StartDate: 2022-05-20 19:06:11+00:00 CpuId: 12x Intel Xeon W 2000 / D-2100 (Skylake / Cascade Lake) {Skylake}, 14nm GpuId: 1x Tesla V100-SXM2-16GB CommitSHA: 3d29584519424f4e843c9fee160c8d1d89c907b7 CommitTime: 2022-05-20 17:23:57 +0200 CommitAuthor: Matthias Krack CommitSubject: Add serial arch file for Darwin arm64 (Apple M1) Populating docker build cache... done. #################### Building Image cp2k-perf-cuda-volta #################### Dockerfile: /tools/docker/Dockerfile.test_performance_cuda_V100 Build-Path: / Build-Args: GIT_COMMIT_SHA=3d29584519424f4e843c9fee160c8d1d89c907b7 Sending build context to Docker daemon 362.9MB Step 1/44 : FROM nvidia/cuda:11.3.1-devel-ubuntu20.04 11.3.1-devel-ubuntu20.04: Pulling from nvidia/cuda d5fd17ec1767: Already exists 086b79b77a03: Already exists 4698168f5888: Already exists 86de3d566666: Already exists 30d00d530989: Already exists 69a2bfee9a44: Already exists 381964195b8b: Already exists fe1468e51d2b: Already exists e807ad87032f: Already exists Digest: sha256:9c11fc2319b34f4488d8eed30b1e383d5696ff0e54ad0d41c2b8c0765b26f117 Status: Downloaded newer image for nvidia/cuda:11.3.1-devel-ubuntu20.04 ---> 0425ac077194 Step 2/44 : ENV CUDA_PATH /usr/local/cuda ---> Using cache ---> d36aa5713ac4 Step 3/44 : ENV LD_LIBRARY_PATH /usr/local/cuda/lib64 ---> Using cache ---> 817b0625cfb0 Step 4/44 : RUN apt-get update -qq && apt-get install -qq --no-install-recommends gfortran mpich libmpich-dev && rm -rf /var/lib/apt/lists/* ---> Using cache ---> a2b760763a81 Step 5/44 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> cc14aa1f4867 Step 6/44 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> fc0098d252fe Step 7/44 : RUN ./install_requirements.sh ubuntu ---> Using cache ---> 2a547ce7cdb9 Step 8/44 : RUN mkdir scripts ---> Using cache ---> c8eade704044 Step 9/44 : 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 ---> d2b1bdd58331 Step 10/44 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 8983f21c050d Step 11/44 : RUN ./install_cp2k_toolchain.sh --mpi-mode=mpich --enable-cuda=yes --gpu-ver=V100 --dry-run ---> Using cache ---> a94e1e326e2f Step 12/44 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> a82ab45f381f Step 13/44 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> bef512f27afe Step 14/44 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 0210c7ccbab2 Step 15/44 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 5b7c43a25b71 Step 16/44 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 0f8ee5463965 Step 17/44 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 6e69dfafdc5a Step 18/44 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 94b5ee8fd051 Step 19/44 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 406f4e840e73 Step 20/44 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> ae8fe13a8637 Step 21/44 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> c094071da92f Step 22/44 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 94e4c6f90d21 Step 23/44 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> fc1d71a507c7 Step 24/44 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> d15ae7fbeab4 Step 25/44 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> e61d00e800a4 Step 26/44 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 4032a997e1ad Step 27/44 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> cb58b7bfeaa0 Step 28/44 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> bd91d000c864 Step 29/44 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 4d03206063f5 Step 30/44 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> f3092f5c0448 Step 31/44 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 3f6c25f49cd8 Step 32/44 : WORKDIR /opt/cp2k ---> Using cache ---> 453533171e36 Step 33/44 : COPY ./Makefile . ---> Using cache ---> 06e32c692de4 Step 34/44 : COPY ./src ./src ---> d9a41596a860 Step 35/44 : COPY ./exts ./exts ---> a474f827e92a Step 36/44 : COPY ./tools/build_utils ./tools/build_utils ---> d4b97da508b5 Step 37/44 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local_cuda.psmp ./arch/ && echo 'Compiling cp2k...' && source /opt/cp2k-toolchain/install/setup && ( make -j ARCH=local_cuda VERSION=psmp &> /dev/null || true ) && ( [ ! -f ./exe/local_cuda/cp2k.psmp ] || ldd ./exe/local_cuda/cp2k.psmp | grep -q libmpi )" ---> Running in 1368c007021a './arch/local_cuda.psmp' -> '/opt/cp2k-toolchain/install/arch/local_cuda.psmp' Compiling cp2k... Removing intermediate container 1368c007021a ---> 3ed6edf0b0d8 Step 38/44 : COPY ./data ./data ---> 4b734a3267cb Step 39/44 : COPY ./tests ./tests ---> 9e70b6c4df66 Step 40/44 : COPY ./tools/regtesting ./tools/regtesting ---> 12ded6918dce Step 41/44 : COPY ./benchmarks ./benchmarks ---> 08f739d212e4 Step 42/44 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> ede642f97589 Step 43/44 : RUN ./test_performance.sh "local_cuda" 2>&1 | tee report.log ---> Running in 0a048fdd9653 ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 60 input files and 0 errors. ========== Running Performance Test ========== Running H2O-64.inp with 3 threads and 2 ranks... done. From /workspace/artifacts/H2O-64_6cpu_1gpu.