Matt Arsenault 210095c5c9 LoadStoreVectorizer: Split even sized illegal chains properly ... Implement isLegalToVectorizeLoadChain for AMDGPU to avoid producing private address spaces accesses that will need to be split up later. This was doing the wrong thing in the case where the queried chain was an even number of elements. A possible <4 x i32> store was being split into store <2 x i32> store i32 store i32 rather than store <2 x i32> store <2 x i32> when legal. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295933 91177308-0d34-0410-b5e6-96231b3b80d8		2017-02-23 03:58:53 +00:00
..
Coroutines	[Coroutines] Add header guard to header that's missing one.	2017-01-30 16:32:20 +00:00
Hello
InstCombine	AMDGPU: Replace disabled exp inputs with undef	2017-02-23 00:44:03 +00:00
Instrumentation	AddressSanitizer: don't track swifterror memory addresses	2017-02-15 20:43:43 +00:00
IPO	Increases full-unroll threshold.	2017-02-18 03:46:51 +00:00
ObjCARC	[CMake] NFC. Updating CMake dependency specifications	2016-11-17 04:36:50 +00:00
Scalar	PredicateInfo: Support switch statements	2017-02-22 22:20:58 +00:00
Utils	PredicateInfo: Support switch statements	2017-02-22 22:20:58 +00:00
Vectorize	LoadStoreVectorizer: Split even sized illegal chains properly	2017-02-23 03:58:53 +00:00
CMakeLists.txt
LLVMBuild.txt