[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: OSKI, an automatically tuned sparse kernel library.
From: |
Andy Adler |
Subject: |
Re: OSKI, an automatically tuned sparse kernel library. |
Date: |
Sat, 9 Jul 2005 06:16:49 -0400 (EDT) |
On Wed, 29 Jun 2005, Richard Vuduc wrote:
> David Bateman wrote:
> > It looks interesting. Octave at the moment has a pretty good sparse
> > matrix mul code, that is significantly faster than matlab for most
> > densities. Matlab beats octave for very low densities.
>
> This is very interesting, and is the sort of issue OSKI addresses
> since tuning is both matrix- and machine-specific.
I've been trying to work on the octave sparse matrix multiply code;
I have a patch for low density sparse matrices that should
increase the performance by about 4x. When I get back from my
vacation (end-July), I'll test and submit it.
I wanted to try to compare this to the OSKI performance. OSKI
provides a "make benchmarks" function with looks promising.
Unfortunately, I couldn't find a way to compare to octave
performance easily.
1. OSKI benchmarks creates its own test matrices. There doesn't
seem to be a way to enter or save these to be tested elsewhere.
2. I wasn't able to find test code for sparse x sparse function.
Richard, would you be able to offer some advice?
--
Andy Adler <address@hidden> 1(613)562-5800x6218
- Re: OSKI, an automatically tuned sparse kernel library.,
Andy Adler <=