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.025 0.026 86.572 86.572 qs_mol_dyn_low 1 2.0 0.004 0.004 86.192 86.194 qs_forces 11 3.9 0.001 0.001 86.143 86.143 qs_energies 11 4.9 0.001 0.001 74.325 74.329 scf_env_do_scf 11 5.9 0.001 0.001 57.888 57.888 velocity_verlet 10 3.0 0.001 0.001 53.308 53.325 scf_env_do_scf_inner_loop 108 6.5 0.005 0.008 49.175 49.175 rebuild_ks_matrix 119 8.3 0.001 0.001 23.817 23.820 qs_ks_build_kohn_sham_matrix 119 9.3 0.016 0.016 23.817 23.820 dbcsr_multiply_generic 2286 12.5 0.118 0.118 23.545 23.589 qs_ks_update_qs_env 119 7.6 0.001 0.001 21.185 21.188 qs_scf_new_mos 108 7.5 0.001 0.001 18.059 18.065 qs_scf_loop_do_ot 108 8.5 0.001 0.001 18.058 18.065 ot_scf_mini 108 9.5 0.003 0.003 16.348 16.350 multiply_cannon 2286 13.5 0.339 0.340 14.720 14.727 sum_up_and_integrate 119 10.3 0.153 0.154 13.657 13.704 multiply_cannon_loop 2286 14.5 0.135 0.135 13.573 13.582 integrate_v_rspace 119 11.3 0.334 0.336 13.504 13.550 qs_rho_update_rho 119 7.7 0.001 0.001 13.388 13.408 calculate_rho_elec 119 8.7 0.835 0.839 13.387 13.407 pw_transfer 1439 11.6 0.077 0.077 10.694 10.750 fft_wrap_pw1pw2 1201 12.6 0.009 0.009 10.352 10.409 ot_mini 108 10.5 0.001 0.001 9.888 9.890 fft_wrap_pw1pw2_140 487 13.2 0.002 0.002 8.941 9.023 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 8.842 8.842 grid_integrate_task_list 119 12.3 8.772 8.819 8.772 8.819 init_scf_loop 11 6.9 0.000 0.000 8.641 8.641 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 8.242 8.394 multiply_cannon_multrec 4572 15.5 2.044 2.051 8.249 8.265 density_rs2pw 119 9.7 0.006 0.006 7.468 7.587 make_m2s 4572 13.5 0.040 0.040 7.275 7.283 make_images 4572 14.5 1.266 1.271 7.115 7.122 init_scf_run 11 5.9 0.001 0.001 6.995 6.995 scf_env_initial_rho_setup 11 6.9 0.000 0.001 6.995 6.995 qs_ot_get_derivative 108 11.5 0.001 0.001 6.604 6.606 prepare_preconditioner 11 7.9 0.000 0.000 5.985 5.987 make_preconditioner 11 8.9 0.000 0.000 5.985 5.987 dbcsr_mm_accdrv_process 9594 16.2 1.353 1.566 5.739 5.750 pw_gpu_r3dc1d_3d_ps 606 14.1 0.009 0.009 5.475 5.489 make_full_inverse_cholesky 11 9.9 0.000 0.000 5.215 5.418 grid_collocate_task_list 119 9.7 5.046 5.113 5.046 5.113 pw_gpu_c1dr3d_3d_ps 595 15.2 0.009 0.009 4.864 4.907 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.547 4.565 potential_pw2rs 119 12.3 0.034 0.035 4.398 4.399 build_core_ppl_forces 11 5.9 4.205 4.335 4.205 4.335 rs_pw_transfer 974 11.9 0.013 0.013 3.933 4.075 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 3.994 4.047 jit_kernel_multiply 11 15.7 3.788 4.012 3.788 4.012 calculate_dm_sparse 119 9.5 0.001 0.001 3.843 3.847 qs_create_task_list 11 7.9 0.000 0.000 3.682 3.717 generate_qs_task_list 11 8.9 1.738 1.759 3.682 3.717 calculate_first_density_matrix 1 7.0 0.000 0.000 3.714 3.714 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.416 3.416 multiply_cannon_sync_h2d 4572 15.5 3.331 3.358 3.331 3.358 ot_diis_step 108 11.5 0.005 0.005 3.269 3.269 wfi_extrapolate 11 7.9 0.001 0.001 3.104 3.105 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 3.048 3.048 mp_waitall_1 64982 16.9 2.809 2.869 2.809 2.869 hybrid_alltoall_any 4725 16.4 1.757 1.761 2.820 2.822 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.806 2.808 apply_single 119 13.6 0.001 0.001 2.806 2.808 make_images_data 4572 15.5 0.048 0.048 2.773 2.777 qs_ot_get_p 119 10.4 0.001 0.001 2.736 2.738 dbcsr_complete_redistribute 329 12.2 1.134 1.152 2.482 2.674 cp_dbcsr_sm_fm_multiply_core 37 10.5 0.000 0.000 2.592 2.592 mp_alltoall_z22v 1201 16.6 2.541 2.586 2.541 2.586 qs_ot_get_derivative_taylor 59 13.0 0.002 0.002 2.457 2.457 cp_dbcsr_plus_fm_fm_t_native 22 8.9 0.001 0.001 2.416 2.419 build_core_ppl 11 7.9 2.291 2.338 2.291 2.338 pw_gpu_fg 606 15.1 2.178 2.213 2.178 2.213 rs_pw_transfer_RS2PW_140 130 11.5 1.483 1.508 1.984 2.146 pw_poisson_solve 119 10.3 0.768 0.770 2.143 2.143 qs_vxc_create 119 10.3 0.002 0.002 2.091 2.120 xc_vxc_pw_create 119 11.3 0.608 0.612 2.089 2.118 cp_fm_cholesky_invert 11 10.9 2.033 2.033 2.033 2.033 build_kinetic_matrix_low 22 6.9 1.906 1.907 1.988 1.989 build_overlap_matrix_low 22 6.9 1.873 1.877 1.953 1.956 dbcsr_special_finalize 6858 15.5 0.033 0.033 1.940 1.943 copy_dbcsr_to_fm 153 11.3 0.003 0.003 1.893 1.904 dbcsr_merge_single_wm 4572 16.5 0.124 0.126 1.846 1.849 pw_gpu_sf 595 16.2 1.771 1.774 1.771 1.774 yz_to_x 606 15.1 0.459 0.464 1.751 1.771 ------------------------------------------------------------------------------- Plot: name="H2O-64_timings_6cpu_1gpu", title="Timings of H2O-64 with 6 CPU Cores and 1 GPU", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_6cpu_1gpu", name="rest", label="rest", y=61.43, yerr=0.0 PlotPoint: plot="H2O-64_timings_6cpu_1gpu", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.772, yerr=0.0 PlotPoint: plot="H2O-64_timings_6cpu_1gpu", name="grid_collocate_task_list", label="grid_collocate_task_list", y=5.046, yerr=0.0 PlotPoint: plot="H2O-64_timings_6cpu_1gpu", name="build_core_ppl_forces", label="build_core_ppl_forces", y=4.205, yerr=0.0 PlotPoint: plot="H2O-64_timings_6cpu_1gpu", name="jit_kernel_multiply", label="jit_kernel_multiply", y=3.788, yerr=0.0 PlotPoint: plot="H2O-64_timings_6cpu_1gpu", name="multiply_cannon_sync_h2d", label="multiply_cannon_sync_h2d", y=3.331, yerr=0.0 Running H2O-64_nonortho.inp with 3 threads and 2 ranks... done. From /workspace/artifacts/H2O-64_nonortho_6cpu_1gpu.