OONumerics User : |
From: Chris Cheung (cheungcc_at_[hidden])
Date: 2007-06-10 21:02:52
Hi Javier,
ATLAS is a good choice and it supports almost any platform possessing
an ANSI/ISO C compiler. If your platform is x86 or x86_64, you can
consider the following hardware-optimized library:
AMD Core Math Library (http://developer.amd.com/acml.jsp)
Intel Math Kernel Library
(http://www.intel.com/cd/software/products/asmo-na/eng/307757.htm)
They generally have better performance than ATLAS on x86 or x86_64.
cheers,
Chris Cheung
clustertech.com
Javier Civera wrote:
> Hi,
>
> I am developing a software that involves large matrices computations
> (matrix-matrix product, matrix-vector product, inverse). I am using
> Linux and compiling with gcc.
>
> I would like to speed up matrix computations, any suggestion to do that?
> My conclusion, after some web surfing, is that I should use ATLAS. In
> "Automated Empirical Optimization of Software and the ATLAS project" by
> Whaley, Petitet and Dongarra, it seems that computational cost can be
> reduced ten times or more. Has anybody experienced with this library and
> obtained this results?
>
> Anyway, this paper is 7 years old, and I can't find a newer reference. I
> know that in http://math-atlas.sourceforge.net I can find some timings,
> but they are not compared with the timings obtained if you do not use
> ATLAS... Does anybody know recent comparisons about the computational
> saving obtained using ATLAS?
>
> Thank you very much, regards,
> _______________________________________________
> oon-list mailing list
> oon-list_at_[hidden]
> http://www.oonumerics.org/mailman/listinfo.cgi/oon-list
>