Nadav Rotem 7431211214 On Sandybridge loading unaligned 256bits using two XMM loads (vmovups and vinsertf128) is faster than using a single vmovups instruction. ... llvm-svn: 172868		2013-01-18 23:10:30 +00:00
..
ARM	Simplify writing floating types to assembly.	2013-01-11 10:36:13 +00:00
CPP	test commit	2012-07-18 17:53:05 +00:00
Generic	For inline asm:	2013-01-11 18:12:39 +00:00
Hexagon	Add indexed load/store instructions for offset validation check.	2013-01-17 18:42:37 +00:00
MBlaze	Continue cleanup of LIT, getting rid of the remaining artifacts from dejagnu	2012-03-25 09:02:19 +00:00
MSP430	Add support for varargs functions for msp430.	2012-11-21 17:28:27 +00:00
Mips	[mips] MipsTargetLowering::getSetCCResultType should return a vector type if	2013-01-04 20:06:01 +00:00
NVPTX	[NVPTX] Fix crash with unnamed struct arguments	2012-12-05 20:50:28 +00:00
PowerPC	Restore reverted test case, this time with REQUIRES: asserts	2013-01-17 19:46:51 +00:00
R600	DAGCombiner: Avoid generating illegal vector INT_TO_FP nodes	2013-01-02 22:13:01 +00:00
SI	Add R600 backend	2012-12-11 21:25:42 +00:00
SPARC	Use TargetTransformInfo to control switch-to-lookup table transformation	2012-10-30 11:23:25 +00:00
Thumb	Use the 'count' attribute to calculate the upper bound of an array.	2012-12-04 21:34:03 +00:00
Thumb2	On some ARM cpus, flags setting movs with shifter operand, i.e. lsl, lsr, asr,	2012-12-20 19:59:30 +00:00
X86	On Sandybridge loading unaligned 256bits using two XMM loads (vmovups and vinsertf128) is faster than using a single vmovups instruction.	2013-01-18 23:10:30 +00:00
XCore	Fix handling of aliases to functions.	2012-11-16 21:12:38 +00:00