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 0.023 83.888 83.888 qs_mol_dyn_low 1 2.0 0.004 0.004 83.476 83.479 qs_forces 11 3.9 0.001 0.001 83.431 83.432 qs_energies 11 4.9 0.001 0.001 71.240 71.241 scf_env_do_scf 11 5.9 0.001 0.001 55.026 55.026 velocity_verlet 10 3.0 0.001 0.001 53.296 53.312 scf_env_do_scf_inner_loop 96 6.5 0.004 0.007 46.114 46.114 rebuild_ks_matrix 107 8.3 0.001 0.001 23.560 23.560 qs_ks_build_kohn_sham_matrix 107 9.3 0.015 0.015 23.560 23.560 qs_ks_update_qs_env 107 7.6 0.001 0.001 20.443 20.443 dbcsr_multiply_generic 1966 12.4 0.103 0.103 20.117 20.214 qs_scf_new_mos 96 7.5 0.001 0.001 15.482 15.482 qs_scf_loop_do_ot 96 8.5 0.001 0.001 15.481 15.482 sum_up_and_integrate 107 10.3 0.139 0.139 14.358 14.449 integrate_v_rspace 107 11.3 0.301 0.302 14.220 14.309 qs_rho_update_rho 107 7.7 0.001 0.001 14.031 14.047 calculate_rho_elec 107 8.7 0.750 0.755 14.031 14.046 ot_scf_mini 96 9.5 0.003 0.003 13.977 13.978 multiply_cannon 1966 13.4 0.294 0.299 12.189 12.198 multiply_cannon_loop 1966 14.4 0.114 0.115 11.215 11.224 grid_integrate_task_list 107 12.3 9.978 10.067 9.978 10.067 pw_transfer 1295 11.6 0.069 0.070 9.623 9.662 fft_wrap_pw1pw2 1081 12.6 0.008 0.008 9.314 9.355 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 9.315 9.315 init_scf_loop 11 6.9 0.000 0.000 8.840 8.840 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 8.214 8.361 ot_mini 96 10.5 0.001 0.001 8.304 8.304 fft_wrap_pw1pw2_140 439 13.2 0.002 0.002 8.029 8.095 density_rs2pw 107 9.7 0.006 0.006 6.705 6.806 multiply_cannon_multrec 3932 15.4 1.806 1.818 6.692 6.711 grid_collocate_task_list 107 9.7 6.549 6.616 6.549 6.616 make_m2s 3932 13.4 0.035 0.035 6.509 6.513 make_images 3932 14.4 1.127 1.129 6.367 6.371 init_scf_run 11 5.9 0.001 0.001 6.309 6.309 scf_env_initial_rho_setup 11 6.9 0.000 0.001 6.308 6.309 prepare_preconditioner 11 7.9 0.000 0.000 6.031 6.033 make_preconditioner 11 8.9 0.000 0.000 6.031 6.033 qs_ot_get_derivative 96 11.5 0.001 0.001 5.449 5.449 make_full_inverse_cholesky 11 9.9 0.000 0.000 5.193 5.391 qs_env_update_s_mstruct 11 6.9 0.000 0.000 5.022 5.061 pw_gpu_r3dc1d_3d_ps 546 14.1 0.009 0.009 4.930 4.940 dbcsr_mm_accdrv_process 8450 16.1 0.684 0.883 4.465 4.470 pw_gpu_c1dr3d_3d_ps 535 15.2 0.008 0.009 4.372 4.402 build_core_ppl_forces 11 5.9 4.157 4.273 4.157 4.273 qs_create_task_list 11 7.9 0.000 0.000 4.157 4.190 generate_qs_task_list 11 8.9 2.305 2.327 4.157 4.190 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 3.987 4.062 potential_pw2rs 107 12.3 0.031 0.031 3.941 3.941 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.825 3.825 rs_pw_transfer 878 11.9 0.011 0.011 3.580 3.738 jit_kernel_multiply 13 15.8 3.246 3.450 3.246 3.450 wfi_extrapolate 11 7.9 0.001 0.001 3.252 3.253 calculate_dm_sparse 107 9.5 0.001 0.001 3.153 3.155 multiply_cannon_sync_h2d 3932 15.4 2.967 3.010 2.967 3.010 ot_diis_step 96 11.5 0.004 0.004 2.841 2.841 calculate_first_density_matrix 1 7.0 0.000 0.000 2.839 2.839 dbcsr_complete_redistribute 317 12.2 1.130 1.191 2.467 2.695 mp_waitall_1 55926 16.8 2.536 2.646 2.536 2.646 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 2.617 2.618 hybrid_alltoall_any 4079 16.3 1.575 1.585 2.567 2.586 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.487 2.499 apply_single 107 13.6 0.000 0.000 2.487 2.499 make_images_data 3932 15.4 0.040 0.040 2.494 2.499 qs_ot_get_p 107 10.4 0.001 0.001 2.386 2.387 build_core_ppl 11 7.9 2.286 2.351 2.286 2.351 mp_alltoall_z22v 1081 16.6 2.305 2.348 2.305 2.348 cp_dbcsr_sm_fm_multiply_core 37 10.5 0.000 0.000 2.169 2.169 rs_pw_transfer_RS2PW_140 118 11.5 1.347 1.371 1.832 2.006 cp_fm_cholesky_invert 11 10.9 2.005 2.005 2.005 2.005 build_kinetic_matrix_low 22 6.9 1.909 1.912 1.992 1.995 pw_gpu_fg 546 15.1 1.944 1.975 1.944 1.975 build_overlap_matrix_low 22 6.9 1.866 1.871 1.946 1.952 pw_poisson_solve 107 10.3 0.691 0.694 1.931 1.931 cp_dbcsr_plus_fm_fm_t_native 22 8.9 0.001 0.001 1.930 1.930 qs_vxc_create 107 10.3 0.002 0.002 1.902 1.926 qs_ot_get_derivative_taylor 53 13.0 0.002 0.002 1.916 1.926 xc_vxc_pw_create 107 11.3 0.547 0.551 1.900 1.924 copy_dbcsr_to_fm 147 11.2 0.003 0.003 1.834 1.876 dbcsr_special_finalize 5898 15.4 0.028 0.029 1.737 1.738 ------------------------------------------------------------------------------- Plot: name="H2O-64_nonortho_timings_6cpu_1gpu", title="Timings of H2O-64_nonortho with 6 CPU Cores and 1 