[FFmpeg-devel] [PATCH 2/2] configure: Use intel math.h header.

Reimar Döffinger Reimar.Doeffinger at gmx.de
Sun May 11 10:24:45 CEST 2014


On 11.05.2014, at 07:42, Matt Oliver <protogonoi at gmail.com> wrote:
> to patch icl to do the same. Adding a -fast-math option would be
> interesting but as it breaks stuff (this being case in point) then your
> right in that its probably not a good idea.

I think in the end nobody could show a significant performance benefit for fast-math anyway.
It also has the nasty property (just like ICL) that output depens on what optimizations the compiler does. E.g. 0*inf is 0 if the compiler sees the constant 0, but it is NaN if it doesn't. That is very non-fun for debugging.
I think the patch is good, and I'd also say the patch to use the other math header can still be interesting, but only if an actual performance benefit can be shown (most likely in some of the less-optimized float audio codecs like on2avc).


More information about the ffmpeg-devel mailing list