From help-octave-request at bevo dot che dot wisc dot edu Fri Feb 4 19:44:57 2000 Subject: Re: ATLAS and octave (and HDF5 too!) From: "O. Scott Sands" To: "John W. Eaton" CC: "Timothy H. Keitt" , R Clint Whaley , atlas@cs.utk.edu, help-octave@bevo.che.wisc.edu, Van den Eynde Gert , "stevenj@alum.mit.edu" Date: Fri, 04 Feb 2000 20:44:52 -0500 --------------73B88615218D27FBD1C68F1E Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit "John W. Eaton" wrote: > On 4-Feb-2000, Timothy H. Keitt wrote: > > | Sounds good to me. > > Yes, I am also interested in this. The last time I checked up on > atlas, I thought it looked promising, but it was not really ready. > But if it supports all of the level 1 and 2 blas plus some lapack [snip] > ms, > and it will not require tweaking the configure script for each new > vendor blas. > > jwe > > ----------------------------------------------------------------------- > Octave is freely available under the terms of the GNU GPL. > > Octave's home on the web: http://www.che.wisc.edu/octave/octave.html > How to fund new projects: http://www.che.wisc.edu/octave/funding.html > Subscription information: http://www.che.wisc.edu/octave/archive.html > ----------------------------------------------------------------------- Thanks to some help from Van Den Eynde, Gert, I've been hacking ATLAS into Octave bleeding edge releases now for several months. It's wonderful. I get a 6X increase in 500X500 matrix multiplication everywhere I take it. I wasn't aware that the WHOLE BLAS was now part of ATLAS. I guess that I'll have to update my ATLAS! -- O. Scott Sands o dot s dot sands at ieee dot org PS: I'm also very happy with the hdf5 patch that has been contributed by steven j of MIT. This is the only way to store ALL of octave's data structures in a binary format file! --------------73B88615218D27FBD1C68F1E Content-Type: text/html; charset=us-ascii Content-Transfer-Encoding: 7bit "John W. Eaton" wrote:
On  4-Feb-2000, Timothy H. Keitt <keitt at nceas dot ucsb dot edu> wrote:

| Sounds good to me.

Yes, I am also interested in this.  The last time I checked up on
atlas, I thought it looked promising, but it was not really ready.
But if it supports all of the level 1 and 2 blas plus some lapack

[snip]
ms,
and it will not require tweaking the configure script for each new
vendor blas.

jwe

-----------------------------------------------------------------------
Octave is freely available under the terms of the GNU GPL.

Octave's home on the web:  http://www.che.wisc.edu/octave/octave.html
How to fund new projects:  http://www.che.wisc.edu/octave/funding.html
Subscription information:  http://www.che.wisc.edu/octave/archive.html
-----------------------------------------------------------------------

Thanks to some help from Van Den Eynde, Gert, I've been hacking ATLAS
into Octave bleeding edge releases now for several months. It's wonderful.
I get a 6X increase in 500X500 matrix multiplication everywhere I take it.

I wasn't aware that the WHOLE BLAS was now part of ATLAS. I guess that
I'll have to update my ATLAS! 

-- 

O. Scott Sands
o dot s dot sands at ieee dot org


PS: I'm also very happy with the hdf5 patch that has been contributed by
steven j of MIT. This is the only way to store ALL of octave's data structures
in a binary format file!
 
  --------------73B88615218D27FBD1C68F1E-- ----------------------------------------------------------------------- Octave is freely available under the terms of the GNU GPL. Octave's home on the web: http://www.che.wisc.edu/octave/octave.html How to fund new projects: http://www.che.wisc.edu/octave/funding.html Subscription information: http://www.che.wisc.edu/octave/archive.html -----------------------------------------------------------------------