[FFmpeg-devel] [PATCH 1/5] x264asm: extend SBUTTERFLY to support SSE1

[Christophe Gisquet]

> So maybe this should be benchmarked to ensure it has no negative
> effects, SBUTTERFLY is used alot

I thought about it but a very small reorder buffer for a out-of-order CPU
should help. But agreed that's wishful thinking.

The other solution is probably to have 2 paths depending on %ifidn %2, %3