 54.379 54.388 dbt_total 4861 11.6 0.024 0.029 49.062 49.099 dbt_contract 1473 13.0 0.086 0.102 37.843 37.864 hfx_ri_update_ks 7 9.6 0.000 0.000 37.704 37.704 hfx_ri_update_ks_Pmat 7 10.6 1.345 1.818 37.703 37.704 dbt_tas_total 2391 14.1 0.107 0.138 35.758 35.769 qs_energies 1 3.0 0.000 0.003 34.531 34.532 scf_env_do_scf 1 4.0 0.000 0.001 34.389 34.389 qs_ks_update_qs_env 8 6.0 0.000 0.000 33.859 33.862 dbt_tas_multiply 1482 14.0 0.004 0.005 31.830 31.835 dbt_tas_dbm 1482 16.0 0.004 0.006 24.212 24.250 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 21.462 21.463 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.004 21.231 21.232 dbm_multiply 1482 18.0 16.190 20.142 16.190 20.142 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 20.132 20.132 hfx_ri_update_forces 1 7.0 0.000 0.000 16.674 16.683 mp_sync 17513 13.6 12.396 15.715 12.396 15.715 dbt_tas_mm_2 649 17.1 0.003 0.003 14.831 14.870 init_scf_loop 2 5.0 0.000 0.000 14.256 14.256 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 11.624 11.635 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 7.421 7.421 dbt_copy 2349 12.4 0.028 0.031 5.997 6.480 dbt_crop 2763 14.2 2.865 3.729 3.509 4.465 dbt_reshape 1256 13.5 1.996 2.469 4.162 4.449 dbt_tas_mm_3T 659 17.1 0.001 0.002 3.701 4.258 precalc_derivatives 1 8.0 0.001 0.002 3.894 3.895 dbt_tas_mm_3N 163 16.5 0.000 0.000 3.770 3.856 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.733 3.733 dbt_tas_merge 649 14.1 1.527 2.119 2.594 3.129 mp_waitall_2 5988 16.5 2.740 2.951 2.740 2.951 dbm_reserve_blocks 8337 16.9 1.980 2.290 1.980 2.290 mp_max_i 3372 12.5 1.831 2.290 1.831 2.290 dbt_tas_reserve_blocks_index 7428 16.1 0.250 0.330 1.911 2.264 dbt_tas_replicate 909 15.6 0.573 0.730 2.117 2.226 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.000 0.000 2.095 2.107 dbt_tas_communicate_buffer 1825 16.3 0.058 0.074 1.904 2.076 dbt_reserve_blocks_index_array 5363 14.2 0.012 0.016 1.609 1.875 dbt_reserve_blocks_index 5398 15.2 0.105 0.127 1.611 1.875 build_3c_derivatives 9 9.0 0.227 0.344 1.788 1.790 mp_alltoall_i 4339 15.3 1.559 1.748 1.559 1.748 dbt_tas_reshape 916 14.4 0.008 0.010 1.616 1.713 dbt_communicate_buffer 1256 14.5 0.042 0.057 1.455 1.562 mp_sum_l 38201 15.3 1.178 1.449 1.178 1.449 convert_to_new_pgrid 4446 16.0 0.035 0.045 1.138 1.363 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.001 0.002 1.358 1.359 dbm_copy 3043 16.9 1.102 1.328 1.102 1.328 ------------------------------------------------------------------------------- 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=68.971, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=185.617, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.472, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="cp_fm_syevd_base", label="cp_fm_syevd_base", y=18.071, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=13.166, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_merge", label="dbt_tas_merge", y=12.565, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_crop", label="dbt_crop", y=6.79, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=5.359, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=17.142999999999994, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=16.19, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.345, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="cp_fm_syevd_base", label="cp_fm_syevd_base", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_merge", label="dbt_tas_merge", y=1.527, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_crop", label="dbt_crop", y=2.865, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=1.996, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=12.396, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.74, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.014 