[R-SIG-Mac]compiling with atlas

[Jan de Leeuw]

Well, I am no so sure either -- but I'll check my no-atlas against
atlas on the same machine soon. Altivec is of little use for double
precision floating point, of course.

On Friday, February 1, 2002, at 08:16 AM, Thomas Lumley wrote:

> On Fri, 1 Feb 2002, Wiener, Matthew wrote:
>
>> One additional question on atlas:  for R, is it generally worth it to
>> optimize BLAS level 1?  I chose yes because I didn't know.  But if 
>> it's not
>> that important, I'd be happy to save the time someday when I need to 
>> update.
>
> Probably not -- in the old days when we only used the Level 1 BLAS there
> seemed to be little performance gain from ATLAS on Linux or from the Sun
> BLAS on Solaris. YMMV, of course. In particular the Altivec instructions
> on G4s could help noticeably.
>
> 	-thomas
>
> _______________________________________________
> R-SIG-Mac mailing list
> R-SIG-Mac@stat.math.ethz.ch
> http://www.stat.math.ethz.ch/mailman/listinfo/r-sig-mac
>
>
===
Jan de Leeuw; Professor and Chair, UCLA Department of Statistics;
US mail: 9432 Boelter Hall, Box 951554, Los Angeles, CA 90095-1554
phone (310)-825-9550;  fax (310)-206-5658;  email: deleeuw@stat.ucla.edu
homepage: http://www.stat.ucla.edu/~deleeuw
========================================================
           No matter where you go, there you are. --- Buckaroo Banzai
                    http://www.stat.ucla.edu/~deleeuw/sounds/nomatter.au
========================================================