Chandler Carruth 46d3e580ed [x86] When splitting 256-bit vectors into 128-bit vectors, don't extract ... subvectors from buildvectors. That doesn't really make any sense and it breaks all of the down-stream matching of buildvectors to cleverly lower shuffles. With this, we now get the shift-based lowering of 256-bit vector shuffles with AVX1 when we split them into 128-bit vectors. We also do much better on the zero-extension patterns, although there remains quite a bit of room for improvement here. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@229299 91177308-0d34-0410-b5e6-96231b3b80d8		2015-02-15 10:12:02 +00:00
..
Analysis
Assembler	AsmWriter/Bitcode: MDImportedEntity	2015-02-13 01:46:02 +00:00
Bindings
Bitcode
BugPoint
CodeGen	[x86] When splitting 256-bit vectors into 128-bit vectors, don't extract	2015-02-15 10:12:02 +00:00
DebugInfo
ExecutionEngine
Feature
FileCheck
Instrumentation
Integer
JitListener
Linker	Add run line that was missing in r228999.	2015-02-13 16:00:03 +00:00
LTO
MC	[X86] Add assembly parser support for mnemonic aliases for AVX-512 vpcmp instructions.	2015-02-15 07:13:48 +00:00
Object
Other
SymbolRewriter
TableGen
tools	gold-plugin: fix test to allow default visibility on local symbols	2015-02-15 09:32:30 +00:00
Transforms	FileCheck-ize a test to make it easier to migrate to typeless pointers	2015-02-15 04:14:00 +00:00
Unit
Verifier
YAMLParser
.clang-format
CMakeLists.txt	Back out two accidental changes that snuck in with r229245. Sorry these	2015-02-14 09:05:58 +00:00
lit.cfg	[gold] Consolidate the gold plugin options and actually search for	2015-02-14 09:43:57 +00:00
lit.site.cfg.in	[gold] Consolidate the gold plugin options and actually search for	2015-02-14 09:43:57 +00:00
Makefile	[gold] Consolidate the gold plugin options and actually search for	2015-02-14 09:43:57 +00:00
Makefile.tests
TestRunner.sh