0.014 234.195 234.195 qs_energies 1 2.0 0.000 0.000 234.016 234.016 mp2_main 1 3.0 0.000 0.000 197.618 197.618 mp2_gpw_main 1 4.0 0.001 0.001 193.626 193.626 mp2_ri_gpw_compute_in 1 5.0 0.368 0.368 143.550 143.550 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 117.838 117.838 mp2_eri_3c_integrate_gpw 2656 7.0 0.012 0.012 91.453 91.453 integrate_v_rspace 2666 8.0 0.704 0.704 77.537 77.537 grid_integrate_task_list 2666 9.0 74.652 74.652 74.652 74.652 mp2_ri_gpw_compute_en 1 5.0 0.076 0.076 50.052 50.052 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.900 9.900 48.365 48.365 scf_env_do_scf 1 3.0 0.000 0.000 35.367 35.367 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 35.366 35.366 qs_scf_new_mos 10 5.0 0.000 0.000 34.110 34.110 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.112 2.112 31.225 31.225 offload_gemm 2080 8.0 29.112 29.112 29.112 29.112 eigensolver 11 5.8 0.001 0.001 25.992 25.992 get_2c_integrals 1 6.0 0.000 0.000 25.323 25.323 calculate_wavefunction 5312 9.0 17.240 17.240 25.255 25.255 cp_fm_diag_elpa 11 6.8 0.000 0.000 23.393 23.393 cp_fm_diag_elpa_base 11 7.8 23.246 23.246 23.393 23.393 dbcsr_multiply_generic 5322 8.0 0.185 0.185 20.468 20.468 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.379 20.379 compute_2c_integrals 1 7.0 0.005 0.005 19.633 19.633 compute_2c_integrals_loop_lm 1 8.0 0.013 0.013 19.614 19.614 mp2_eri_2c_integrate_gpw 1 9.0 3.287 3.287 19.601 19.601 pw_transfer 63872 10.6 0.990 0.990 12.147 12.147 fft_wrap_pw1pw2 53228 11.4 0.115 0.115 10.831 10.831 multiply_cannon 5322 9.0 0.409 0.409 10.087 10.087 qs_diis_b_step 9 6.0 0.000 0.000 9.669 9.669 multiply_cannon_loop 5322 10.0 0.235 0.235 8.744 8.744 cp_fm_symm 18 7.0 8.490 8.490 8.490 8.490 make_m2s 10644 9.0 0.060 0.060 8.302 8.302 make_images 10644 10.0 3.176 3.176 7.924 7.924 fft_wrap_pw1pw2_20 21271 12.4 0.695 0.695 7.650 7.650 multiply_cannon_multrec 5322 11.0 7.055 7.055 7.091 7.091 fft3d_s 53229 13.4 6.825 6.825 6.860 6.860 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.115 2.115 5.905 5.905 mp2_ri_gpw_compute_en_ener 2080 7.0 5.439 5.439 5.439 5.439 cp_fm_triangular_invert 2 6.0 5.131 5.131 5.131 5.131 copy_dbcsr_to_fm 2679 8.0 0.024 0.024 4.821 4.821 ------------------------------------------------------------------------------- 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 0.005 0.021 39.842 39.853 qs_energies 1 2.0 0.000 0.000 39.776 39.776 mp2_main 1 3.0 0.000 0.001 37.525 37.526 mp2_gpw_main 1 4.0 0.001 0.001 37.392 37.392 mp2_ri_gpw_compute_in 1 5.0 0.043 0.043 17.502 22.839 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.799 21.138 mp2_ri_gpw_compute_en 1 5.0 0.157 0.167 19.815 20.265 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.893 19.200 integrate_v_rspace 93 8.1 0.096 0.110 13.841 19.036 grid_integrate_task_list 93 9.1 13.465 18.729 13.465 18.729 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.675 0.803 13.429 13.439 mp2_ri_gpw_compute_en_expansio 65 7.0 0.064 0.084 10.083 10.404 offload_gemm 65 8.0 10.018 10.334 10.018 10.334 mp_min_d 2 7.0 5.384 5.898 5.384 5.898 mp2_ri_get_integ_group_size 1 6.0 0.000 0.000 5.339 5.789 mp2_ri_gpw_compute_en_comm 17 7.0 0.086 0.137 2.352 2.703 mp_sendrecv_dm3 510 8.0 1.825 2.342 1.825 2.342 scf_env_do_scf 1 3.0 0.000 0.000 2.123 2.124 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 2.123 2.123 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.637 1.858 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.620 1.844 get_2c_integrals 1 6.0 0.000 0.000 1.629 1.661 compute_2c_integrals 1 7.0 0.002 0.004 1.369 1.390 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 0.967 1.309 mp2_eri_2c_integrate_gpw 1 9.0 0.204 0.348 0.966 