[petsc-users] AllReduce function for mat

[Ghosh, Swarnava]

The matrix is dense and each process has the same number of nonzeros.

----- Original Message -----
From: "Barry Smith" <bsmith at mcs.anl.gov>
To: "Swarnava Ghosh" <sghosh2012 at gatech.edu>
Cc: "PETSc users list" <petsc-users at mcs.anl.gov>
Sent: Monday, February 9, 2015 12:11:07 PM
Subject: Re: [petsc-users] AllReduce function for mat


> On Feb 9, 2015, at 10:57 AM, Ghosh, Swarnava <sghosh2012 at gatech.edu> wrote:
> 
> Hi,
> 
>   I have sequential matrix on each process. I wanted to do something like MPI_Allreduce to this matrix to add entries from all processes. The resulting matrix is sequential. 

   Is the matrix dense or sparse?
   If sparse is each process providing a different set of nonzero values? Or are all processes providing ALL nonzeros in the matrix (to be added together). 

>   I wanted to know if there is a PETSc function to do this?
> 
> -- 
> SG
> 


--