[Numpy-discussion] additional dtype argument to numpy.dot() (Re: Numpy-discussion Digest, Vol 29, Issue 48)

[David Cournapeau]

On Thu, Feb 19, 2009 at 2:37 AM, David Henderson
<davidh at ipac.caltech.edu> wrote:
> Hi Paul, list:
>
> Thanks for the reply.
>
> numpy.sum()  does indeed have a dtype for the accumulator for the
> sum. numpy.sum() does not implement an inner (dot) product, just a
> straight summation.

You may be interested in xblas, which is a new BLAS specification
which explicitly handle mixed precision and increased accumulator
precision:

http://www.netlib.org/xblas/

For now, it is completely unsupported in numpy, but this may be a good
thing to add if you are interested in extra precision,

David