Community
cancel
Showing results for 
Search instead for 
Did you mean: 
h88433
Beginner
43 Views

MKL Pardiso Performance on multi core processors

Hello,

I have been running the parallel version of the MKL with Pardiso as a solver in finite element applications. I have run on both dual and quad core intel machines. It seems that the performance gain in parallel mode is not muchfaster than sequential mode. I was just doing some reading in the Pardiso manual (university of Basel) and read the following,

(o) Reproducibility of exact numerical results staon multi-core architectures. The solver is now able to compute the exact bit identical solution independent on the number of cores without effecting the scalability.
Here are some results for a nonlinear FE model with 500'000 elements.

Intel MKL PARDISO 10.2

1 core - factor: 17.980 sec., solve: 1.13 sec.

2 cores - factor: 9.790 sec., solve: 1.13 sec.

4 cores - factor: 6.120 sec., solve: 1.05 sec.

8 cores - factor: 3.830 sec., solve: 1.05 sec.

U Basel PARDISO 4.0.0:

1 core - factor: 16.820 sec., solve: 1.09 sec.

2 cores - factor: 9.021 sec., solve: 0.67 sec.

4 cores - factor: 5.186 sec., solve: 0.53 sec.

8 cores - factor: 3.170 sec., solve: 0.43 sec.

This method is currently only working for symmetric indefinite matrices.

This seems to be consistent with what I am experiencing using the MKL 10.2. Do we get updated versions of Pardiso from Basel ?
john

0 Kudos
2 Replies
Gennady_F_Intel
Moderator
43 Views

john, this is well know problem for us and we are working on it.There is no updated version yet. i will inform you when it will available.--Gennady
h88433
Beginner
43 Views

Hi Gennady, thnaks again for your quick reply. I am very pleased to hear that there will be an update. Will this be Pardiso 4.0 ? Any idea when that may take place ?
john
Reply