GPU", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_6cpu_1gpu", name="rest", label="rest", y=56.99100000000001, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_6cpu_1gpu", name="grid_integrate_task_list", label="grid_integrate_task_list", y=9.978, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_6cpu_1gpu", name="grid_collocate_task_list", label="grid_collocate_task_list", y=6.549, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_6cpu_1gpu", name="build_core_ppl_forces", label="build_core_ppl_forces", y=4.157, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_6cpu_1gpu", name="jit_kernel_multiply", label="jit_kernel_multiply", y=3.246, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_6cpu_1gpu", name="multiply_cannon_sync_h2d", label="multiply_cannon_sync_h2d", y=2.967, yerr=0.0 Running GW_PBE_4benzene.inp with 3 threads and 2 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_6cpu_1gpu.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 0.019 154.357 154.358 qs_energies 1 2.0 0.000 0.000 154.087 154.089 mp2_main 1 3.0 0.000 0.000 147.997 147.999 mp2_gpw_main 1 4.0 0.000 0.000 144.947 144.949 rpa_ri_compute_en 1 5.0 0.000 0.000 137.743 137.745 rpa_num_int 1 6.0 0.000 0.000 137.728 137.730 dbt_total 2336 9.6 0.017 0.017 119.549 119.550 compute_mat_P_omega 1 7.0 0.001 0.002 117.900 117.906 compute_mat_P_omega_contract 10 8.0 5.254 5.260 117.489 117.490 dbt_contract 787 11.0 21.666 21.726 83.644 83.801 dbt_tas_total 1149 12.2 0.186 0.275 58.270 58.270 dbt_tas_multiply 807 12.1 0.003 0.003 57.545 57.545 dbt_tas_dbm 807 14.1 0.004 0.005 46.639 46.639 dbm_multiply 807 16.1 45.595 45.603 45.595 45.603 compute_mat_P_omega_calc_M_occ 250 9.0 5.238 5.241 38.741 38.741 dbt_copy 1107 10.7 16.850 16.956 34.585 34.729 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 27.570 27.570 dbt_tas_mm_1N 524 15.1 0.002 0.002 25.832 26.077 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 19.869 19.869 dbt_tas_mm_2 251 15.0 0.002 0.002 18.606 18.606 compute_QP_energies 1 7.0 0.000 0.000 14.250 14.250 compute_self_energy_cubic_gw 1 8.0 0.043 0.043 14.246 14.249 dbt_tas_reserve_blocks_index 3266 13.6 2.578 2.588 9.633 10.133 compute_mat_P_omega_copy_M_vir 250 9.0 0.002 0.002 9.935 9.937 dbt_tas_copy 511 11.5 7.001 7.049 9.188 9.276 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 8.802 8.808 dbt_reserve_blocks_index 2347 12.3 0.536 0.537 7.800 8.261 dbt_reserve_blocks_index_array 2289 11.4 0.010 0.011 7.767 8.228 contract_cubic_gw 21 9.0 0.000 0.000 8.103 8.103 dbcsr_multiply_generic 30 8.1 0.002 0.002 7.396 7.436 multiply_cannon 30 9.1 0.011 0.014 7.257 7.293 multiply_cannon_loop 30 10.1 0.002 0.002 7.209 7.245 dbm_reserve_blocks 3634 14.7 6.700 7.214 6.700 7.214 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 7.196 7.196 scf_env_do_scf 1 3.0 0.000 0.000 5.723 5.723 scf_env_do_scf_inner_loop 17 4.0 0.001 0.001 5.723 5.723 multiply_cannon_multrec 60 11.1 0.245 0.249 5.306 5.308 dbcsr_mm_accdrv_process 328 12.3 0.023 0.024 4.830 4.843 jit_kernel_multiply 17 11.6 4.801 4.815 4.801 4.815 dbt_communicate_buffer 594 11.8 0.011 0.011 4.317 4.389 mp_sync 8689 11.6 2.934 4.221 2.934 4.221 convert_to_new_pgrid 2421 14.1 0.033 0.033 3.351 4.138 dbm_copy 1614 15.1 3.318 4.105 3.318 4.105 trace_sigma_gw 21 9.0 1.229 1.237 3.888 3.888 qs_scf_new_mos 17 5.0 0.000 0.000 3.844 3.869 get_2c_integrals 1 6.0 0.000 0.000 3.434 3.434 ------------------------------------------------------------------------------- Plot: name="GW_PBE_4benzene_timings_6cpu_1gpu", title="Timings of GW_PBE_4benzene with 6 CPU Cores and 1 GPU", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_6cpu_1gpu", name="rest", label="rest", y=56.545, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_6cpu_1gpu", name="dbm_multiply", label="dbm_multiply", y=45.595, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_6cpu_1gpu", name="dbt_contract", label="dbt_contract", y=21.666, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_6cpu_1gpu", name="dbt_copy", label="dbt_copy", y=16.85, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_6cpu_1gpu", name="dbt_tas_copy", label="dbt_tas_copy", y=7.001, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_6cpu_1gpu", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=6.7, yerr=0.0 Running RI-HFX_H2O-32.inp with 3 threads and 2 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_6cpu_1gpu.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 0.019 363.888 363.888 qs_forces 1 2.0 0.000 0.000 363.451 363.451 rebuild_ks_matrix 7 6.6 0.000 0.000 360.195 360.195 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 360.195 360.195 hfx_ks_matrix 7 8.6 0.000 0.000 357.355 357.357 dbt_total 4939 11.6 0.038 0.038 307.273 307.273 hfx_ri_update_ks 7 9.6 0.000 0.000 233.636 233.636 hfx_ri_update_ks_Pmat 7 10.6 27.293 27.329 233.617 233.633 qs_energies 1 3.0 0.000 0.000 209.863 209.863 scf_env_do_scf 1 4.0 0.000 0.000 208.475 208.475 dbt_contract 1473 13.0 86.173 86.332 208.059 208.149 qs_ks_update_qs_env 8 6.0 0.000 0.000 206.653 206.653 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 153.544 153.544 dbt_tas_total 2391 14.1 1.257 1.342 123.861 