Intel compilers and libraries

C J Kenneth Tan -- Heuchera Technologies cjtan at optimanumerics.com
Mon Oct 6 10:54:43 EDT 2003


Jose,

Pardon me for some advertising here, but our OptimaNumerics Linear
Algebra Library can very significantly outperform Intel MKL.
Depending on the particular routine and platform, we have seen
performance advantage of almost 32x (yes, that's 32 times!) using
OptimaNumerics Linear Algebra Library!

I can send you one of our white papers which shows performance
benchmark details off-line.  If anyone else is interested, please do
send me an e-mail also.


Best wishes,
Kenneth Tan
-----------------------------------------------------------------------
C. J. Kenneth Tan, Ph.D.
Heuchera Technologies Ltd.
E-mail: cjtan at OptimaNumerics.com      Telephone: +44 798 941 7838
Web: http://www.OptimaNumerics.com    Facsimile: +44 289 066 3015
-----------------------------------------------------------------------
This e-mail (and any attachments) is confidential and privileged.  It
is intended only for the addressee(s) stated above.  If you are not an
addressee, please accept my apologies and please do not use,
disseminate, disclose, copy, publish or distribute information in this
e-mail nor take any action through knowledge of its contents: to do so
is strictly prohibited and may be unlawful.  Please inform me that
this e-mail has gone astray, and delete this e-mail from your system.
Thank you for your co-operation.
-----------------------------------------------------------------------




On Mon, 6 Oct 2003, [iso-8859-1] Jos? M. P?rez S?nchez wrote:

> Date: Mon, 06 Oct 2003 13:21:02 +0200
> From: "[iso-8859-1] Jos? M. P?rez S?nchez" <iosephus at sgirmn.pluri.ucm.es>
> To: beowulf at beowulf.org
> Subject: Intel compilers and libraries
>
> Hello:
>
> We are thinking about purchasing the Intel C++ compiler for linux,
> mainly for getting the most of our harware (Xeon 2.4Gz processors), we
> are also interested in the Intel MKL (Math Kernel Library), I would like
> to know if the performance gain using Intel compiler+libraries, which exploit
> SSE2 and make other optimizations for P4/Xeon, are as good as Intel
> claims, anyone in the list using those products?
>
> On the other hand, isn't MKL just as good as any other good math library compiled
> with Xeon/P4 optimization and extensions (using Intel C++ compiler for
> example).
>
> Another question, the only difference I can see reading Intel docs between
> P4 and Xeon is more cache on Xeon, and HyperThreading (below P4/Xeon 3Ghz),
> does it really makes a big difference taking into account the much more
> expensive Xeons are. Any one having experience with both platforms.
>
> Greetings:
>
> Jose M. P?rez.
> Madrid. Spain.
>
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org
> To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
>
_______________________________________________
Beowulf mailing list, Beowulf at beowulf.org
To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf



More information about the Beowulf mailing list