Loop Vectorize: optimize the vectorization of trunc(induction_var). The truncation...
authorNadav Rotem <nrotem@apple.com>
Tue, 11 Dec 2012 18:58:10 +0000 (18:58 +0000)
committerNadav Rotem <nrotem@apple.com>
Tue, 11 Dec 2012 18:58:10 +0000 (18:58 +0000)
commite266efb70bfdd0c546a83455ce54372360712545
treeade8ca80438c78ffa6e0c9cda5088aaacd630b52
parentc2e3d5cb2980b06fd51b8f535561fe2ecd2c8a55
Loop Vectorize: optimize the vectorization of trunc(induction_var). The truncation is now done on scalars.

llvm-svn: 169904
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
llvm/test/Transforms/LoopVectorize/cast-induction.ll [new file with mode: 0644]
llvm/test/Transforms/LoopVectorize/cpp-new-array.ll
llvm/test/Transforms/LoopVectorize/gcc-examples.ll
llvm/test/Transforms/LoopVectorize/induction_plus.ll