llvm-project/llvm/lib
Silviu Baranga 755ec0e027 [AArch64] Turn on by default interleaved access vectorization
Summary:
This change turns on by default interleaved access vectorization
for AArch64.

We also clean up some tests which were spedifically enabling this
behaviour.

Reviewers: rengolin

Subscribers: aemerson, llvm-commits, rengolin

Differential Revision: http://reviews.llvm.org/D12149

llvm-svn: 246542
2015-09-01 11:26:46 +00:00
..
Analysis [BasicAA] Fix the handling of sext and zext in the analysis of GEPs. 2015-08-31 22:32:47 +00:00
AsmParser Fix bug in method LLLexer::FP80HexToIntPair 2015-08-31 21:36:14 +00:00
Bitcode [BitcodeReader] Ensure we can read constant vector selects with an i1 condition 2015-08-31 18:00:30 +00:00
CodeGen [ARM][AArch64] Turn on by default interleaved access lowering 2015-09-01 11:12:35 +00:00
DebugInfo
ExecutionEngine [SectionMemoryManager] Use range-based for loops. No functional change intended. 2015-08-31 13:39:14 +00:00
Fuzzer
IR Rollback of commit "Repress sanitization on User dtor." 2015-08-31 21:06:08 +00:00
IRReader
LTO Fix typo. 2015-09-01 10:13:49 +00:00
LibDriver
LineEditor
Linker
MC [MC/AsmParser] Avoid setting MCSymbol.IsUsed in some cases 2015-08-31 17:44:53 +00:00
Object
Option
Passes
ProfileData
Support
TableGen
Target [AArch64] Turn on by default interleaved access vectorization 2015-09-01 11:26:46 +00:00
Transforms Fix Windows build by including raw_ostream.h 2015-08-31 21:19:18 +00:00
CMakeLists.txt
LLVMBuild.txt
Makefile