Jakob Stoklund Olesen f06f6f50e9 Experimental support for aligned NEON spills. ...

ARM targets with NEON units have access to aligned vector loads and
stores that are potentially faster than unaligned operations.

Add support for spilling the callee-saved NEON registers to an aligned
stack area using 16-byte aligned NEON loads and store.

This feature is off by default, controlled by an -align-neon-spills
command line option.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147211 91177308-0d34-0410-b5e6-96231b3b80d8

2011-12-23 00:36:18 +00:00

..

Analysis

Make the unreachable probability much much heavier. The previous

2011-12-22 09:26:37 +00:00

Archive

Support/FileSystem: Add file_magic and move a vew clients over to it.

2011-12-13 23:17:12 +00:00

AsmParser

Removes unused field TheError from LLLexer.

2011-12-21 10:02:45 +00:00

Bitcode

The powers that be have decided that LLVM IR should now support 16-bit

2011-12-17 00:04:22 +00:00

CodeGen

drop unneeded config.h includes

2011-12-22 23:04:07 +00:00

DebugInfo

Unweaken vtables as per http://llvm.org/docs/CodingStandards.html#ll_virtual_anch

2011-12-20 02:50:00 +00:00

ExecutionEngine

Fix up the CMake build for the new files added in r146960, they're

2011-12-20 08:42:11 +00:00

Linker

drop unneeded config.h includes

2011-12-22 23:04:07 +00:00

MC

Move all the dependencies on X86FixupKinds.h to a single method in preparation

2011-12-22 22:21:47 +00:00

Object

Unweaken vtables as per http://llvm.org/docs/CodingStandards.html#ll_virtual_anch

2011-12-20 02:50:00 +00:00

Support

drop unneeded config.h includes

2011-12-22 23:04:07 +00:00

TableGen

TableGen: add a comment

2011-12-22 23:16:09 +00:00

Target

Experimental support for aligned NEON spills.

2011-12-23 00:36:18 +00:00

Transforms

Add the actual code for r147175.

2011-12-22 21:10:46 +00:00

VMCore

Give string constants generated by IRBuilder private linkage.

2011-12-22 14:22:14 +00:00

CMakeLists.txt

…

LLVMBuild.txt

…

Makefile

…