[PATCH 2/2] ARM cost model: Add vector reverse shuffle costs

[Nadav Rotem]

Both patches LGTM. 

Thanks,
Nadav

On Feb 8, 2013, at 9:42 AM, Arnold Schwaighofer <aschwaighofer at apple.com> wrote:

> A reverse shuffle is lowered to a vrev and possibly a vext instruction (quad
> word). The backend has a deficiency in lowering native v8i16 and v16i8 types.
> They are scalarized to memory. Reflect this in their cost.
> 
> <0002-ARM-cost-model-Add-vector-reverse-shuffle-costs.patch>