From: Steven Watanabe (steven_at_[hidden])
Date: 2007-04-04 15:53:28
Martin Schulz <Martin.Schulz <at> synopsys.com> writes:
> > I'm not sure why my simple matrix multiplication results are
> > so much slower...the others are comparable.
> This could be very well a cache size issue.
That's exactly what's happening. The basic matrix
multiplication algorithm used by ublas is very cache
unfriendly for large matrices. The ublas version is
primarily to make sure that my implementation is
Boost list run by bdawes at acm.org, gregod at cs.rpi.edu, cpdaniel at pacbell.net, john at johnmaddock.co.uk