This is the mail archive of the gsl-discuss@sourceware.org mailing list for the GSL project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: gslclapack


Brian,

On 2006-03-28 12:48 +0100 Brian Gough (bjg@network-theory.co.uk) wrote:

> Date: Tue, 28 Mar 2006 12:48:30 +0100
> From: Brian Gough <bjg@network-theory.co.uk>
> To: James Bergstra <james.bergstra@umontreal.ca>
> Cc: gsl-discuss <gsl-discuss@sources.redhat.com>
> Subject: Re: gslclapack
> 
> James Bergstra writes:
>  > On one hand, I'm jealous that lapack has a fancy routine, and react "let's
>  > implement that for gsl too" and on the other hand, I think "why is gsl
>  > re-implementing (what I believe is) a very standard library?"
> 
> LAPACK is huge & tedious to install.  GSL is meant to be easy to use -
> a dependency on lapack would be a pain.

How do you find LAPACK being a pain?  The public version of LAPACK has
been well tested and the design has been well thought out.  It has a
very comprehensive test suite also. 

Having LAPACK in the backend would also enable GSL users to take
advantage of high performance implementations of LAPACK.  We are able
to deliver substantially better performance LAPACK in OptimaNumerics
Libraries (even when compared to commercial products).  Some benchmark
results are included here:
http://www.OptimaNumerics.com/docs/hpc-asia05/hpc-asia05.pdf .

What's the price of performance?  This question can be phrased as
what's the price of electricity and what's the price of server room
space.


Kenneth Tan
-----------------------------------------------------------------------
C J Kenneth Tan, PhD
OptimaNumerics Ltd                    Telephone: +44 798 941 7838
E-mail: cjtan@OptimaNumerics.com      Telephone: +44 207 099 4428
Web: http://www.OptimaNumerics.com    Facsimile: +44 207 100 4572
-----------------------------------------------------------------------


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]