Nadav Rotem 86e848c849 SLPVectorizer: start constructing chains at stores that are not power of two. ...

The type <3 x i8> is a common in graphics and we want to be able to vectorize it.

This changes accelerates bullet by 12% and 471_omnetpp by 5%.

llvm-svn: 184317

2013-06-19 15:57:29 +00:00

..

BBVectorize.cpp

BBVectorize: Fixup debugging statements

2013-03-10 20:57:42 +00:00

CMakeLists.txt

Add support for bottom-up SLP vectorization infrastructure.

2013-04-09 19:44:35 +00:00

LLVMBuild.txt

…

LoopVectorize.cpp

Fix for a regression caused by the LoopVectorizer when

2013-06-17 18:49:06 +00:00

Makefile

…

SLPVectorizer.cpp

Scan the successor blocks and use the PHI nodes as a hint for possible chain roots.

2013-06-18 15:58:05 +00:00

Vectorize.cpp

This patch breaks up Wrap.h so that it does not have to include all of

2013-05-01 20:59:00 +00:00

VecUtils.cpp

SLPVectorizer: start constructing chains at stores that are not power of two.

2013-06-19 15:57:29 +00:00

VecUtils.h

Document the return value and fix a typo.

2013-06-19 05:47:33 +00:00