Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

- Intel Community
- Software Development SDKs and Libraries
- Intel® oneAPI Math Kernel Library & Intel® Math Kernel Library
- Back-substitution of Pardiso not executing in parallel

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Mute
- Printer Friendly Page

Highlighted
##

Jens_E_

Beginner

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

03-25-2015
07:33 AM

25 Views

Back-substitution of Pardiso not executing in parallel

All,

In an iterative algorithm I'm reusing the factorization of a symmetric indefinite matrix to solve for different right-hand sides. The back-substitution is performed in a loop with a single right-hand side being sent to pardiso at each time.

I'm using paridiso_64 and mkl 11.1u2.

I'm using vtune to perform a concurrency analysis of the application. The execution of the pardiso factorization step seems to be running efficiently in parallel, so I think I've linked the right mkl libraries. However the back substiution is not parallel. It seems pardiso spawns three openmp workers in my case, and only one is active for the back substitution stages.

I searched the forum and found a thread with a similar question, but I did not find an answer there. However it was mentioned that the back substitution is serial in certain situations.

My iparm is non-default as follows:

iparm[0] = 1; //use non-default values

iparm[1] = 3; //parallel metis nested disection

iparm[26] = 0; //matrix checks

iparm[7] = 2;

iparm[9] = 8;

iparm[10] = 1; //scaling

iparm[12] = 1; //enable matching

iparm[20] = 1; //pivoting

(Otherwise 0. Note the 0 indexing.)

Any suggestions?

Thanks!

Jens

4 Replies

Highlighted
##

Alexander_K_Intel2

Employee

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

03-25-2015
11:50 AM

25 Views

Hi,

Your version of MKL is quite old, could you check you testcase on new version of MKL. During last years performance and scaling of MKL Pardiso solving step have significantly improved

Thanks,

Alex

Highlighted
##

Jens_E_

Beginner

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

03-26-2015
02:31 AM

25 Views

Okay, thanks.

Just to confirm: is back-substitution supposed to be parallel also when used for only a single right hand side?

Jens

Highlighted
##

Alexander_K_Intel2

Employee

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

03-26-2015
02:33 AM

25 Views

Hi Jens,

Sure, solving steps of MKL pardiso parallelized for both one and many rhs.

Thanks,

Alex

Highlighted
##

Jens_E_

Beginner

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

03-26-2015
02:36 PM

25 Views

Thanks, I updated to 11.2 u2, and it works a lot better.

For more complete information about compiler optimizations, see our Optimization Notice.