Re: [ublas] Performance with SSE2

From: Ian McCulloch (ianmcc_at_[hidden])
Date: 2007-03-13 00:32:47

Preben Hagh Strunge Holm wrote:

>>> Okay, I use 72x72 matrices and vectors of the size 72. So it might be
>>> beneficial to use atlas-blas then!
>> 
>> Yes, unless your matrices are sparse. "Standard" BLAS only support dense
>> (and sometimes packed, banded) matrices.
> 
> Hmm... most of them are actually sparse (compressed matrix).
> 
> For future optimizations I better try these other proposed methods out.

For size 72, the matrices would have to be *extremely* sparse to see a
speedup over dense routines.  Sparse operations lose a lot of efficiency on
mondern architectures from indirect pointer lookups, and possibly poor
cache performance, whereas vectorized dense operations are getting
relatively faster.  If you try some performance benchmarks of BLAS vs
sparse, it would be interesting to see the results.

Cheers,
Ian