[petsc-users] Columnwise and 2D partitioning for matrices that have irregular sparsity patterns

[R. Oğuz Selvitopi]

Hello,

Is it possible to partition a parallel matrix in PETSc as follows:

A B C
D E F
G H I

The blocks A-D-G belong to processor 0 (A is the diagonal block, D and
G are off-diagonal blocks)

The blocks B-E-H belong to processor 1 (E is the diagonal block, B and
H are off-diagonal blocks)

The blocks C-F-I belong to processor 2 (I is the diagonal block, C and
F are off-diagonal blocks)


Or, is it possible to have nine processors and each has a block of the
matrix above? Block A belongs to processor 0, block B belongs to
processor 1, and so on...


As far as I read from documentation, PETSc always seems to be
considering a rowwise partitioning, where blocks A-B-C belong to
processor 0, D-E-F belong to processor 1 and G-H-I belong to processor
2.

Is there a way to obtain the partitioning schemes I described above?


Thanks in advance.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20140103/5c11cb90/attachment.html>