Elena Demikhovsky 3a880de6e6 AVX-512: Added more intrinsics for convert and min/max. ... Removed vzeroupper from AVX-512 mode - our optimization gude does not recommend to insert vzeroupper at all. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@198557 91177308-0d34-0410-b5e6-96231b3b80d8		2014-01-05 10:46:09 +00:00
..
AArch64	For AArch64 Neon, simplify scalar dup by lane0 for fp.	2013-12-30 02:44:35 +00:00
ARM	Make the ARM ABI selectable via SubtargetFeature.	2014-01-02 13:40:08 +00:00
CPP	Begin adding docs and IR-level support for the inalloca attribute	2013-12-19 02:14:12 +00:00
Generic	Attempt to fix buildbots by XFAILing some architectures.	2014-01-05 03:10:56 +00:00
Hexagon
Inputs
Mips	[Mips] Does not take in account 'use-soft-float' attribute's value when	2013-12-25 17:00:27 +00:00
MSP430
NVPTX	[NVPTX] Fix off-by-one error when creating the VT list for an SDNode	2013-12-05 12:58:00 +00:00
PowerPC	Implement initial-exec TLS for PPC32.	2013-12-20 18:08:54 +00:00
R600	R600: Allow ftrunc	2013-12-20 05:11:55 +00:00
SPARC	[SparcV9]: Implement RETURNADDR and FRAMEADDR lowering in SPARC64.	2014-01-04 07:17:21 +00:00
SystemZ	[SystemZ] Use interlocked-access 1 instructions for CodeGen	2013-12-24 15:18:04 +00:00
Thumb	Correctly handle the degenerated triple "thumb".	2013-12-18 21:29:44 +00:00
Thumb2	Enabling thumb2 mode used to force support for armv6t2. Replace this	2013-12-13 11:16:00 +00:00
X86	AVX-512: Added more intrinsics for convert and min/max.	2014-01-05 10:46:09 +00:00
XCore	XCore target: Make handling of large frames not dependent upon an FP.	2013-12-02 11:05:28 +00:00