Boost logo

Ublas :

Subject: Re: [ublas] question about the atlas and
From: Kaveh Kohan (kaveh.kohan_at_[hidden])
Date: 2009-04-01 12:20:04

Could you please refer me to a documentation about MKL libraries? Does it handle sparse matrix too? Is it c++ or ANSI C library. Lastly, you mean I need to link boost with MKL library or it a whole new library?


From: "K.M.A.Chai_at_[hidden]" <K.M.A.Chai_at_[hidden]>
To: ublas_at_[hidden]
Sent: Wednesday, April 1, 2009 12:15:59 PM
Subject: Re: [ublas] question about the atlas and

In terms of speed, note that for the intel platforms, Matlab uses Intel MKL (blas and lapack). My experience is that neither ublas, gsl, nor atlas beats Intel MKL on intel platforms for large matrices.

Hence, if speed is what you want, you may want to link to the MKL libraries.

> - My program involves multiplication of very tall matrix by almost
square matrix (1000000x 30 by 30 x 30). I have performed this multiplication using gsl and it produced the result after 4.1second. Similar operation, using ublas took about 37second! Similar operation takes about 0.5second in MATLAB. I presume that there is a blunder in my program but I cannot figure it out: >

-- The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.

ublas mailing list