Chandler Carruth 9471b89b1d [x86] Run most of the rest of the shuffle combining over non-128-bit ... vectors. This lets us fix the rest of the v16 lowering problems when pshufb is clearly better. We might still be able to improve some of the lowerings by enabling the other combine-based rewriting to fire for non-128-bit vectors, but this at least should remove any regressions from using the fancy v16i16 lowering strategy. llvm-svn: 230753		2015-02-27 12:13:14 +00:00
..
AArch64	Bugfix: SCEVExpander incorrectly marks increment operations as no-wrap	2015-02-25 20:02:59 +00:00
ARM	Use ".arch_extension" ARM directive to support hwdiv on krait	2015-02-26 18:08:41 +00:00
BPF
CPP
Generic
Hexagon
Inputs
Mips	[mips] Account for constant-zero operands in ADDE nodes.	2015-02-27 09:01:39 +00:00
MSP430
NVPTX
PowerPC	[PowerPC] Make LDtocL and friends invariant loads	2015-02-25 21:36:59 +00:00
R600	R600/SI: Remove M0 from DS assembly strings	2015-02-26 17:08:43 +00:00
SPARC
SystemZ
Thumb	Improve handling of stack accesses in Thumb-1	2015-02-25 14:41:06 +00:00
Thumb2
X86	[x86] Run most of the rest of the shuffle combining over non-128-bit	2015-02-27 12:13:14 +00:00
XCore