1.307 qs_scf_new_mos 10 5.0 0.000 0.000 1.043 1.119 calculate_wavefunction 166 9.0 0.483 0.685 0.838 1.080 multiply_cannon 176 9.0 0.014 0.021 0.982 1.062 eigensolver 11 5.8 0.001 0.001 1.031 1.033 multiply_cannon_loop 176 10.0 0.002 0.002 0.927 1.006 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.870 0.871 cp_fm_redistribute_end 11 7.8 0.328 0.861 0.342 0.864 multiply_cannon_multrec 246 11.0 0.806 0.850 0.811 0.856 pw_transfer 2120 10.5 0.037 0.048 0.751 0.847 cp_fm_diag_elpa_base 11 7.8 0.508 0.821 0.519 0.835 ------------------------------------------------------------------------------- Plot: name="RI-MP2_ammonia_timings_32omp", title="Timings of RI-MP2_ammonia with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="rest", label="rest", y=72.98999999999998, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=74.652, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="offload_gemm", label="offload_gemm", y=29.112, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=23.246, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=17.24, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=9.9, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.055, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_min_d", label="mp_min_d", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 Plot: name="RI-MP2_ammonia_timings_32mpi", title="Timings of RI-MP2_ammonia with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="rest", label="rest", y=6.677999999999997, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.465, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="offload_gemm", label="offload_gemm", y=10.018, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.508, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.483, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=0.675, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.806, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_min_d", label="mp_min_d", y=5.384, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.825, 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 0.074 0.074 218.394 218.394 qs_energies 1 2.0 0.000 0.000 217.097 217.097 scf_env_do_scf 1 3.0 0.000 0.000 207.434 207.434 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 207.434 207.434 qs_scf_new_mos 15 5.0 0.000 0.000 133.614 133.614 eigensolver 15 6.0 0.001 0.001 126.117 126.117 cp_fm_diag_elpa 15 7.0 0.000 0.000 113.353 113.353 cp_fm_diag_elpa_base 15 8.0 110.760 110.760 113.353 113.353 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.852 48.852 rebuild_ks_matrix 15 6.0 0.000 0.000 48.644 48.644 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.644 48.644 qs_vxc_create 15 8.0 0.014 0.014 33.559 33.559 calculate_dispersion_nonloc 15 9.0 7.170 7.170 29.380 29.380 pw_transfer 1191 10.0 0.050 0.050 22.395 22.395 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 22.211 22.211 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.772 21.772 calculate_rho_elec 16 6.0 0.216 0.216 21.772 21.772 grid_collocate_task_list 16 7.0 20.468 20.468 20.468 20.468 fft_wrap_pw1pw2_150 765 12.0 3.146 3.146 16.039 16.039 sum_up_and_integrate 15 8.0 0.040 0.040 13.788 13.788 integrate_v_rspace 15 9.0 0.017 0.017 13.747 13.747 grid_integrate_task_list 15 10.0 13.256 13.256 13.256 13.256 cp_fm_cholesky_restore 45 7.0 10.492 10.492 10.492 10.492 fft3d_s 1087 13.0 10.310 10.310 10.317 10.317 pw_scatter_s 585 13.1 6.976 6.976 6.976 6.976 init_scf_run 1 3.0 0.000 0.000 6.242 6.242 fft_wrap_pw1pw2_200 197 12.3 0.623 0.623 5.981 5.981 dbcsr_complete_redistribute 46 8.3 2.142 2.142 5.304 5.304 copy_dbcsr_to_fm 16 5.9 0.000 0.000 5.303 5.303 cp_fm_upper_to_full 30 8.0 4.863 4.863 4.863 4.863 vdW_energy 15 10.0 4.425 4.425 4.425 4.425 gspace_mixing 