Filipe Cabecinhas cd9f6b870e Optimize some special cases for SSE4a insertqi ... Summary: Since the upper 64 bits of the destination register are undefined when performing this operation, we can substitute it and let the optimizer figure out that only a copy is needed. Also added range merging, if an instruction copies a range that can be merged with a previous copied range. Added test cases for both optimizations. Reviewers: grosbach, nadav CC: llvm-commits Differential Revision: http://reviews.llvm.org/D3357 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207055 91177308-0d34-0410-b5e6-96231b3b80d8		2014-04-24 00:38:14 +00:00
..
Analysis	[LCG] Normalize the post-order SCC iterator to just iterate over the SCC	2014-04-23 23:51:07 +00:00
AsmParser
Bitcode
CodeGen	And actually use the DwarfDebug::AccelNames to emit the names.	2014-04-23 23:46:25 +00:00
DebugInfo
ExecutionEngine	[Modules] Fix potential ODR violations by sinking the DEBUG_TYPE	2014-04-22 03:04:17 +00:00
IR	llvm-cov: Add support for gcov's --long-file-names option	2014-04-23 21:44:55 +00:00
IRReader
LineEditor
Linker
LTO	Create MCTargetOptions.	2014-04-23 11:16:03 +00:00
MC	MC: honour IMAGE_SCN_CNT_INITIALIZED_DATA	2014-04-23 21:29:34 +00:00
Object	[yaml2obj][ELF] Remove unnecessary space between namespace name and	2014-04-23 17:30:29 +00:00
Option
ProfileData	ProfileData: Avoid unnecessary copies of CounterData	2014-04-23 18:50:16 +00:00
Support	cl::ParseCommandLineOptions(): Use StringRef to receive sys::path::filename() instead of std::string.	2014-04-23 14:51:23 +00:00
TableGen
Target	[ARM64] Fix the information we give to the peephole optimizer for comparison.	2014-04-23 20:43:38 +00:00
Transforms	Optimize some special cases for SSE4a insertqi	2014-04-24 00:38:14 +00:00
CMakeLists.txt
LLVMBuild.txt
Makefile