projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 90622a1) | patch
[InstCombine] Move SSE2/AVX2 arithmetic vector shift folding to instcombiner
authorSimon Pilgrim <llvm-dev@redking.me.uk>
Mon, 10 Aug 2015 20:21:15 +0000 (20:21 +0000)
committerSimon Pilgrim <llvm-dev@redking.me.uk>
Mon, 10 Aug 2015 20:21:15 +0000 (20:21 +0000)
commitac77529540b03ac974fc203e668747b2d27374ec
tree5235faeed1b503f0863818173c22dd8a4b33876dtree | snapshot
parent90622a1bc989e5bcb05a5d1fcf9c36fb14a2bbfbcommit | diff
[InstCombine] Move SSE2/AVX2 arithmetic vector shift folding to instcombiner

As discussed in D11760, this patch moves the (V)PSRA(WD) arithmetic shift-by-constant folding to InstCombine to match the logical shift implementations.

Differential Revision: http://reviews.llvm.org/D11886

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@244495 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/X86/X86ISelLowering.cpp diff | blob | history
lib/Transforms/InstCombine/InstCombineCalls.cpp diff | blob | history
test/CodeGen/X86/combine-avx2-intrinsics.ll diff | blob | history
test/CodeGen/X86/combine-sse2-intrinsics.ll [deleted file] blob | history
test/Transforms/InstCombine/x86-vector-shifts.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors