[gst-devel] Re: liboil questions

[David Schleef]

On Fri, Jan 06, 2006 at 01:59:36PM +0100, Stefan Kost wrote:
> Suggestion:
> oil_scalarmult_xxx(data,factor,num_values);
> Multiply all elements in a vector with one and the same factor. Maybe
> having a variant with and without clipping.

Already there.  Those functions also use strides, so they'll be
replaced sson.

> > All platforms benefit somewhat.  i386 benefits a lot more.
> > 
> Even platforms like arm or sparc?

Yes.

> What about running such a benchmark on all gstreamer build-slaves. The
> slave would fail if a chosen 'optimized' implementation is slower that
> the normal C version. This seems to be part of the unit-tests anyway, right?

Liboil chooses the fastest implementation automatically.  If
'make check' fails, that indicates a bug.  Otherwise, no further
testing is necessary.



dave...

-- 
David Schleef
Big Kitten LLC (http://www.bigkitten.com/) -- data acquisition on Linux