PATCH: Use NEON fused multiply-add instructions

Mark Mitchell mark@codesourcery.com
Thu May 21 17:37:00 GMT 2009


Richard Earnshaw wrote:

> Doesn't the cortex-a8 scheduler need to know how to handle those
> amazingly long neon_type attributes?

Isn't that already handled in cortex-a8-neon.md?  I didn't check all the
alternatives, but at least several of them are.

Thanks,

-- 
Mark Mitchell
CodeSourcery
mark@codesourcery.com
(650) 331-3385 x713



More information about the Gcc-patches mailing list