Hi, I'm not sure if this is a naive question, but is there any speed or performance difference when using VecScatterCreateToZero or similar routine, compared to MPI standard routines such as mpi_gather, mpi_gatherv etc?
Yours sincerely, TAY wee-beng On 16/4/2012 6:26 PM, Jed Brown wrote: > > > On Mon, Apr 16, 2012 at 11:25, Abraham Taicher > <ataicher at ices.utexas.edu <mailto:ataicher at ices.utexas.edu>> wrote: > > Hi, > > I have a parallel vector spread across all processors that I would > like to gather into a single processor, say the root processor. > Is there PETSc functionality to do this? I tried looking for a > PETSc gather function but the one I found, VecStrideGather > > <http://www.mcs.anl.gov/petsc/petsc-current/docs/manualpages/Vec/VecStrideGather.html>, > does not seem to apply. Should I simply use the MPI routine > MPI_Gather? > > > http://www.mcs.anl.gov/petsc/petsc-current/docs/manualpages/Vec/VecScatterCreateToZero.html > -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120417/7fad7999/attachment.htm>