123.861 hfx_ri_update_forces 1 7.0 0.000 0.000 123.718 123.719 scf_env_do_scf_inner_loop 6 5.0 0.000 0.000 120.895 120.895 dbt_tas_multiply 1482 14.0 0.006 0.006 107.125 107.126 init_scf_loop 2 5.0 0.000 0.000 87.579 87.579 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 80.587 80.587 dbt_copy 2411 12.3 37.547 37.747 79.356 79.843 dbt_tas_dbm 1482 16.0 0.008 0.008 76.856 76.856 hfx_ri_forces_Pmat_3c 1 8.0 0.003 0.003 74.589 74.593 dbm_multiply 1482 18.0 73.739 74.097 73.739 74.097 hfx_ri_update_ks_Pmat_KS 567 11.6 0.005 0.005 67.335 67.335 dbt_tas_mm_3T 659 17.1 0.002 0.002 37.213 37.459 precalc_derivatives 1 8.0 0.004 0.004 37.171 37.171 dbt_tas_reserve_blocks_index 7477 15.3 6.871 6.898 26.560 26.763 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 26.620 26.620 dbt_tas_mm_2 649 17.1 0.005 0.005 22.928 22.928 dbt_reserve_blocks_index 5058 14.5 1.331 1.331 22.504 22.595 dbt_reserve_blocks_index_array 5023 13.5 0.022 0.022 22.329 22.419 dbm_reserve_blocks 8383 16.2 19.690 19.924 19.690 19.924 build_3c_derivatives 9 9.0 2.795 2.836 16.102 16.112 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.002 0.002 15.867 15.868 dbt_tas_copy 1495 13.0 9.544 9.598 14.113 14.149 dbt_tas_replicate 906 15.6 6.923 7.094 13.426 13.429 dbt_tas_reshape 906 14.4 0.012 0.013 11.949 11.980 dbt_tas_mm_3N 163 16.5 0.001 0.001 11.809 11.834 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.000 0.000 11.747 11.765 mp_sync 17657 13.5 10.217 11.078 10.217 11.078 mp_waitall_2 5456 16.5 7.466 8.353 7.466 8.353 dbt_communicate_buffer 916 13.8 0.018 0.018 8.022 8.147 dbt_tas_reshape_buffer_obtain 906 15.4 5.116 5.172 7.806 7.927 dbt_tas_merge 649 14.1 5.653 5.867 7.783 7.886 mp_isend_dv 4849 16.3 7.059 7.760 7.059 7.760 dbt_split_blocks_generic 174 12.2 5.271 5.310 7.530 7.585 ------------------------------------------------------------------------------- Plot: name="RI-HFX_H2O-32_timings_6cpu_1gpu", title="Timings of RI-HFX_H2O-32 with 6 CPU Cores and 1 GPU", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_6cpu_1gpu", name="rest", label="rest", y=119.44599999999997, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_6cpu_1gpu", name="dbt_contract", label="dbt_contract", y=86.173, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_6cpu_1gpu", name="dbm_multiply", label="dbm_multiply", y=73.739, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_6cpu_1gpu", name="dbt_copy", label="dbt_copy", y=37.547, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_6cpu_1gpu", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=27.293, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_6cpu_1gpu", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=19.69, yerr=0.0 Running RI-MP2_ammonia.inp with 3 threads and 2 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_6cpu_1gpu.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 0.015 107.124 107.124 qs_energies 1 2.0 0.000 0.000 106.969 106.969 mp2_main 1 3.0 0.000 0.000 100.264 100.264 mp2_gpw_main 1 4.0 0.001 0.001 99.894 99.894 mp2_ri_gpw_compute_in 1 5.0 0.422 0.424 59.080 59.094 mp2_ri_gpw_compute_in_loop 1 6.0 0.011 0.012 45.686 45.702 mp2_ri_gpw_compute_en 1 5.0 0.067 0.067 40.764 40.779 mp2_ri_gpw_compute_en_RI_loop 1 6.0 7.221 7.233 37.666 37.677 mp2_eri_3c_integrate_gpw 1328 7.0 0.014 0.014 22.258 23.044 dbcsr_multiply_generic 2666 8.0 0.127 0.130 20.439 21.170 ao_to_mo_and_store_B_mult_1 1328 7.0 0.009 0.010 18.782 19.513 calculate_wavefunction 2656 9.0 11.125 11.151 17.465 18.292 mp2_ri_gpw_compute_en_expansio 1040 7.0 1.574 1.577 17.183 17.288 offload_gemm 1040 8.0 15.609 15.718 15.609 15.718 multiply_cannon 2666 9.0 0.416 0.421 12.958 13.680 get_2c_integrals 1 6.0 0.000 0.000 12.909 12.910 multiply_cannon_loop 2666 10.0 0.099 0.100 11.790 12.508 compute_2c_integrals 1 7.0 0.008 0.008 12.018 12.019 compute_2c_integrals_loop_lm 1 8.0 0.013 0.014 11.786 11.879 mp2_eri_2c_integrate_gpw 1 9.0 2.232 2.268 11.773 11.867 integrate_v_rspace 1338 8.0 0.968 0.968 11.451 11.452 pw_transfer 32000 10.6 0.884 0.888 9.614 10.465 fft_wrap_pw1pw2 26668 11.4 0.098 0.099 8.592 9.447 grid_integrate_task_list 1338 9.0 9.294 9.297 9.294 9.297 fill_local_i_aL 2080 7.0 8.361 8.394 8.361 8.394 multiply_cannon_multrec 2676 11.0 3.632 4.093 6.827 7.272 make_m2s 5332 9.0 0.043 0.044 6.890 6.893 make_images 5332 10.0 2.399 2.401 6.740 6.743 pw_gpu_r3dc1d_3d 13282 13.2 5.507 6.369 5.507 6.369 fft_wrap_pw1pw2_20 10647 12.4 0.023 0.024 5.644 6.171 scf_env_do_scf 1 3.0 0.000 0.000 5.950 5.950 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 5.950 5.950 mp2_ri_gpw_compute_en_ener 1040 7.0 4.898 4.994 4.898 4.994 qs_scf_new_mos 10 5.0 0.000 0.000 4.866 4.868 ao_to_mo_and_store_B_E_Ex_1 1328 7.0 2.596 2.623 4.323 4.361 multiply_cannon_sync_h2d 2676 11.0 3.000 3.285 3.000 3.285 mp2_ri_create_group 1 6.0 0.000 0.000 2.999 3.005 replicate_iaK_2intgroup 1 7.0 2.598 2.602 2.999 3.005 hybrid_alltoall_any 6683 11.6 2.768 2.771 2.992 2.998 eigensolver 11 5.8 0.001 0.001 2.960 2.960 dbcsr_mm_accdrv_process 5392 12.0 