14 5.0 0.171 0.171 4.404 4.404 ------------------------------------------------------------------------------- From /workspace/artifacts/diag_cu144_broy_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.013 0.026 61.336 61.347 qs_energies 1 2.0 0.000 0.000 61.090 61.091 scf_env_do_scf 1 3.0 0.000 0.001 56.980 56.981 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 56.980 56.981 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.391 24.418 rebuild_ks_matrix 15 6.0 0.000 0.000 24.359 24.386 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.006 24.359 24.386 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.596 20.603 calculate_rho_elec 16 6.0 0.007 0.007 20.596 20.603 grid_collocate_task_list 16 7.0 19.167 19.681 19.167 19.681 sum_up_and_integrate 15 8.0 0.005 0.008 14.006 14.063 integrate_v_rspace 15 9.0 0.001 0.001 14.000 14.060 grid_integrate_task_list 15 10.0 12.727 13.178 12.727 13.178 qs_scf_new_mos 15 5.0 0.000 0.000 12.686 12.774 eigensolver 15 6.0 0.001 0.002 11.693 11.729 qs_vxc_create 15 8.0 0.001 0.001 10.050 10.057 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.374 8.382 cp_fm_diag_elpa_base 15 8.0 8.224 8.254 8.368 8.370 calculate_dispersion_nonloc 15 9.0 0.960 1.785 8.256 8.284 pw_transfer 1191 10.0 0.069 0.082 7.688 7.813 fft_wrap_pw1pw2 1086 11.0 0.010 0.015 7.541 7.707 fft3d_ps 1086 13.0 2.279 2.789 5.974 6.328 fft_wrap_pw1pw2_150 765 12.0 0.232 0.283 5.177 5.267 mp_alltoall_z22v 1086 15.0 3.163 4.071 3.163 4.071 cp_fm_cholesky_restore 45 7.0 3.169 3.238 3.169 3.238 yz_to_x 501 13.9 0.196 0.280 2.389 2.873 qs_energies_init_hamiltonians 1 3.0 0.000 0.001 2.472 2.473 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.146 2.346 fft_wrap_pw1pw2_200 197 12.3 0.160 0.189 2.260 2.331 xc_vxc_pw_create 15 9.0 0.014 0.018 1.793 1.822 rs_pw_transfer 158 9.4 0.001 0.003 1.358 1.607 x_to_yz 585 14.1 0.314 0.356 1.285 1.599 density_rs2pw 16 7.0 0.001 0.001 1.297 1.475 init_scf_run 1 3.0 0.000 0.000 1.402 1.403 build_core_ppnl 1 5.0 1.250 1.385 1.250 1.385 vdW_energy 15 10.0 1.302 1.376 1.302 1.376 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.304 1.305 xc_pw_derive 90 11.0 0.001 0.001 1.209 1.281 ------------------------------------------------------------------------------- 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=53.108000000000004, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=110.76, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.468, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.256, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.492, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.31, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=14.886000000000003, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.224, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.167, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.727, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.169, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.163, yerr=0.0 Running bench_dftb.inp with 1 threads and 32 ranks... done. Running bench_dftb.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/bench_dftb_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.075 0.075 351.444 351.444 qs_energies 1 2.0 0.000 0.000 351.309 351.309 ls_scf 1 3.0 0.000 0.000 350.102 350.102 ls_scf_main 1 4.0 0.002 0.002 337.652 337.652 density_matrix_trs4 11 5.0 0.011 0.011 244.769 244.769 arnoldi_extremal 12 6.1 0.000 0.000 163.742 163.742 arnoldi_normal_ev 12 7.1 0.014 0.014 163.742 163.742 build_subspace 23 8.1 0.083 0.083 161.177 161.177 dbcsr_matrix_vector_mult 652 9.0 0.197 0.197 137.308 137.308 dbcsr_matrix_vector_mult_local 652 10.0 126.102 126.102 126.106 126.106 ls_scf_dm_to_ks 11 5.0 0.000 0.000 87.694 87.694 