G4's for scientific computing

Eray Ozkural erayo at cs.bilkent.edu.tr
Sun Apr 14 21:08:39 PDT 2002


-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On Monday 15 April 2002 04:57, William R. Pearson wrote:
>
> I might have agreed with the statement that one must have hand-tuned
> Altivec code which pretty much excludes general purpose scientific
> computing 4 months ago, but our experience has been very positive -
> our programs are not specialized signal processing programs, but, in
> retrospect, it was easy to get very dramatic speed up.
>

I imagine fake vector processing would only work for certain type of problems. 
That's not SIMD by any measure. Don't you really need multiple data streams 
for general purpose HPC?

Regards,

- -- 
Eray Ozkural (exa) <erayo at cs.bilkent.edu.tr>
Comp. Sci. Dept., Bilkent University, Ankara
www: http://www.cs.bilkent.edu.tr/~erayo  Malfunction: http://mp3.com/ariza
GPG public key fingerprint: 360C 852F 88B0 A745 F31B  EA0F 7C07 AE16 874D 539C
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.0.6 (GNU/Linux)
Comment: For info see http://www.gnupg.org

iD8DBQE8ulJHfAeuFodNU5wRAn7oAJ9n7oJC3nfBv29EBYOpypOjBGLUmACcCmPO
kY+ZBvrh1ev4iQnFMkQV4IA=
=YeV6
-----END PGP SIGNATURE-----




More information about the Beowulf mailing list