0.381 0.388 2.924 2.941 make_images_data 5332 11.0 0.054 0.054 2.921 2.924 fft_wrap_pw1pw2_10 15957 12.5 0.021 0.022 2.311 2.639 jit_kernel_multiply 8 13.0 2.455 2.467 2.455 2.467 cp_fm_diag_elpa 11 6.8 0.000 0.000 2.400 2.400 cp_fm_diag_elpa_base 11 7.8 2.277 2.289 2.399 2.400 potential_pw2rs 2666 10.0 0.084 0.084 2.395 2.396 pw_gpu_c1dr3d_3d 13280 13.7 2.374 2.379 2.374 2.379 ------------------------------------------------------------------------------- Plot: name="RI-MP2_ammonia_timings_6cpu_1gpu", title="Timings of RI-MP2_ammonia with 6 CPU Cores and 1 GPU", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_6cpu_1gpu", name="rest", label="rest", y=55.51399999999998, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_6cpu_1gpu", name="offload_gemm", label="offload_gemm", y=15.609, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_6cpu_1gpu", name="calculate_wavefunction", label="calculate_wavefunction", y=11.125, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_6cpu_1gpu", name="grid_integrate_task_list", label="grid_integrate_task_list", y=9.294, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_6cpu_1gpu", name="fill_local_i_aL", label="fill_local_i_aL", y=8.361, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_6cpu_1gpu", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=7.221, yerr=0.0 Running diag_cu144_broy.inp with 3 threads and 2 ranks... done. From /workspace/artifacts/diag_cu144_broy_6cpu_1gpu.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.068 0.069 166.527 166.527 qs_energies 1 2.0 0.000 0.000 165.544 165.545 scf_env_do_scf 1 3.0 0.000 0.000 153.614 153.614 scf_env_do_scf_inner_loop 15 4.0 0.001 0.002 153.614 153.614 qs_ks_update_qs_env 15 5.0 0.000 0.000 80.555 80.591 rebuild_ks_matrix 15 6.0 0.000 0.000 80.386 80.422 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 80.386 80.422 qs_scf_new_mos 15 5.0 0.000 0.000 53.343 53.377 eigensolver 15 6.0 0.002 0.002 46.496 46.515 qs_vxc_create 15 8.0 0.000 0.000 43.946 43.949 calculate_dispersion_nonloc 15 9.0 10.820 11.016 37.940 37.943 sum_up_and_integrate 15 8.0 0.039 0.039 35.398 35.437 integrate_v_rspace 15 9.0 0.043 0.043 35.359 35.398 grid_integrate_task_list 15 10.0 34.315 34.351 34.315 34.351 cp_fm_diag_elpa 15 7.0 0.000 0.000 30.505 30.510 cp_fm_diag_elpa_base 15 8.0 28.188 28.630 30.500 30.501 pw_transfer 1191 10.0 0.076 0.080 21.194 21.339 fft_wrap_pw1pw2 1086 11.0 0.010 0.010 20.899 21.046 qs_rho_update_rho 16 5.0 0.000 0.000 16.946 16.947 calculate_rho_elec 16 6.0 0.173 0.173 16.946 16.947 grid_collocate_task_list 16 7.0 14.879 14.890 14.879 14.890 fft_wrap_pw1pw2_150 765 12.0 0.003 0.003 14.245 14.404 cp_fm_cholesky_restore 45 7.0 13.599 14.111 13.599 14.111 pw_gpu_c1dr3d_3d_ps 585 13.1 0.011 0.011 10.954 10.957 pw_gpu_r3dc1d_3d_ps 501 12.9 0.008 0.009 9.931 10.082 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 9.651 9.651 vdW_energy 15 10.0 9.027 9.086 9.027 9.086 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 8.044 8.067 fft_wrap_pw1pw2_200 197 12.3 0.001 0.001 6.109 6.120 xc_vxc_pw_create 15 9.0 0.170 0.171 6.005 6.011 cp_fm_upper_to_full 30 8.0 4.702 5.669 4.702 5.669 mp_alltoall_z22v 1086 15.0 5.271 5.323 5.271 5.323 copy_dbcsr_to_fm 16 5.9 0.001 0.001 4.591 4.648 pw_gpu_sf 585 14.1 4.129 4.133 4.129 4.133 dbcsr_complete_redistribute 46 8.3 1.607 1.609 4.117 4.121 pw_gpu_fg 501 13.9 3.992 4.012 3.992 4.012 build_core_ppnl 1 5.0 3.981 3.990 3.981 3.990 xc_rho_set_and_dset_create 15 10.0 0.121 0.121 3.756 3.758 gspace_mixing 14 5.0 0.120 0.120 3.697 3.697 x_to_yz 585 14.1 0.964 0.981 3.587 3.628 yz_to_x 501 13.9 0.797 0.800 3.446 3.558 ------------------------------------------------------------------------------- Plot: name="diag_cu144_broy_timings_6cpu_1gpu", title="Timings of diag_cu144_broy with 6 CPU Cores and 1 GPU", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_6cpu_1gpu", name="rest", label="rest", y=64.72599999999997, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_6cpu_1gpu", name="grid_integrate_task_list", label="grid_integrate_task_list", y=34.315, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_6cpu_1gpu", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=28.188, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_6cpu_1gpu", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.879, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_6cpu_1gpu", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=13.599, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_6cpu_1gpu", name="calculate_dispersion_nonloc", label="calculate_dispersion_nonloc", y=10.82, yerr=0.0 Running bench_dftb.inp with 3 threads and 2 ranks... done. From /workspace/artifacts/bench_dftb_6cpu_1gpu.