So, to do this, would I want to rebuild PETSc using a vendor compiler like
Intel or PGI? Are there other performance benefits to building PETSc with a
vendor compiler such as Intel or PGI besides the benefit of linking with
vendor blas?
Xiaoye S. Li writes:
For SuperLU, MUMPS, UMFPACK etc, you
Thanks for the suggestion. That seems to be the case for me as well. Do you
use UMFPACK via PETSc or directly? Do you use any of the PETSc options for
UMFPACK or recommend any that I should experiment with?
Thanks,
Dave
Stefano Zampini writes:
Try UMFPACK. The fastest for my linear solves.
I have been comparing sequential SuperLU on one of my linear solves versus
PETSc LU. I am finding SuperLU to be a little over 2x slower than PETSc LU.
I was wondering if this is due to SuperLU not being tuned to my problem or if
the PETSc LU algorithm performance is expected to be superior to
Try UMFPACK. The fastest for my linear solves.
2011/12/20 Dave Nystrom dnystrom1 at comcast.net
I have been comparing sequential SuperLU on one of my linear solves versus
PETSc LU. I am finding SuperLU to be a little over 2x slower than PETSc
LU.
I was wondering if this is due to SuperLU
Dave :
I've observed same performance. PETSc LU uses simple algorithm and
implementation,
and our recent releases pay particular attention to efficient data
accessing in solve phase,
thus it outperforms other packages sometime.
SuperLU has built-in schemes, such at row/col permutation, equil etc,
For SuperLU, MUMPS, UMFPACK etc, you need to link with a good BLAS, like
MKL you mentioned. The internal algorithms exploit dense matrix
sub-blocks, and good BLAS usually make a difference. For very sparse
problems, the above packages may not help, since there is not much blocking
to exploit,
