0 KSP Residual norm 1.355319272568e-06 1 KSP Residual norm 1.281168167902e-08 2 KSP Residual norm 2.148977497796e-09 3 KSP Residual norm 1.257733699598e-09 4 KSP Residual norm 5.204015586633e-10 5 KSP Residual norm 3.966786066776e-10 6 KSP Residual norm 2.065857839381e-10 7 KSP Residual norm 1.146518725379e-10 8 KSP Residual norm 7.003749349948e-11 9 KSP Residual norm 4.218206878161e-11 10 KSP Residual norm 2.512189393736e-11 11 KSP Residual norm 1.520747152712e-11 12 KSP Residual norm 9.366474671750e-12 KSP Object: 1 MPI processes type: cg maximum iterations=10000, initial guess is zero tolerances: relative=1e-05, absolute=1e-50, divergence=10000. left preconditioning using PRECONDITIONED norm type for convergence test PC Object: 1 MPI processes type: gamg type is MULTIPLICATIVE, levels=7 cycles=v Cycles per PCApply=1 Using externally compute Galerkin coarse grid matrices GAMG specific options Threshold for dropping small values in graph on each level = 0. 0. 0. 0. 0. 0. 0. Threshold scaling factor for each level not specified = 1. AGG specific options Symmetric graph false Number of levels to square graph 1 Number smoothing steps 1 Complexity: grid = 1.43319 Coarse grid solver -- level ------------------------------- KSP Object: (mg_coarse_) 1 MPI processes type: preonly maximum iterations=10000, initial guess is zero tolerances: relative=1e-05, absolute=1e-50, divergence=10000. left preconditioning using NONE norm type for convergence test PC Object: (mg_coarse_) 1 MPI processes type: bjacobi number of blocks = 1 Local solver information for first block is in the following KSP and PC objects on rank 0: Use -mg_coarse_ksp_view ::ascii_info_detail to display information for all blocks KSP Object: (mg_coarse_sub_) 1 MPI processes type: preonly maximum iterations=1, initial guess is zero tolerances: relative=1e-05, absolute=1e-50, divergence=10000. left preconditioning using NONE norm type for convergence test PC Object: (mg_coarse_sub_) 1 MPI processes type: lu out-of-place factorization tolerance for zero pivot 2.22045e-14 using diagonal shift on blocks to prevent zero pivot [INBLOCKS] matrix ordering: nd factor fill ratio given 5., needed 1. Factored matrix follows: Mat Object: 1 MPI processes type: seqaijcusparse rows=6, cols=6 package used to perform factorization: cusparse total: nonzeros=36, allocated nonzeros=36 using I-node routines: found 2 nodes, limit used is 5 linear system matrix = precond matrix: Mat Object: (mg_coarse_sub_) 1 MPI processes type: seqaijcusparse rows=6, cols=6 total: nonzeros=36, allocated nonzeros=36 total number of mallocs used during MatSetValues calls=0 not using I-node routines linear system matrix = precond matrix: Mat Object: (mg_coarse_sub_) 1 MPI processes type: seqaijcusparse rows=6, cols=6 total: nonzeros=36, allocated nonzeros=36 total number of mallocs used during MatSetValues calls=0 not using I-node routines Down solver (pre-smoother) on level 1 ------------------------------- KSP Object: (mg_levels_1_) 1 MPI processes type: chebyshev eigenvalue estimates used: min = 0.0999739, max = 1.09971 eigenvalues estimate via gmres min -3.55588e-07, max 0.999739 eigenvalues estimated using gmres with translations [0. 0.1; 0. 