matrix_ls_to_qs 11 6.0 0.000 0.000 84.476 84.476 dbcsr_multiply_generic 185 6.1 0.858 0.858 73.549 73.549 dbcsr_copy_into_existing 11 7.0 47.166 47.166 47.166 47.166 multiply_cannon 185 7.1 0.323 0.323 44.820 44.820 dbcsr_complete_redistribute 23 7.5 30.088 30.088 40.973 40.973 matrix_decluster 11 7.0 0.000 0.000 37.309 37.309 multiply_cannon_loop 185 8.1 0.271 0.271 32.406 32.406 make_m2s 370 7.1 0.038 0.038 24.372 24.372 make_images 370 8.1 10.468 10.468 22.818 22.818 multiply_cannon_multrec 185 9.1 22.601 22.601 22.805 22.805 dbcsr_finalize 646 7.5 0.188 0.188 14.306 14.306 dbcsr_merge_all 597 8.5 2.203 2.203 13.239 13.239 DGKS_ortho_d 702 9.1 13.023 13.023 13.026 13.026 setup_rec_index_2d 370 8.1 11.978 11.978 11.978 11.978 ls_scf_init_scf 1 4.0 0.000 0.000 11.739 11.739 ls_scf_init_matrix_S 1 5.0 0.000 0.000 11.410 11.410 Gram_Schmidt_ortho_d 702 9.1 11.035 11.035 11.036 11.036 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 10.780 10.780 dbcsr_sort_indices 1103 9.9 10.137 10.137 10.137 10.137 tree_to_linear_d 110 9.4 9.817 9.817 9.817 9.817 calculate_norms 370 9.1 9.329 9.329 9.329 9.329 quick_finalize 395 10.0 0.416 0.416 8.833 8.833 dbcsr_special_finalize 370 9.1 0.002 0.002 8.172 8.172 ------------------------------------------------------------------------------- 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 0.012 0.026 64.338 64.349 qs_energies 1 2.0 0.000 0.000 64.254 64.255 ls_scf 1 3.0 0.000 0.000 64.195 64.196 ls_scf_main 1 4.0 0.000 0.008 61.710 61.711 density_matrix_trs4 11 5.0 0.006 0.017 59.056 59.134 dbcsr_multiply_generic 185 6.1 0.055 0.068 55.169 55.478 multiply_cannon 185 7.1 0.030 0.035 45.513 47.215 multiply_cannon_loop 185 8.1 0.097 0.120 43.202 44.622 multiply_cannon_multrec 1480 9.1 26.722 31.963 26.960 32.279 mp_waitall_1 11936 10.3 14.456 17.790 14.456 17.790 multiply_cannon_metrocomm3 1480 9.1 0.012 0.017 8.334 13.744 multiply_cannon_metrocomm1 1480 9.1 0.007 0.009 3.539 9.678 make_m2s 370 7.1 0.033 0.036 6.419 6.500 make_images 370 8.1 0.618 0.707 6.295 6.376 calculate_norms 2960 9.1 4.218 6.072 4.218 6.072 mp_sum_l 1119 5.6 2.381 3.392 2.381 3.392 arnoldi_extremal 12 6.1 0.000 0.000 3.228 3.246 arnoldi_normal_ev 12 7.1 0.001 0.004 3.227 3.245 build_subspace 23 8.1 0.018 0.024 3.128 3.130 make_images_data 370 9.1 0.009 0.012 2.802 3.059 dbcsr_matrix_vector_mult 652 9.0 0.009 0.042 2.205 2.863 hybrid_alltoall_any 393 9.9 0.170 1.135 2.422 2.629 dbcsr_matrix_vector_mult_local 652 10.0 1.599 2.525 1.601 2.527 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.524 2.388 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.315 2.388 dbcsr_complete_redistribute 23 7.5 1.171 1.606 1.849 2.057 matrix_ls_to_qs 11 6.0 0.000 0.000 1.796 2.019 ls_scf_init_scf 1 4.0 0.000 0.000 1.913 1.918 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.877 1.881 matrix_decluster 11 7.0 0.000 0.000 1.658 1.846 make_images_pack 370 9.1 1.523 1.805 1.526 1.812 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.716 1.718 buffer_matrices_ensure_size 370 8.1 1.207 1.425 1.207 1.425 mp_sum_d 1403 6.7 1.020 1.371 1.020 1.371 dbcsr_finalize 646 7.5 0.007 0.009 1.191 1.316 ------------------------------------------------------------------------------- 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=103.13500000000002, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=126.102, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=47.166, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.088, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.601, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="DGKS_ortho_d", label="DGKS_ortho_d", y=13.023, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.329, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=13.790999999999997, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.599, 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=1.171, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=26.722, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="DGKS_ortho_d", label="DGKS_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.218, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.456, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.381, yerr=0.0 Running dbcsr.inp with 1 threads and 32 ranks... done. Running dbcsr.