Benjamin Kramer b8f0d89d05 X86: Promote sitofp <8 x i16> to <8 x i32> when AVX is available. ... A vector sext + sitofp is a lot cheaper than 8 scalar conversions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178448 91177308-0d34-0410-b5e6-96231b3b80d8		2013-03-31 12:49:15 +00:00
..
AArch64	Update PEI's virtual-register-based scavenging to support multiple simultaneous mappings	2013-03-26 18:56:54 +00:00
ARM	Remove the old CodePlacementOpt pass.	2013-03-29 17:14:24 +00:00
CPP
Generic	XFAIL some of the generic CodeGen tests for Hexagon.	2013-03-25 21:04:16 +00:00
Hexagon	Hexagon: Enable SupportDebugInfomation and DwarfInSection flags.	2013-03-28 19:34:49 +00:00
Inputs	Revert "Adding DIImportedModules to DIScopes."	2013-03-28 02:44:59 +00:00
MBlaze
Mips	[mips] Add patterns for DSP indexed load instructions.	2013-03-30 02:14:45 +00:00
MSP430
NVPTX	[NVPTX] Remove support for SM < 2.0. This was never fully supported anyway.	2013-03-30 14:29:30 +00:00
PowerPC	Add the PPC lfiwax instruction	2013-03-31 10:12:51 +00:00
R600	R600/SI: add SETO/SETUO patterns	2013-03-27 15:27:31 +00:00
SI
SPARC
Thumb	Revert "Adding DIImportedModules to DIScopes."	2013-03-28 02:44:59 +00:00
Thumb2
X86	X86: Promote sitofp <8 x i16> to <8 x i32> when AVX is available.	2013-03-31 12:49:15 +00:00
XCore