1.1] KSP Object: (mg_levels_1_esteig_) 1 MPI processes type: gmres restart=30, using Classical (unmodified) Gram-Schmidt Orthogonalization with no iterative refinement happy breakdown tolerance 1e-30 maximum iterations=10, initial guess is zero tolerances: relative=1e-12, absolute=1e-50, divergence=10000. left preconditioning using PRECONDITIONED norm type for convergence test estimating eigenvalues using noisy right hand side maximum iterations=2, nonzero initial guess tolerances: relative=1e-05, absolute=1e-50, divergence=10000. left preconditioning using NONE norm type for convergence test PC Object: (mg_levels_1_) 1 MPI processes type: sor type = local_symmetric, iterations = 1, local iterations = 1, omega = 1. linear system matrix = precond matrix: Mat Object: 1 MPI processes type: seqaijcusparse rows=94, cols=94 total: nonzeros=2802, allocated nonzeros=2802 total number of mallocs used during MatSetValues calls=0 not using I-node routines Up solver (post-smoother) same as down solver (pre-smoother) Down solver (pre-smoother) on level 2 ------------------------------- KSP Object: (mg_levels_2_) 1 MPI processes type: chebyshev eigenvalue estimates used: min = 0.0998807, max = 1.09869 eigenvalues estimate via gmres min 0.0106477, max 0.998807 eigenvalues estimated using gmres with translations [0. 0.1; 0. 1.1] KSP Object: (mg_levels_2_esteig_) 1 MPI processes type: gmres restart=30, using Classical (unmodified) Gram-Schmidt Orthogonalization with no iterative refinement happy breakdown tolerance 1e-30 maximum iterations=10, initial guess is zero tolerances: relative=1e-12, absolute=1e-50, divergence=10000. left preconditioning using PRECONDITIONED norm type for convergence test estimating eigenvalues using noisy right hand side maximum iterations=2, nonzero initial guess tolerances: relative=1e-05, absolute=1e-50, divergence=10000. left preconditioning using NONE norm type for convergence test PC Object: (mg_levels_2_) 1 MPI processes type: sor type = local_symmetric, iterations = 1, local iterations = 1, omega = 1. linear system matrix = precond matrix: Mat Object: 1 MPI processes type: seqaijcusparse rows=1311, cols=1311 total: nonzeros=46641, allocated nonzeros=46641 total number of mallocs used during MatSetValues calls=0 not using I-node routines Up solver (post-smoother) same as down solver (pre-smoother) Down solver (pre-smoother) on level 3 ------------------------------- KSP Object: (mg_levels_3_) 1 MPI processes type: chebyshev eigenvalue estimates used: min = 0.0997459, max = 1.0972 eigenvalues estimate via gmres min 0.0133132, max 0.997459 eigenvalues estimated using gmres with translations [0. 0.1; 0. 1.1] KSP Object: (mg_levels_3_esteig_) 1 MPI processes type: gmres restart=30, using Classical (unmodified) Gram-Schmidt Orthogonalization with no iterative refinement happy breakdown tolerance 1e-30 maximum iterations=10, initial guess is zero tolerances: relative=1e-12, absolute=1e-50, divergence=10000. left preconditioning using PRECONDITIONED norm type for convergence test estimating eigenvalues using noisy right hand side maximum iterations=2, nonzero initial guess tolerances: relative=1e-05, absolute=1e-50, divergence=10000. left preconditioning using NONE norm type for convergence test PC Object: (mg_levels_3_) 1 MPI processes type: sor type = local_symmetric, iterations = 1, local iterations = 1, omega = 1. linear system matrix = precond matrix: Mat Object: 1 MPI processes type: seqaijcusparse rows=19196, cols=19196 total: nonzeros=643118, allocated nonzeros=643118 total number of mallocs used during MatSetValues calls=0 not using I-node routines Up solver (post-smoother) same as down solver (pre-smoother) Down solver (pre-smoother) on level 4 ------------------------------- KSP Object: (mg_levels_4_) 1 MPI processes type: chebyshev eigenvalue estimates used: min = 0.0995886, max = 1.09547 eigenvalues estimate via gmres min 0.0141615, max 0.995886 eigenvalues estimated using gmres with translations [0. 0.1; 0. 1.1] KSP Object: (mg_levels_4_esteig_) 1 MPI processes type: gmres restart=30, using Classical (unmodified) Gram-Schmidt Orthogonalization with no iterative refinement happy breakdown tolerance 1e-30 maximum iterations=10, initial guess is zero tolerances: relative=1e-12, absolute=1e-50, divergence=10000. left preconditioning using PRECONDITIONED norm type for convergence test estimating eigenvalues using noisy right hand side maximum iterations=2, nonzero initial guess tolerances: relative=1e-05, absolute=1e-50, divergence=10000. left preconditioning using NONE norm type for convergence test PC Object: (mg_levels_4_) 1 MPI processes type: sor type = local_symmetric, iterations = 1, local iterations = 1, omega = 1. linear system matrix = precond matrix: Mat Object: 1 MPI processes type: seqaijcusparse rows=213277, cols=213277 total: nonzeros=5094075, allocated nonzeros=5094075 total number of mallocs used during MatSetValues calls=0 not using I-node routines Up solver (post-smoother) same as down solver (pre-smoother) Down solver (pre-smoother) on level 5 ------------------------------- KSP Object: (mg_levels_5_) 1 MPI processes type: chebyshev eigenvalue estimates used: min = 0.0990462, max = 1.08951 eigenvalues estimate via gmres min 0.0136677, max 0.990462 eigenvalues estimated using gmres with translations [0. 0.1; 0. 1.1] KSP Object: (mg_levels_5_esteig_) 1 MPI processes type: gmres restart=30, using Classical (unmodified) Gram-Schmidt Orthogonalization with no iterative refinement happy breakdown tolerance 1e-30 maximum iterations=10, initial guess is zero tolerances: relative=1e-12, absolute=1e-50, divergence=10000. left preconditioning using PRECONDITIONED norm type for convergence test estimating eigenvalues using noisy right hand side maximum iterations=2, nonzero initial guess tolerances: relative=1e-05, absolute=1e-50, divergence=10000. left preconditioning using NONE norm type for convergence test PC Object: (mg_levels_5_) 1 MPI processes type: sor type = local_symmetric, iterations = 1, local iterations = 1, omega = 1. linear system matrix = precond matrix: Mat Object: 1 MPI processes type: seqaijcusparse rows=1258856, cols=1258856 total: nonzeros=13701672, allocated nonzeros=13701672 total number of mallocs used during MatSetValues calls=0 not using I-node routines Up solver (post-smoother) same as down solver (pre-smoother) Down solver (pre-smoother) on level 6 ------------------------------- KSP Object: (mg_levels_6_) 1 MPI processes type: chebyshev eigenvalue estimates used: min = 62.8342, max = 691.176 eigenvalues estimate via gmres min 628.342, max 628.342 eigenvalues estimated using gmres with translations [0. 