Re: [deal.II] p4est critical number of elements in each Proc

Hi Phani, My case is a little bit more complicated than yours. But you are right, one of the bugs is exactly what you said, namely, I forgot to use this "max" collective operation to collect these two flags. Another bug is tricky for me, actually I still do not know this bug's reason. This bug dis

Re: [deal.II] TBB error inside FESystem constructor when using development version dealii (dealii-8.5.1 works fine) in debug mode

On Thu, Mar 22, 2018, at 02:50 CDT, Sambit Das wrote: > Hi Matthias, > > I reinstalled dealii to use external tbb library and that resolved my issue > :) > I used the following additional flags: > > -DDEAL_II_WITH_THREADS=ON > -DTBB_INCLUDE_DIRS="/sw/arcts/centos7/intel/18.1/compilers_and_lib

[deal.II] Re: Adding an independent DoF to a Trilinos system

I did some digging into the Trilinos reinit_matrix, and I've found that all of my lost time is coming from the operation graph->FillComplete(input_col_map, input_row_map) This step is accounting for as much as 20 seconds per call for a 1x200,000 matrix on 4 processors. I also found that this

Re: [deal.II] p4est critical number of elements in each Proc

HI Qing, I do not know how your mesh generation algorithm works. In my case I have a parameter called refine_flag which is set to 1 on a given processor if any cells in that processor have to be refined. Then I call triangulation.execute_coarsening_and_refinement(); only if refine_flag is 1. Lets

[deal.II] For docker, cmake runs examples fine when I run it in the pre-installed src example folder, but not after I copied it to ~/shared

Short summary: cmake runs examples fine when I run it in the pre-installed src example folder, but not after I copied it to ~/shared. Could you please help see why? Full story: first, when I run it in the pre-installed src example folder, it works: ``` E:\dealii>docker pull dealii/dealii:v8.5.

Re: [deal.II] p4est critical number of elements in each Proc

Hi Phani, So what was that MPI bug? Could you share your solution? I have a similar deadlock. Thank you! Best, Qing On Tuesday, December 12, 2017 at 9:29:36 AM UTC-7, Phani Motamarri wrote: > > Thanks for your reply Dr Wolfgang. It was my bad, I had a MPI bug in my > code which was causing

[deal.II] Reason for SolverGMRES being slower in parallel?

Hi, I'm going to solve a Schur complement in my preconditioner for SUPG stabilized fluid solver and will be using ILU(0) decomposition. Since the BlockJacobi does not turn out to work well, I wrote a wrapper for Pilut, which is a package for ILUT decomposition in Hypre and wrapped by PETSc. I t

Re: [deal.II] TBB error inside FESystem constructor when using development version dealii (dealii-8.5.1 works fine) in debug mode

Hi Matthias, I reinstalled dealii to use external tbb library and that resolved my issue :) I used the following additional flags: -DDEAL_II_WITH_THREADS=ON -DTBB_INCLUDE_DIRS="/sw/arcts/centos7/intel/18.1/compilers_and_libraries_2018.1.163/linux/tbb/include/tbb" -DTBB_USER_INCLUDE_DIRS="/sw