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 0.034 239.040 239.040 qs_energies 1 2.0 0.000 0.000 238.954 238.955 ls_scf 1 3.0 0.000 0.000 238.162 238.163 ls_scf_main 1 4.0 0.001 0.001 229.078 229.079 density_matrix_trs4 11 5.0 0.008 0.010 190.982 191.034 dbcsr_multiply_generic 185 6.1 0.246 0.246 156.927 156.958 multiply_cannon 185 7.1 0.955 1.039 111.630 111.773 multiply_cannon_loop 185 8.1 0.275 0.277 97.958 98.026 multiply_cannon_multrec 370 9.1 78.826 78.962 89.152 89.256 make_m2s 370 7.1 0.025 0.025 36.246 36.307 make_images 370 8.1 12.086 12.291 35.374 35.430 ls_scf_dm_to_ks 11 5.0 0.000 0.000 34.245 34.296 matrix_ls_to_qs 11 6.0 0.000 0.000 32.200 32.234 dbcsr_complete_redistribute 23 7.5 20.793 20.909 28.415 28.468 matrix_decluster 11 7.0 0.000 0.000 26.026 26.075 arnoldi_extremal 12 6.1 0.000 0.000 23.698 23.707 arnoldi_normal_ev 12 7.1 0.012 0.012 23.698 23.706 build_subspace 23 8.1 0.057 0.057 23.207 23.207 dbcsr_matrix_vector_mult 652 9.0 0.116 0.116 22.093 22.163 dbcsr_matrix_vector_mult_local 652 10.0 21.209 21.278 21.214 21.283 dbcsr_finalize 646 7.5 0.174 0.178 14.261 14.479 dbcsr_merge_all 597 8.5 1.857 2.056 11.551 11.782 setup_rec_index_2d 370 8.1 10.351 10.386 10.351 10.386 make_images_data 370 9.1 0.009 0.010 8.331 8.389 dbcsr_special_finalize 555 9.1 0.008 0.008 8.231 8.251 hybrid_alltoall_any 393 9.9 3.968 3.979 7.965 8.032 dbcsr_sort_indices 1287 10.0 7.790 7.810 7.790 7.810 ls_scf_init_scf 1 4.0 0.000 0.000 7.782 7.783 dbcsr_add_d 280 6.0 0.001 0.001 7.466 7.705 dbcsr_add_anytype 280 7.0 3.695 3.713 7.465 7.704 ls_scf_init_matrix_S 1 5.0 0.000 0.000 7.356 7.357 dbcsr_mm_accdrv_process 14501 10.0 0.407 0.408 6.888 6.893 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 6.682 6.683 tree_to_linear_d 110 9.4 6.433 6.439 6.433 6.439 dbcsr_mm_accdrv_process_sort 14501 11.0 6.258 6.264 6.258 6.264 dbcsr_copy_into_existing 11 7.0 6.173 6.189 6.174 6.189 make_images_pack 370 9.1 5.536 5.657 5.548 5.668 dbcsr_merge_single_wm 370 10.1 0.484 0.485 5.290 5.295 ------------------------------------------------------------------------------- Plot: name="bench_dftb_timings_6cpu_1gpu", title="Timings of bench_dftb with 6 CPU Cores and 1 GPU", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_6cpu_1gpu", name="rest", label="rest", y=95.77499999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_6cpu_1gpu", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=78.826, yerr=0.0 PlotPoint: plot="bench_dftb_timings_6cpu_1gpu", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=21.209, yerr=0.0 PlotPoint: plot="bench_dftb_timings_6cpu_1gpu", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=20.793, yerr=0.0 PlotPoint: plot="bench_dftb_timings_6cpu_1gpu", name="make_images", label="make_images", y=12.086, yerr=0.0 PlotPoint: plot="bench_dftb_timings_6cpu_1gpu", name="setup_rec_index_2d", label="setup_rec_index_2d", y=10.351, yerr=0.0 Running dbcsr.inp with 3 threads and 2 ranks... done. From /workspace/artifacts/dbcsr_6cpu_1gpu.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.003 0.004 46.418 46.419 lib_test 1 2.0 0.000 0.000 46.409 46.413 dbcsr_run_tests 3 3.0 0.001 0.001 46.409 46.413 test_multiplies_multiproc 3 4.0 0.001 0.001 36.573 36.696 dbcsr_multiply_generic 9 5.0 0.001 0.001 26.404 26.406 multiply_cannon 9 6.0 0.070 0.127 19.289 19.617 multiply_cannon_loop 9 7.0 0.002 0.002 18.267 18.557 multiply_cannon_multrec 18 8.0 9.271 9.552 16.794 17.090 dbcsr_make_random_matrix 9 4.0 7.009 7.061 9.755 9.877 dbcsr_redistribute 9 5.0 5.790 5.840 7.544 7.565 dbcsr_mm_accdrv_process 8199 9.0 1.139 1.163 6.978 6.988 dbcsr_finalize 27 5.7 0.001 0.001 6.034 6.197 dbcsr_merge_all 18 6.5 2.617 2.624 5.771 5.936 dbcsr_mm_accdrv_process_sort 8199 10.0 4.402 4.410 4.402 4.410 make_m2s 18 6.0 0.001 0.001 3.228 3.229 make_images 18 7.0 0.441 0.446 3.200 3.202 dbcsr_data_copy_aa2 18 7.5 1.490 1.663 1.490 1.663 tree_to_linear_d 9 7.0 1.549 1.551 1.549 1.551 mp_alltoall_d11v 27 6.0 1.551 1.551 1.551 1.551 dbcsr_checksum 6 5.0 1.479 1.481 1.483 1.484 jit_kernel_multiply 6 10.0 1.436 1.457 1.436 1.457 dbcsr_data_release 507 7.7 1.128 1.129 1.128 1.129 make_images_data 18 8.0 0.000 0.000 1.044 1.048 hybrid_alltoall_any 18 9.0 0.683 0.683 1.016 1.020 make_images_pack 18 8.0 0.990 1.003 0.990 1.004 ------------------------------------------------------------------------------- Plot: name="dbcsr_timings_6cpu_1gpu", title="Timings of dbcsr with 6 CPU Cores and 1 GPU", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_6cpu_1gpu", name="rest", label="rest", y=17.328999999999997, yerr=0.0 PlotPoint: plot="dbcsr_timings_6cpu_1gpu", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=9.271, yerr=0.0 PlotPoint: plot="dbcsr_timings_6cpu_1gpu", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=7.009, yerr=0.0 PlotPoint: plot="dbcsr_timings_6cpu_1gpu", name="dbcsr_redistribute", label="dbcsr_redistribute", y=5.79, yerr=0.0 PlotPoint: plot="dbcsr_timings_6cpu_1gpu", name="dbcsr_mm_accdrv_process_sort", label="dbcsr_mm_accdrv_process_sort", y=4.402, yerr=0.0 PlotPoint: plot="dbcsr_timings_6cpu_1gpu", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.617, yerr=0.0 Running MQAE_single_node.inp with 3 threads and 2 ranks... done. From /workspace/artifacts/MQAE_single_node_6cpu_1gpu.