Yi Jiang e1b34bf1fe In this patch we are trying to do two things: ...

1) If the width of vectorization list candidate is bigger than vector reg width, we will break it down to fit the vector reg.
2) We do not vectorize the width which is not power of two.

The performance result shows it will help some spec benchmarks. mesa improved 6.97% and ammp improved 1.54%. 

llvm-svn: 189830

2013-09-03 17:26:04 +00:00

..

Hello

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

InstCombine

InstCombine: Check for zero shift amounts before subtracting one causing integer overflow.

2013-08-30 14:35:35 +00:00

Instrumentation

[msan] Fix handling of select with struct arguments.

2013-09-03 13:05:29 +00:00

IPO

Compulsive reformatting.

2013-08-30 21:07:33 +00:00

ObjCARC

[objc-arc] Track if we encountered an additive overflow while computing {TopDown,BottomUp}PathCounts and do nothing if it occurred.

2013-08-09 23:22:27 +00:00

Scalar

Revert: r189565 - Add getUnrollingPreferences to TTI

2013-08-29 03:33:15 +00:00

Utils

SimplifyLibCalls: When emitting an overloaded fp function check that it's available.

2013-08-31 18:19:35 +00:00

Vectorize

In this patch we are trying to do two things:

2013-09-03 17:26:04 +00:00

CMakeLists.txt

Extracted ObjCARC.cpp into its own library libLLVMObjCARCOpts in preparation for refactoring the ARC Optimizer.

2013-01-28 01:35:51 +00:00

LLVMBuild.txt

Extracted ObjCARC.cpp into its own library libLLVMObjCARCOpts in preparation for refactoring the ARC Optimizer.

2013-01-28 01:35:51 +00:00

Makefile

Extracted ObjCARC.cpp into its own library libLLVMObjCARCOpts in preparation for refactoring the ARC Optimizer.

2013-01-28 01:35:51 +00:00