0.1; 0. 1.1] KSP Object: (mg_levels_6_esteig_) 1 MPI processes type: gmres restart=30, using Classical (unmodified) Gram-Schmidt Orthogonalization with no iterative refinement happy breakdown tolerance 1e-30 maximum iterations=10, initial guess is zero tolerances: relative=1e-12, absolute=1e-50, divergence=10000. left preconditioning using PRECONDITIONED norm type for convergence test estimating eigenvalues using noisy right hand side maximum iterations=2, nonzero initial guess tolerances: relative=1e-05, absolute=1e-50, divergence=10000. left preconditioning using NONE norm type for convergence test PC Object: (mg_levels_6_) 1 MPI processes type: sor type = local_symmetric, iterations = 1, local iterations = 1, omega = 1. linear system matrix = precond matrix: Mat Object: 1 MPI processes type: seqaijcusparse rows=9000000, cols=9000000 total: nonzeros=44988000, allocated nonzeros=44988000 total number of mallocs used during MatSetValues calls=0 has attached null space not using I-node routines Up solver (post-smoother) same as down solver (pre-smoother) linear system matrix = precond matrix: Mat Object: 1 MPI processes type: seqaijcusparse rows=9000000, cols=9000000 total: nonzeros=44988000, allocated nonzeros=44988000 total number of mallocs used during MatSetValues calls=0 has attached null space not using I-node routines ************************************************************************************************************************ *** WIDEN YOUR WINDOW TO 120 CHARACTERS. Use 'enscript -r -fCourier9' to print this document *** ************************************************************************************************************************ ---------------------------------------------- PETSc Performance Summary: ---------------------------------------------- ./ex50 on a named 15182d0f546e with 1 processor, by Unknown Tue Mar 22 22:28:44 2022 Using Petsc Release Version 3.16.5, unknown Max Max/Min Avg Total Time (sec): 3.134e+01 1.000 3.134e+01 Objects: 4.730e+02 1.000 4.730e+02 Flop: 2.671e+10 1.000 2.671e+10 2.671e+10 Flop/sec: 8.521e+08 1.000 8.521e+08 8.521e+08 MPI Messages: 0.000e+00 0.000 0.000e+00 0.000e+00 MPI Message Lengths: 0.000e+00 0.000 0.000e+00 0.000e+00 MPI Reductions: 0.000e+00 0.000 Flop counting convention: 1 flop = 1 real number operation of type (multiply/divide/add/subtract) e.g., VecAXPY() for real vectors of length N --> 2N flop and VecAXPY() for complex vectors of length N --> 8N flop Summary of Stages: ----- Time ------ ----- Flop ------ --- Messages --- -- Message Lengths -- -- Reductions -- Avg %Total Avg %Total Count %Total Avg %Total Count %Total 0: Main Stage: 3.1343e+01 100.0% 2.6708e+10 100.0% 0.000e+00 0.0% 0.000e+00 0.0% 0.000e+00 0.0% ------------------------------------------------------------------------------------------------------------------------ See the 'Profiling' chapter of the users' manual for details on interpreting output. Phase summary info: Count: number of times phase was executed Time and Flop: Max - maximum over all processors Ratio - ratio of maximum to minimum over all processors Mess: number of messages sent AvgLen: average message length (bytes) Reduct: number of global reductions Global: entire computation Stage: stages of a computation. Set stages with PetscLogStagePush() and