[Numpy-discussion] performance matrix multiplication vs. matlab

[Eric Firing]

David Cournapeau wrote:

> 
> It really depends on the CPU, compiler, how atlas was compiled, etc...
> it can be slightly faster to 10 times faster (if you use a very poorly
> optimized ATLAS).
> 
> For some recent benchmarks:
> 
> http://eigen.tuxfamily.org/index.php?title=Benchmark
> 

David,

The eigen web site indicates that eigen achieves high performance 
without all the compilation difficulty of atlas.  Does eigen have enough 
functionality to replace atlas in numpy?  Presumably it would need C 
compatibility wrappers to emulate the blas functions.  Would that kill 
its performance?  Or be very difficult?

(I'm asking from curiosity combined with complete ignorance.  Until 
yesterday I had never even heard of eigen.)

Eric

> cheers,
> 
> David