[Numpy-discussion] Does float16 exist?

Charles R Harris charlesr.harris@gmail....
Mon Jan 7 14:53:06 CST 2008


On Jan 7, 2008 1:00 PM, Darren Dale <darren.dale@cornell.edu> wrote:

> One of my collaborators would like to use 16bit float arrays. According to
> http://www.scipy.org/Tentative_NumPy_Tutorial, and references to float16
> in
> numpy.core.numerictypes, it appears that this should be possible, but the
> following doesnt work:
> a=arange(10, dtype='float16')
> TypeError: data type not understood
> Can anyone offer some advice?

Does he care about speed? I think some graphics cards might support float16,
but any normal implementation in C would reguire software floating point, a
new type, and you couldn't rely on the normal operators. It might be doable
in C++ with operator overloading and templates, but doing it in C would be a
real hassle.

> Thanks,
> Darren

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://projects.scipy.org/pipermail/numpy-discussion/attachments/20080107/1fe1a2b4/attachment.html 

More information about the Numpy-discussion mailing list