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/dbcsr_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.007 69.750 69.750 lib_test 1 2.0 0.000 0.000 69.678 69.678 dbcsr_run_tests 3 3.0 0.002 0.002 69.678 69.678 test_multiplies_multiproc 3 4.0 0.001 0.001 54.538 54.538 dbcsr_redistribute 9 5.0 35.673 35.673 37.161 37.161 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.698 15.698 dbcsr_make_random_matrix 9 4.0 12.245 12.245 15.042 15.042 multiply_cannon 9 6.0 0.001 0.001 11.253 11.253 multiply_cannon_loop 9 7.0 0.028 0.028 10.898 10.898 multiply_cannon_multrec 9 8.0 10.870 10.870 10.870 10.870 dbcsr_finalize 27 5.7 0.030 0.030 5.241 5.241 dbcsr_merge_all 18 6.5 1.938 1.938 4.554 4.554 dbcsr_data_release 975 7.6 2.510 2.510 2.510 2.510 tree_to_linear_d 9 7.0 1.801 1.801 1.801 1.801 make_m2s 18 6.0 0.001 0.001 1.480 1.480 make_images 18 7.0 0.517 0.517 1.435 1.435 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.004 0.010 17.451 17.456 lib_test 1 2.0 0.000 0.000 17.424 17.442 dbcsr_run_tests 3 3.0 0.000 0.001 17.420 17.438 test_multiplies_multiproc 3 4.0 0.000 0.002 16.600 16.640 dbcsr_multiply_generic 9 5.0 0.001 0.001 14.795 14.883 multiply_cannon 9 6.0 0.001 0.002 13.086 13.404 multiply_cannon_loop 9 7.0 0.002 0.002 12.808 13.130 multiply_cannon_multrec 72 8.0 10.534 11.570 10.534 11.571 mp_waitall_1 576 9.2 2.581 3.280 2.581 3.280 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.989 2.739 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.278 1.160 mp_sum_l 390 2.5 0.487 1.144 0.487 1.144 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.484 1.140 dbcsr_make_random_matrix 9 4.0 0.661 0.915 0.790 1.002 dbcsr_data_release 444 7.6 0.646 0.734 0.646 0.734 dbcsr_finalize 27 5.7 0.000 0.000 0.597 0.705 make_m2s 18 6.0 0.001 0.001 0.642 0.680 make_images 18 7.0 0.021 0.027 0.639 0.676 dbcsr_destroy 111 5.9 0.000 0.000 0.530 0.636 dbcsr_merge_all 18 6.5 0.087 0.103 0.479 0.578 dbcsr_checksum 6 5.0 0.153 0.522 0.525 0.529 make_images_data 18 8.0 0.000 0.001 0.341 0.436 dbcsr_redistribute 9 5.0 0.223 0.270 0.387 0.415 hybrid_alltoall_any 18 9.0 0.023 0.097 0.301 0.398 mp_sum_d 191 1.2 0.372 0.391 0.372 0.391 dbcsr_data_copy_aa2 18 7.5 0.286 0.380 0.286 0.380 ------------------------------------------------------------------------------- Plot: name="dbcsr_timings_32omp", title="Timings of dbcsr with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32omp", name="rest", label="rest", y=6.514000000000003, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.673, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.245, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.87, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.51, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.938, 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=2.2319999999999993, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.223, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.661, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.534, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.646, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.087, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.487, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.581, yerr=0.0 Running MQAE_single_node.inp with 1 threads and 32 ranks... done. Running MQAE_single_node.