PetscLogStagePop(). %T - percent time in this phase %F - percent flop in this phase %M - percent messages in this phase %L - percent message lengths in this phase %R - percent reductions in this phase Total Mflop/s: 10e-6 * (sum of flop over all processors)/(max time over all processors) GPU Mflop/s: 10e-6 * (sum of flop on GPU over all processors)/(max GPU time over all processors) CpuToGpu Count: total number of CPU to GPU copies per processor CpuToGpu Size (Mbytes): 10e-6 * (total size of CPU to GPU copies per processor) GpuToCpu Count: total number of GPU to CPU copies per processor GpuToCpu Size (Mbytes): 10e-6 * (total size of GPU to CPU copies per processor) GPU %F: percent flops on GPU in this event ------------------------------------------------------------------------------------------------------------------------ Event Count Time (sec) Flop --- Global --- --- Stage ---- Total GPU - CpuToGpu - - GpuToCpu - GPU Max Ratio Max Ratio Max Ratio Mess AvgLen Reduct %T %F %M %L %R %T %F %M %L %R Mflop/s Mflop/s Count Size Count Size %F --------------------------------------------------------------------------------------------------------------------------------------------------------------- --- Event Stage 0: Main Stage MatMult 435 1.0 1.8739e-01 1.0 8.77e+09 1.0 0.0e+00 0.0e+00 0.0e+00 1 33 0 0 0 1 33 0 0 0 46811 89587 5 8.64e+02 0 0.00e+00 100 MatMultAdd 78 1.0 1.1723e-02 1.0 7.20e+08 1.0 0.0e+00 0.0e+00 0.0e+00 0 3 0 0 0 0 3 0 0 0 61413 68042 0 0.00e+00 0 0.00e+00 100 MatMultTranspose 78 1.0 1.0474e-02 1.0 5.84e+08 1.0 0.0e+00 0.0e+00 0.0e+00 0 2 0 0 0 0 2 0 0 0 55714 64009 0 0.00e+00 0 0.00e+00 100 MatSolve 13 1.0 1.8954e-03 1.0 8.58e+02 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 1 0 0.00e+00 0 0.00e+00 100 MatSOR 369 1.0 9.1214e+00 1.0 7.32e+09 1.0 0.0e+00 0.0e+00 0.0e+00 29 27 0 0 0 29 27 0 0 0 803 0 0 0.00e+00 565 1.35e+03 0 MatLUFactorSym 1 1.0 2.2572e-05 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 MatLUFactorNum 1 1.0 5.8271e-03 1.0 1.31e+02 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 4 6.08e-04 1 2.88e-04 0 MatConvert 6 1.0 3.2619e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 1 0 0 0 0 1 0 0 0 0 0 0 0 0.00e+00 5 1.56e+02 0 MatScale 18 1.0 2.9161e-01 1.0 1.84e+08 1.0 0.0e+00 0.0e+00 0.0e+00 1 1 0 0 0 1 1 0 0 0 632 59727 6 2.22e+02 12 3.05e+02 15 MatResidual 78 1.0 1.3446e-01 1.0 1.70e+09 1.0 0.0e+00 0.0e+00 0.0e+00 0 6 0 0 0 0 6 0 0 0 12612 81790 1 7.20e+01 0 0.00e+00 93 MatAssemblyBegin 15 1.0 5.2980e-06 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 MatAssemblyEnd 15 1.0 6.1145e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 2 0 0 0 0 2 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 MatGetRowIJ 1 1.0 1.9376e-05 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 MatGetOrdering 1 1.0 1.2669e-04 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 MatCoarsen 6 1.0 1.1028e+00 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 4 0 0 0 0 4 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 MatView 10 1.0 4.4277e-04 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 MatAXPY 6 1.0 1.4566e-02 1.0 3.82e+07 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 2621 2677 0 0.00e+00 0 0.00e+00 100 MatMatMultSym 6 1.0 3.3593e-01 1.0 1.29e+08 1.0 0.0e+00 0.0e+00 