Intel® Fortran Compiler
Build applications that can scale for the future with optimized code designed for Intel® Xeon® and compatible processors.
29238 Discussions

Parallel performance - Dual P4 Xeon

damien_veyret7
Beginner
‎09-03-2002 05:46 AM
408 Views
I want to parallelize a (very big) sparse matrix-vector multiplication on a Dual Intel P4 Xeon. I tried the Qparallel option and the OpenMP directives : in both cases, it takes longer than using one CPU ...
I've read that a poor cache utilization (or a memory bandwith limitation) could be the cause. Is that true ? Can some third-party products (like NAG library) help ?

Damien Veyret
0 Kudos

Link Copied

1 Reply
Steven_L_Intel1
Employee
‎09-03-2002 01:31 PM
408 Views
This is not an area I am an expert in, but I'd think it would be an ideal application for the Intel VTune performance analyzer. Rather than guessing, use VTune to see where your program is spending its time and let it make suggestions for improvements. If you haven't tried it, you should - it's quite impressive! There's a 30-day free trial. You may also want to see if the Intel Performance Libraries can be of help.

http://developer.intel.com/software/products/

Steve
0 Kudos
Copy link
Reply

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

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