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/MQAE_single_node_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.048 0.048 136.228 136.228 qs_mol_dyn_low 1 2.0 0.003 0.003 134.744 134.744 velocity_verlet 5 3.0 0.003 0.003 110.097 110.097 qmmm_el_coupling 6 3.8 0.000 0.000 82.937 82.937 qmmm_elec_with_gaussian 6 4.8 0.078 0.078 82.930 82.930 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 82.182 82.182 qmmm_elec_gaussian_low_G 6 6.8 81.257 81.257 81.257 81.257 qs_forces 6 3.8 0.000 0.000 43.207 43.207 qs_energies 6 4.8 0.000 0.000 39.026 39.026 scf_env_do_scf 6 5.8 0.001 0.001 35.656 35.656 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 25.055 25.055 rebuild_ks_matrix 45 8.4 0.000 0.000 24.294 24.294 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.293 24.293 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.537 20.537 pw_transfer 966 12.3 0.047 0.047 16.609 16.609 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.417 16.417 fft_wrap_pw1pw2_150 507 15.2 2.017 2.017 16.000 16.000 qs_vxc_create 45 10.4 0.001 0.001 13.025 13.025 xc_vxc_pw_create 45 11.4 0.655 0.655 13.024 13.024 init_scf_loop 6 6.8 0.000 0.000 10.596 10.596 xc_pw_derive 270 13.4 0.002 0.002 8.879 8.879 fft3d_s 802 15.6 7.512 7.512 7.527 7.527 prepare_preconditioner 6 7.8 0.000 0.000 7.338 7.338 make_preconditioner 6 8.8 0.000 0.000 6.985 6.985 qs_rho_update_rho_low 45 7.9 0.000 0.000 6.942 6.942 calculate_rho_elec 45 8.9 0.563 0.563 6.942 6.942 xc_rho_set_and_dset_create 45 12.4 0.704 0.704 6.815 6.815 make_full_all 6 9.8 0.001 0.001 6.544 6.544 pw_scatter_s 429 15.8 5.615 5.615 5.615 5.615 xc_pw_divergence 45 12.4 0.001 0.001 5.510 5.510 qmmm_forces 6 3.8 0.001 0.001 5.487 5.487 qmmm_forces_with_gaussian 6 4.8 0.095 0.095 5.155 5.155 pw_integral_ab 2539 7.4 4.309 4.309 4.309 4.309 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.304 4.304 qs_ks_ddapc 45 10.4 0.001 0.001 4.277 4.277 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.764 3.764 cp_fm_diag_elpa 18 11.2 0.000 0.000 3.671 3.671 cp_fm_diag_elpa_base 18 12.2 3.663 3.663 3.671 3.671 qmmm_forces_gaussian_low_G 6 6.8 3.588 3.588 3.588 3.588 grid_collocate_task_list 45 9.9 3.222 3.222 3.222 3.222 density_rs2pw 45 9.9 0.001 0.001 3.157 3.157 sum_up_and_integrate 45 10.4 0.113 0.113 3.014 3.014 pw_poisson_solve 51 9.9 1.266 1.266 2.965 2.965 integrate_v_rspace 45 11.4 0.012 0.012 2.901 2.901 ------------------------------------------------------------------------------- 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 0.032 0.050 55.966 55.977 qs_mol_dyn_low 1 2.0 0.003 0.004 54.792 54.848 qs_forces 6 3.8 0.000 0.001 39.013 39.013 qs_energies 6 4.8 0.000 0.000 37.237 37.237 scf_env_do_scf 6 5.8 0.000 0.001 36.296 36.297 scf_env_do_scf_inner_loop 113 6.2 0.002 0.015 34.825 34.826 rebuild_ks_matrix 119 8.1 0.000 0.000 25.548 25.558 qs_ks_build_kohn_sham_matrix 119 9.1 0.013 0.018 25.548 25.558 qs_ks_update_qs_env 119 7.3 0.001 0.001 24.056 24.067 velocity_verlet 5 3.0 0.002 0.004 23.190 23.193 pw_transfer 2446 12.3 0.151 0.176 16.200 16.602 fft_wrap_pw1pw2 2059 13.4 0.020 0.024 15.850 16.300 fft_wrap_pw1pw2_150 1321 14.9 1.081 1.334 15.185 15.645 qs_vxc_create 119 10.1 0.002 0.003 12.900 12.910 fft3d_ps 2059 15.4 6.172 7.194 12.042 12.909 xc_vxc_pw_create 119 11.1 0.138 0.210 12.898 12.909 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.485 10.489 calculate_rho_elec 119 8.3 0.048 0.055 10.484 10.488 xc_pw_derive 714 13.1 0.009 0.012 9.728 9.997 sum_up_and_integrate 119 10.1 0.048 0.063 9.267 9.396 integrate_v_rspace 119 11.1 0.003 0.004 9.219 9.345 qmmm_forces 6 3.8 0.002 0.002 7.898 7.899 