The output is:
local_size = 25, on process 0
rstart = 0, on process 0
rend = 25, on process 0
local_size = 25, on process 1
rstart = 0, on process 1
rend = 25, on process 1
local_size = 25, on process 2
rstart = 0, on process 2
rend = 25, on process 2
local_size = 25, on process 3
rstart = 0, on process 3
rend = 25, on process 3
Using PETSC_COMM_SELF has no effect.
Am Freitag, 23. November 2018, 18:02:45 MEZ hat zakaryah
<[email protected]> Folgendes geschrieben:
What does your output look like? With PETSC_COMM_WORLD, I think you will only
get the output from the rank 0 process. Try with PETSC_COMM_SELF.
On Fri, Nov 23, 2018, 11:56 AM Matthew Knepley via petsc-users
<[email protected] wrote:
On Fri, Nov 23, 2018 at 9:54 AM Klaus Burkart via petsc-users
<[email protected]> wrote:
Hello,
I am trying to compute the local row ranges allocated to the processes i.e.
rstart and rend of each process, needed as a prerequisite for
MatMPIAIJSetPreallocation using d_nnz and o_nnz.
I tried the following:
...
PetscInitialize(0,0,PETSC_NULL,PETSC_NULL);
MPI_Comm_size(PETSC_COMM_WORLD,&size);
MPI_Comm_rank(PETSC_COMM_WORLD,&rank);
MatCreate(PETSC_COMM_WORLD,&A);
MatSetType(A,MATMPIAIJ);
PetscInt local_size = PETSC_DECIDE;
PetscSplitOwnership(PETSC_COMM_WORLD, &local_size, &N);
MPI_Scan(&local_size, &rend, 1, MPIU_INT, MPI_SUM, PETSC_COMM_WORLD);
This looks right to me. Not sure what your problem is. However, you can always
use PetscLayout to dothis automatically.
Thanks,
Matt
rstart = rend - local_size;
PetscInt d_nnz[local_size], o_nnz[local_size];
/*
compute d_nnz and o_nnz here
MatMPIAIJSetPreallocation(A,0,d_nnz,0,o_nnz);
*/
for (rank = 0; rank < size; rank++) {
PetscPrintf(PETSC_COMM_WORLD,"local_size = %d, on process %d\n",
local_size, rank);
PetscPrintf(PETSC_COMM_WORLD,"rstart = %d, on process %d\n", rstart, rank);
PetscPrintf(PETSC_COMM_WORLD,"rend = %d, on process %d\n", rend, rank);
}
PetscFinalize();
The local size is 25 rows on each process but rstart and rend are 0 and 25 on
all processes, I expected 0 and 25, 25 and 50, 50 and 75 and 75 and 101. N = 100
I can't spot the error. Any ideas, what's the problem?
Klaus
--
What most experimenters take for granted before they begin their experiments is
infinitely more interesting than any results to which their experiments lead.
-- Norbert Wiener
https://www.cse.buffalo.edu/~knepley/
