[FFmpeg-devel] [PATCH] ff_scalarproduct_float_sse

[Reimar Döffinger]

On Wed, Jan 20, 2010 at 02:03:31PM -0800, Jason Garrett-Glaser wrote:
> > 1. i do want to be able to try to avoid the call overhead for some functions
> > that are called often (jasons idea of interleaving block decode with idct is
> > an example)
> 
> IMO x264's solution is fine here: things which are actually inlined
> should use inline asm, and things which aren't should use yasm.

That assumes that you will never ever want to change your decision,
at least that's how I understood Michael's point.