qmmm_forces_with_gaussian 6 4.8 0.319 0.364 7.116 7.710 xc_rho_set_and_dset_create 119 12.1 0.340 0.716 6.161 7.220 rs_pw_transfer 988 11.5 0.010 0.015 6.960 7.203 qmmm_el_coupling 6 3.8 0.000 0.000 6.767 7.013 qmmm_elec_with_gaussian 6 4.8 0.335 0.392 6.765 7.011 xc_pw_divergence 119 12.1 0.004 0.005 6.351 6.585 density_rs2pw 119 9.3 0.005 0.007 6.060 6.253 mp_alltoall_z22v 2059 17.4 4.617 6.153 4.617 6.153 potential_pw2rs 119 12.1 0.005 0.006 5.261 5.286 grid_collocate_task_list 119 9.3 4.226 4.622 4.226 4.622 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.849 4.147 grid_integrate_task_list 119 12.1 3.346 4.019 3.346 4.019 yz_to_x 964 16.0 0.471 0.654 2.883 3.656 x_to_yz 1095 16.8 0.729 0.890 2.935 3.603 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.305 3.558 qmmm_forces_gaussian_low_G 6 6.8 3.169 3.469 3.169 3.469 mp_waitany 4028 12.8 2.543 3.353 2.543 3.353 qmmm_elec_gaussian_low_G 6 6.8 2.716 2.965 2.716 2.965 rs_pw_transfer_PW2RS_150 125 13.9 1.090 1.340 2.681 2.781 pw_restrict_s3 18 5.8 1.285 1.585 2.322 2.599 rs_pw_transfer_RS2PW_150 125 11.2 0.848 1.074 2.283 2.539 dbcsr_multiply_generic 2588 12.3 0.056 0.069 2.064 2.480 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 1.940 2.179 pw_prolongate_s3 18 6.8 1.085 1.314 1.940 2.179 mp_waitall_1 188862 16.2 1.793 2.115 1.793 2.115 qs_scf_new_mos 113 7.2 0.000 0.000 2.089 2.104 qs_scf_loop_do_ot 113 8.2 0.000 0.000 2.089 2.104 ot_scf_mini 113 9.2 0.001 0.001 2.000 2.009 mp_sum_dm3 33 5.7 1.723 1.875 1.723 1.875 qs_ks_ddapc 119 10.1 0.002 0.002 1.705 1.828 mp_sum_d 5820 12.2 1.089 1.805 1.089 1.805 pw_integral_ab 2761 7.7 1.020 1.188 1.416 1.614 pw_gather_p 964 15.0 1.140 1.572 1.140 1.572 pw_scatter_p 1095 15.8 1.539 1.567 1.539 1.567 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.506 1.506 init_scf_loop 6 6.8 0.000 0.000 1.469 1.469 xc_functional_eval 238 13.1 0.003 0.004 0.729 1.365 ot_mini 113 10.2 0.001 0.001 1.216 1.223 mp_sum_dm 514 5.2 0.808 1.202 0.808 1.202 ------------------------------------------------------------------------------- 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=27.062000000000026, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=81.257, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.512, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.615, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.309, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=3.663, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.588, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.222, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", 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=30.7, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.716, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_scatter_s", label="pw_scatter_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=1.02, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.169, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.226, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.346, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.617, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.172, yerr=0.0 Summary: Performance test took 44 minutes. Status: OK Removing intermediate container 98ad1b2ac190 ---> f532a61b1ae9 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 708dbf2e270a Removing intermediate container 708dbf2e270a ---> bef4fffee4dc Step 42/42 : ENTRYPOINT [] ---> Running in ba79ccfa2c45 Removing intermediate container ba79ccfa2c45 ---> eb59c8bba930 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built eb59c8bba930 Successfully tagged gcr.io/cp2k-org-project/img_cp2k-perf-openmp-arch-14b:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2022-08-07 15:05:17+00:00