- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I am going to run a CFD simulation that the memory usage will be over 100 GB.
I use mkl PARDISO in order to solve the linear system that arises.
Very recently I informed about Intel Phi coprocessor and their capabilities that has.
In order to accelerate the solving, I was wondering if PARDISO incorporates Intel Phi technology internally in order
not to modify my code.
Thank you in advance.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dionisys, Yes, in MKL version 11.3 we greatly optimized Pardiso Solver for SMP systems and particaly for Xeon Phi Processor. You may have a look at this KB Article: https://software.intel.com/en-us/articles/significant-scalability-and-performance-improvement-for-intel-mkl-pardiso-on-smp-systems
and try to use Pardiso by himself and let us know the results of your experiments.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
you may also have a look at this article ( http://www.scirp.org/journal/PaperInformation.aspx?PaperID=58156 ) where you may see speed up results on Xeon Phi for different stages of Pardiso's computations... all these optimizations are applicable for SMP computations. I hope that helps you to start evaluate this solver on your side.
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page