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.034 0.037 171.137 171.138 qs_mol_dyn_low 1 2.0 0.003 0.003 169.704 169.743 qs_forces 6 3.8 0.001 0.001 99.874 99.874 qs_energies 6 4.8 0.000 0.000 93.602 93.602 scf_env_do_scf 6 5.8 0.000 0.001 86.028 86.028 velocity_verlet 5 3.0 0.003 0.003 84.432 84.491 scf_env_do_scf_inner_loop 113 6.2 0.005 0.007 79.328 79.328 rebuild_ks_matrix 119 8.1 0.000 0.000 64.964 64.965 qs_ks_build_kohn_sham_matrix 119 9.1 0.016 0.016 64.964 64.964 qs_ks_update_qs_env 119 7.3 0.001 0.001 60.973 60.974 pw_transfer 2446 12.3 0.145 0.146 41.169 41.315 fft_wrap_pw1pw2 2059 13.4 0.019 0.019 40.312 40.457 fft_wrap_pw1pw2_150 1321 14.9 0.006 0.007 38.611 38.800 qs_vxc_create 119 10.1 0.002 0.002 37.995 37.998 xc_vxc_pw_create 119 11.1 1.339 1.353 37.993 37.996 qmmm_el_coupling 6 3.8 0.000 0.000 36.227 36.252 qmmm_elec_with_gaussian 6 4.8 0.130 0.167 36.222 36.247 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 34.706 34.840 qmmm_elec_gaussian_low_G 6 6.8 30.429 30.568 30.429 30.568 qmmm_forces 6 3.8 0.001 0.001 30.495 30.495 qmmm_forces_with_gaussian 6 4.8 0.100 0.107 30.189 30.206 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 28.633 28.664 xc_pw_derive 714 13.1 0.007 0.007 24.185 24.319 qmmm_forces_gaussian_low_G 6 6.8 24.093 24.125 24.093 24.125 pw_gpu_c1dr3d_3d_ps 1095 15.8 0.023 0.023 21.754 21.775 xc_rho_set_and_dset_create 119 12.1 2.446 2.455 20.206 20.292 pw_gpu_r3dc1d_3d_ps 964 15.0 0.016 0.017 18.531 18.653 xc_pw_divergence 119 12.1 0.004 0.004 16.092 16.200 qs_rho_update_rho 119 7.3 0.001 0.001 14.874 15.086 calculate_rho_elec 119 8.3 1.026 1.026 14.873 15.085 dbcsr_multiply_generic 2588 12.3 0.079 0.079 14.711 14.843 multiply_cannon 2588 13.3 0.199 0.200 13.272 13.511 sum_up_and_integrate 119 10.1 0.273 0.274 13.141 13.167 multiply_cannon_loop 2588 14.3 0.120 0.120 12.740 12.978 integrate_v_rspace 119 11.1 0.020 0.021 12.867 12.895 density_rs2pw 119 9.3 0.006 0.006 11.161 11.340 mp_alltoall_z22v 2059 17.4 10.611 10.662 10.611 10.662 multiply_cannon_multrec 5176 15.3 3.924 3.939 9.652 9.769 x_to_yz 1095 16.8 2.124 2.157 7.907 7.937 qs_scf_new_mos 113 7.2 0.001 0.001 7.784 7.785 qs_scf_loop_do_ot 113 8.2 0.001 0.001 7.784 7.785 pw_gpu_sf 1095 16.8 7.771 7.772 7.771 7.772 pw_gpu_fg 964 16.0 7.654 7.758 7.654 7.758 ot_scf_mini 113 9.2 0.002 0.002 7.492 7.493 qs_ks_ddapc 119 10.1 0.002 0.002 7.115 7.141 init_scf_loop 6 6.8 0.000 0.000 6.698 6.698 potential_pw2rs 119 12.1 0.032 0.032 6.549 6.551 yz_to_x 964 16.0 1.624 1.629 6.452 6.469 grid_integrate_task_list 119 12.1 6.298 6.323 6.298 6.323 pw_gpu_ffc 1095 16.8 6.040 6.091 6.040 6.091 pw_integral_ab 2761 7.7 5.724 5.745 5.813 5.828 dbcsr_mm_accdrv_process 13832 16.0 1.378 1.779 5.660 5.762 rs_pw_transfer 988 11.5 0.011 0.011 5.442 5.653 init_scf_run 6 5.8 0.000 0.000 5.516 5.516 scf_env_initial_rho_setup 6 6.8 0.000 0.000 5.515 5.516 xc_functional_eval 238 13.1 0.002 0.002 4.951 5.037 ot_mini 113 10.2 0.001 0.001 5.030 5.031 jit_kernel_multiply 24 14.6 4.254 4.757 4.254 4.757 calculate_first_density_matrix 1 7.0 0.000 0.000 4.433 4.644 qmmm_forces_gaussian_low_R 6 6.8 0.000 0.000 4.540 4.542 qmmm_forces_with_gaussian_LG 6 7.8 4.540 4.542 4.540 4.542 pw_gpu_cff 964 16.0 4.359 4.361 4.359 4.361 qmmm_elec_gaussian_low_R 6 6.8 0.000 0.000 4.277 4.281 qmmm_elec_with_gaussian_LG 6 7.8 4.277 4.281 4.277 4.281 qs_ot_get_derivative 113 11.2 0.001 0.001 4.138 4.139 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 4.007 4.007 pw_poisson_solve 125 9.9 1.393 1.405 3.817 3.818 cp_ddapc_apply_CD 119 11.1 0.008 0.012 3.519 3.519 ------------------------------------------------------------------------------- Plot: name="MQAE_single_node_timings_6cpu_1gpu", title="Timings of MQAE_single_node with 6 CPU Cores and 1 GPU", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_6cpu_1gpu", name="rest", label="rest", y=90.57900000000001, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_6cpu_1gpu", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=30.429, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_6cpu_1gpu", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=24.093, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_6cpu_1gpu", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=10.611, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_6cpu_1gpu", name="pw_gpu_sf", label="pw_gpu_sf", y=7.771, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_6cpu_1gpu", name="pw_gpu_fg", label="pw_gpu_fg", y=7.654, yerr=0.0 Summary: Performance test took 23 minutes. Status: OK Removing intermediate container 0a048fdd9653 ---> 705555e7443a Step 44/44 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in a9ae9b7c5d7b Removing intermediate container a9ae9b7c5d7b ---> ee1c96167383 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built ee1c96167383 Successfully tagged gcr.io/cp2k-org-project/img_cp2k-perf-cuda-volta-arch-b51:master Pushing new image... done. #################### Running Image cp2k-perf-cuda-volta #################### Uploading artifacts... done EndDate: 2022-05-20 19:49:05+00:00