0.0e+00 1 0 0 0 0 1 0 0 0 0 384 2543 6 1.68e+02 6 1.53e+02 100 MatMatMultNum 6 1.0 1.5769e-05 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 MatPtAPSymbolic 6 1.0 6.3788e-01 1.0 6.98e+08 1.0 0.0e+00 0.0e+00 0.0e+00 2 3 0 0 0 2 3 0 0 0 1094 3368 6 4.32e+02 12 3.42e+02 100 MatPtAPNumeric 6 1.0 5.4855e-03 1.0 6.98e+08 1.0 0.0e+00 0.0e+00 0.0e+00 0 3 0 0 0 0 3 0 0 0 127241 131242 0 0.00e+00 0 0.00e+00 100 MatTrnMatMultSym 1 1.0 3.5031e+00 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 11 0 0 0 0 11 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 MatCUSPARSCopyTo 19 1.0 1.5878e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 1 0 0 0 0 1 0 0 0 0 0 0 19 1.40e+03 0 0.00e+00 0 MatCUSPARSCopyFr 12 1.0 1.2665e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 12 3.77e+02 0 MatCUSPARSSolAnl 2 1.0 5.3567e-03 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 MatCUSPARSGenT 6 1.0 1.7722e-02 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 KSPSetUp 15 1.0 1.4330e+00 1.0 1.61e+09 1.0 0.0e+00 0.0e+00 0.0e+00 5 6 0 0 0 5 6 0 0 0 1125 57233 56 2.03e+02 50 1.19e+02 54 KSPSolve 1 1.0 1.1262e+01 1.0 1.92e+10 1.0 0.0e+00 0.0e+00 0.0e+00 36 72 0 0 0 36 72 0 0 0 1702 72783 267 8.37e+02 516 1.23e+03 47 KSPGMRESOrthog 111 1.0 6.5277e-02 1.0 2.67e+09 1.0 0.0e+00 0.0e+00 0.0e+00 0 10 0 0 0 0 10 0 0 0 40947 82665 50 1.19e+02 0 0.00e+00 99 DMCreateMat 1 1.0 2.1166e+00 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 7 0 0 0 0 7 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 SFSetGraph 1 1.0 4.9719e-03 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 VecMDot 111 1.0 4.3884e-02 1.0 1.34e+09 1.0 0.0e+00 0.0e+00 0.0e+00 0 5 0 0 0 0 5 0 0 0 30455 67140 50 1.19e+02 0 0.00e+00 99 VecTDot 24 1.0 2.1719e-01 1.0 4.32e+08 1.0 0.0e+00 0.0e+00 0.0e+00 1 2 0 0 0 1 2 0 0 0 1989 0 0 0.00e+00 0 0.00e+00 0 VecNorm 136 1.0 1.3871e-01 1.0 5.34e+08 1.0 0.0e+00 0.0e+00 0.0e+00 0 2 0 0 0 0 2 0 0 0 3848 33411 5 1.19e+01 0 0.00e+00 49 VecScale 123 1.0 1.5541e-02 1.0 1.50e+08 1.0 0.0e+00 0.0e+00 0.0e+00 0 1 0 0 0 0 1 0 0 0 9641 57362 0 0.00e+00 0 0.00e+00 88 VecCopy 248 1.0 3.9159e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 1 0 0 0 0 1 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 VecSet 397 1.0 3.4404e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 1 0 0 0 0 1 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 VecAXPY 36 1.0 2.0782e-01 1.0 4.74e+08 1.0 0.0e+00 0.0e+00 0.0e+00 1 2 0 0 0 1 2 0 0 0 2281 97133 0 0.00e+00 0 0.00e+00 5 VecAYPX 479 1.0 7.4606e-01 1.0 1.37e+09 1.0 0.0e+00 0.0e+00 0.0e+00 2 5 0 0 0 2 5 0 0 0 1832 23794 130 3.10e+02 0 0.00e+00 17 VecAXPBYCZ 156 1.0 3.0376e-01 1.0 1.56e+09 1.0 0.0e+00 0.0e+00 0.0e+00 1 6 0 0 0 1 6 0 0 0 5129 61327 130 3.10e+02 0 0.00e+00 25 VecMAXPY 123 1.0 3.1475e-02 1.0 1.59e+09 1.0 0.0e+00 0.0e+00 0.0e+00 0 6 0 0 0 0 6 0 0 0 50647 108009 0 0.00e+00 0 0.00e+00 98 VecAssemblyBegin 1 1.0 1.1520e-06 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 VecAssemblyEnd 1 1.0 7.0000e-08 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 VecPointwiseMult 66 1.0 8.7004e-03 1.0 1.15e+08 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 13266 39381 6 8.39e+01 0 0.00e+00 100 VecSetRandom 6 1.0 3.1645e-04 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 VecNormalize 123 1.0 