[llvm-commits] [PATCH 3/6] Optimize zext on PPC64

[Hal Finkel]

On Wed, 22 Aug 2012 11:11:31 +0100
Tobias von Koch <tobias.von.koch at gmail.com> wrote:

> Dear all,
> 
> This is part of a series of patches for the PowerPC backend to improve
> support for Freescale processors.
> 
> Please review and commit if this is OK - I don't have commit access.

r162724. Thanks!

 -Hal

> 
> Thanks!
> Tobias
> 
> Description of patch:
> 
> zeroextend IR instruction is lowered to an 'and' node with an
> immediate mask operand, which in turn gets legalised to a sequence of
> ori's & ands. This can be done more efficiently using the rldicl
> instruction.



-- 
Hal Finkel
Postdoctoral Appointee
Leadership Computing Facility
Argonne National Laboratory