Re: LAPACK vs. GSL matrix algebra

[Gerard Jungman <jungman at lanl dot gov>]

On Mon, 2004-09-27 at 14:02, Linas Vepstas wrote:
> 
> Did you auto-gen the cblas code and/or headers, or 
> are these hand-written?

In short, it was all done by hand.

The implementation of the GSL native cblas/ was extremely
tedious, but obviously we don't need that step for getting
lapack interfaces.

The stuff in the blas/ directory was not hard, and since
cblas was a stationary target it seemed reasonable to
just do it all by hand. It think it took me one long
afternoon to get it all in, plus some later cleanup.

Questions:

 Is there a C-LAPACK standard, in the same way that
 there is a C-BLAS standard? I think there was some
 work done, but I don't know if it was ever finished.

 Would GSL target a C-LAPACK standard or the standard
 fortran? It is probably more work to target fortran.

 What is the usage model? Suppose somebody wants to
 use GSL interfaces over an external lapack. The external
 lapack is presumably implemented in terms of an external
 blas, probably both in fortran. What if the user also
 uses explicit blas functions (also through a GSL interface)?
 How do we guarantee that the blas called by lapack functions
 is consistent with the blas available through GSL interfaces.
 The goal is to write code using GSL interfaces and be able
 to switch in any conformant linear algebra sub-system with
 at most a re-compile, and perhaps only with a re-link.

 Hasn't somebody done all this already??? And can't
 we arrange so that all the work is done through ATLAS?


We've had these discussions here before. I wish there
was some actual plan to make this all work right.

-- 
Gerard Jungman <jungman@lanl.gov>
Los Alamos National Laboratory