On Mon, Dec 21, 2009 at 12:28:03PM -0800, Richard Henderson wrote:
> On 12/21/2009 01:13 AM, Laurent Desnogues wrote:
>> The question for the generalized movcond is how useful is it?
>> Which front-ends would need it and would the cost to generate
>> code for it on some (most?) back-ends be amortized?
>
> ... Any front end that has a conditional move instruction?
> Sparcv9, Mips32, Alpha, ARM...
>
> That said, I think the *biggest* gains are to be had because with
^^^^^
This word is the main reason why I am not convinced at all by movcond.
> movcond -- at least on some targets -- we can have one BB per TB, and
> avoid any intermediate spilling of global registers back to memory.
Memory load/stores are far more frequent, and also spill global
registers back to memory.
--
Aurelien Jarno GPG: 1024D/F1BCDB73
aurel...@aurel32.net http://www.aurel32.net
