Revert r211771. It was: "[X86] Improve the selection of SSE3/AVX addsub instructions".
authorAndrea Di Biagio <Andrea_DiBiagio@sn.scee.net>
Wed, 23 Jul 2014 11:20:24 +0000 (11:20 +0000)
committerAndrea Di Biagio <Andrea_DiBiagio@sn.scee.net>
Wed, 23 Jul 2014 11:20:24 +0000 (11:20 +0000)
commitbf0fb36d7229d2e0d71474e7597201062fb06577
treeffef2a2a860a43a59c26afd42ded5b2840d7b96e
parent5a37cccc7ee4983f8c555711dc82b26fce67cecc
Revert r211771. It was: "[X86] Improve the selection of SSE3/AVX addsub instructions".

This chang fully reverts r211771.
That revision added a canonicalization rule which has the potential to causes a
combine-cycle in the target-independent canonicalizing DAG combine.

The plan is to move the logic that forms target specific addsub nodes as part of
the lowering of shuffles.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213736 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/X86/X86ISelLowering.cpp
test/CodeGen/X86/sse3-avx-addsub.ll