4.3463e-02 1.0 4.50e+08 1.0 0.0e+00 0.0e+00 0.0e+00 0 2 0 0 0 0 2 0 0 0 10343 38813 5 1.19e+01 0 0.00e+00 88 VecCUDACopyTo 343 1.0 1.0832e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 343 1.38e+03 0 0.00e+00 0 VecCUDACopyFrom 583 1.0 1.2651e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 583 1.60e+03 0 PCGAMGGraph_AGG 6 1.0 4.1480e+00 1.0 1.29e+08 1.0 0.0e+00 0.0e+00 0.0e+00 13 0 0 0 0 13 0 0 0 0 31 0 6 8.39e+01 11 2.40e+02 0 PCGAMGCoarse_AGG 6 1.0 6.8863e+00 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 22 0 0 0 0 22 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 PCGAMGProl_AGG 6 1.0 1.4945e+00 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 5 0 0 0 0 5 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 PCGAMGPOpt_AGG 6 1.0 1.7024e+00 1.0 4.41e+09 1.0 0.0e+00 0.0e+00 0.0e+00 5 17 0 0 0 5 17 0 0 0 2589 35696 31 1.22e+03 24 5.42e+02 99 GAMG: createProl 6 1.0 1.4314e+01 1.0 4.54e+09 1.0 0.0e+00 0.0e+00 0.0e+00 46 17 0 0 0 46 17 0 0 0 317 35515 37 1.30e+03 35 7.82e+02 97 Graph 12 1.0 4.1173e+00 1.0 1.29e+08 1.0 0.0e+00 0.0e+00 0.0e+00 13 0 0 0 0 13 0 0 0 0 31 0 6 8.39e+01 11 2.40e+02 0 MIS/Agg 6 1.0 1.1043e+00 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 4 0 0 0 0 4 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 SA: col data 6 1.0 3.2944e-02 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 SA: frmProl0 6 1.0 1.3765e+00 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 4 0 0 0 0 4 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 SA: smooth 6 1.0 6.5276e-01 1.0 2.23e+08 1.0 0.0e+00 0.0e+00 0.0e+00 2 1 0 0 0 2 1 0 0 0 341 2956 18 4.73e+02 18 4.58e+02 88 GAMG: partLevel 6 1.0 6.4355e-01 1.0 1.40e+09 1.0 0.0e+00 0.0e+00 0.0e+00 2 5 0 0 0 2 5 0 0 0 2169 6568 6 4.32e+02 12 3.42e+02 100 PCGAMG Squ l00 1 1.0 3.5031e+00 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00 11 0 0 0 0 11 0 0 0 0 0 0 0 0.00e+00 0 0.00e+00 0 PCGAMG Gal l00 1 1.0 4.3696e-01 1.0 8.01e+08 1.0 0.0e+00 0.0e+00 0.0e+00 1 3 0 0 0 1 3 0 0 0 1834 6846 1 3.12e+02 2 2.52e+02 100 PCGAMG Opt l00 1 1.0 2.5304e-01 1.0 9.00e+07 1.0 0.0e+00 0.0e+00 0.0e+00 1 0 0 0 0 1 0 0 0 0 356 3084 1 1.44e+02 1 1.22e+02 100 PCGAMG Gal l01 1 1.0 1.3747e-01 1.0 4.15e+08 1.0 0.0e+00 0.0e+00 0.0e+00 0 2 0 0 0 0 2 0 0 0 3017 7195 1 9.60e+01 2 7.43e+01 100 PCGAMG Opt l01 1 1.0 5.7769e-02 1.0 2.74e+07 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 474 2420 1 2.01e+01 1 2.52e+01 100 PCGAMG Gal l02 1 1.0 5.0812e-02 1.0 1.59e+08 1.0 0.0e+00 0.0e+00 0.0e+00 0 1 0 0 0 0 1 0 0 0 3123 5805 1 2.22e+01 2 1.46e+01 100 PCGAMG Opt l02 1 1.0 1.7501e-02 1.0 1.02e+07 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 582 1469 1 3.41e+00 1 5.08e+00 100 PCGAMG Gal l03 1 1.0 1.0274e-02 1.0 1.97e+07 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 1917 2968 1 2.16e+00 2 1.35e+00 100 PCGAMG Opt l03 1 1.0 3.9484e-03 1.0 1.29e+06 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 326 791 1 3.07e-01 1 4.79e-01 100 PCGAMG Gal l04 1 1.0 4.7975e-03 1.0 1.43e+06 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 297 547 1 1.44e-01 2 8.87e-02 100 PCGAMG Opt l04 1 1.0 2.0451e-03 1.0 9.33e+04 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 46 105 1 2.10e-02 1 3.28e-02 100 PCGAMG Gal l05 1 1.0 3.2192e-03 1.0 4.67e+04 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 