[Trilinos-Users] Typical memory usage of Epetra_FECrsMatrix?

[Heroux, Michael A]

James,

The final optimized data structure for FECrsMatrix should contain NZ doubles and (NZ+N) ints, where NZ is the total number of nonzeros and N is the problem dimension.

I am not sure if there are auxiliary data structures associated with collecting off-processor contributions, but even if there are, they should hopefully be small.

If this is insufficient information, let me know.

Mike

On May 21, 2013, at 8:44 AM, "Ramsey, James J CIV (US)" <james.j.ramsey14.civ at mail.mil> wrote:

> I'm trying to get a sense of what the expected memory usage of a Epetra_FECrsMatrix should be, given a certain number of rows and nonzeros per row. I've seen the description of the CRS format at http://netlib.org/utk/papers/templates/node91.html, but it seems to lead to an underestimation of my memory usage, which worries me. So far, using the "massif" tool from valgrind tells me that my program used about 193 MB of heap memory for a finite element problem with 29,791 brick elements and 3 DOF per node, and about 800 MB of the heap for a similar finite element problem, but with 125,000 elements. I know that there are typically 81 nonzeros per row here in these particular problems. Looking at GNOME's system monitor shows me the resident memory usage is more like 500 and 900 MB, respectively. Does this look to be in the ballpark of reasonableness (taking into account the other data structures in the program that also take up memory), or should I be more suspicious?
> _______________________________________________
> Trilinos-Users mailing list
> Trilinos-Users at software.sandia.gov
> http://software.sandia.gov/mailman/listinfo/trilinos-users
>