Intel compilers and libraries

C J Kenneth Tan -- Heuchera Technologies cjtan at
Thu Oct 9 06:04:20 EDT 2003


> Is it a 100x100 matrix LU decomposition? Well, no, because Intel's
> MKL and the free ATLAS library run at a respectable % of peak.

Our benchmarks concentrate on xGEQRF, xGESVD, xGETRF, xGETRS, xGESV,
xPOTRF, xPOSV, xPPTRF, xGEEV, extending to xGETRI, and xTRTRI.

Have you tried DPPSV or DPOSV on Itanium, for example?  I would be
interested in the percentage of peak that you achieve with MKL and
ATLAS, for up to 10000x10000 matrices.

ATLAS does not have full LAPACK implementation.

> 4) Put your performance whitepapers on your website, or it looks
> fishy.

Our white papers are not on the Web they contain performance data, and
particularly, performance data comparing against our competitors.  It
may expose us to libel legal issues.  Putting legitimacy of any legal
issues aside, it is not good for any business to be engulf in legal
squabbles.  We are in the process of clearing this with our legal
department at the moment.

As I have noted in my previous e-mail, anyone who wants to get a hold
of the white papers are welcome to please send me an e-mail.

> I looked and didn't see a single performance claim there.

There is one on the front page!

C. J. Kenneth Tan, Ph.D.
Heuchera Technologies Ltd.
E-mail: cjtan at      Telephone: +44 798 941 7838
Web:    Facsimile: +44 289 066 3015
Beowulf mailing list, Beowulf at
To change your subscription (digest mode or unsubscribe) visit

More information about the Beowulf mailing list