15 37 1 4.15e-03 2 2.63e-03 100 PCGAMG Opt l05 1 1.0 1.8375e-03 1.0 5.60e+03 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 3 7 1 1.53e-03 1 1.64e-03 100 PCSetUp 2 1.0 1.6304e+01 1.0 7.54e+09 1.0 0.0e+00 0.0e+00 0.0e+00 52 28 0 0 0 52 28 0 0 0 463 18952 103 1.94e+03 98 1.24e+03 88 PCSetUpOnBlocks 13 1.0 6.0370e-03 1.0 1.31e+02 1.0 0.0e+00 0.0e+00 0.0e+00 0 0 0 0 0 0 0 0 0 0 0 0 4 6.08e-04 1 2.88e-04 0 PCApply 13 1.0 1.0392e+01 1.0 1.69e+10 1.0 0.0e+00 0.0e+00 0.0e+00 33 63 0 0 0 33 63 0 0 0 1626 71002 266 7.65e+02 516 1.23e+03 48 --------------------------------------------------------------------------------------------------------------------------------------------------------------- Memory usage is given in bytes: Object Type Creations Destructions Memory Descendants' Mem. Reports information only for process 0. --- Event Stage 0: Main Stage Krylov Solver 21 21 383400 0. DMKSP interface 1 1 664 0. Matrix 46 46 3358684572 0. Matrix Coarsen 6 6 3792 0. Matrix Null Space 2 2 1216 0. Distributed Mesh 18 18 91520 0. Index Set 11 11 36010016 0. IS L to G Mapping 1 1 36000680 0. Star Forest Graph 37 37 40392 0. Discrete System 18 18 16272 0. Weak Form 18 18 11232 0. Vector 258 258 3033930352 0. Preconditioner 21 21 20744 0. Viewer 3 2 1696 0. PetscRandom 12 12 8088 0. ======================================================================================================================== Average time to get PetscTime(): 3.51e-08 #PETSc Option Table entries: -da_grid_x 3000 -da_grid_y 3000 -ksp_monitor -ksp_type cg -ksp_view -log-view -log_view -mat_type aijcusparse -pc_gamg_agg_nsmooths 1 -pc_gamg_type agg -pc_type gamg -vec_type cuda #End of PETSc Option Table entries Compiled without FORTRAN kernels Compiled with full precision matrices (default) sizeof(short) 2 sizeof(int) 4 sizeof(long) 8 sizeof(void*) 8 sizeof(PetscScalar) 8 sizeof(PetscInt) 4 Configure options: --with-cuda --with-64-bit-indices=0 --with-precision=double --with-debugging=0 --COPTFLAGS=-O3 --CXXOPTFLAGS=-O3 --FOPTFLAGS=-O3 --prefix=/opt/openfoam/ThirdParty/platforms/linux64GccDPInt32/petsc-git --with-hypre --with-hypre-dir=/opt/hypre PETSC_ARCH=linux64GccDPInt32Opt --doCleanup=1 --force ----------------------------------------- Libraries compiled on 2022-03-15 06:27:16 on 15182d0f546e Machine characteristics: Linux-5.4.0-100-generic-x86_64-with-glibc2.29 Using PETSc directory: /opt/openfoam/ThirdParty/platforms/linux64GccDPInt32/petsc-git Using PETSc arch: ----------------------------------------- Using C compiler: mpicc -fPIC -Wall -Wwrite-strings -Wno-strict-aliasing -Wno-unknown-pragmas -fstack-protector -fvisibility=hidden -O3 ----------------------------------------- Using include paths: -I/opt/openfoam/ThirdParty/platforms/linux64GccDPInt32/petsc-git/include -I/opt/hypre/include -I/usr/local/cuda/include ----------------------------------------- Using C linker: mpicc Using libraries: -Wl,-rpath,/opt/openfoam/ThirdParty/platforms/linux64GccDPInt32/petsc-git/lib -L/opt/openfoam/ThirdParty/platforms/linux64GccDPInt32/petsc-git/lib -lpetsc -Wl,-rpath,/opt/hypre/lib -L/opt/hypre/lib -Wl,-rpath,/usr/local/cuda/lib64 -L/usr/local/cuda/lib64 -lHYPRE -llapack -lblas -lm -lcudart -lcufft -lcublas -lcusparse -lcusolver -lcurand -lquadmath -lstdc++ -ldl