Hal Finkel 064551e94c By default, use Early-CSE instead of GVN for vectorization cleanup. ...

As has been suggested by Duncan and others, Early-CSE and GVN should
do similar redundancy elimination, but Early-CSE is much less expensive.
Most of my autovectorization benchmarks show a performance regresion, but
all of these are < 0.1%, and so I think that it is still worth using
the less expensive pass.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154673 91177308-0d34-0410-b5e6-96231b3b80d8

2012-04-13 17:15:33 +00:00

..

ArgumentPromotion.cpp

…

CMakeLists.txt

…

ConstantMerge.cpp

…

DeadArgumentElimination.cpp

…

ExtractGV.cpp

…

FunctionAttrs.cpp

…

GlobalDCE.cpp

…

GlobalOpt.cpp

…

InlineAlways.cpp

Fix a pretty scary bug I introduced into the always inliner with

2012-04-01 10:21:05 +00:00

Inliner.cpp

Add two statistics to help track how we are computing the inline cost.

2012-04-11 10:15:10 +00:00

InlineSimple.cpp

Remove a bunch of empty, dead, and no-op methods from all of these

2012-03-31 12:48:08 +00:00

Internalize.cpp

Code-gen may inject code into the IR before it emits the ASM. The linker

2012-04-13 01:06:27 +00:00

IPConstantPropagation.cpp

…

IPO.cpp

…

LLVMBuild.txt

…

LoopExtractor.cpp

…

Makefile

…

MergeFunctions.cpp

…

PartialInlining.cpp

…

PassManagerBuilder.cpp

By default, use Early-CSE instead of GVN for vectorization cleanup.

2012-04-13 17:15:33 +00:00

PruneEH.cpp

…

StripDeadPrototypes.cpp

…

StripSymbols.cpp

…