[ARM] Add instruction selection patterns for vmin/vmax
authorSilviu Baranga <silviu.baranga@arm.com>
Wed, 19 Aug 2015 14:11:27 +0000 (14:11 +0000)
committerSilviu Baranga <silviu.baranga@arm.com>
Wed, 19 Aug 2015 14:11:27 +0000 (14:11 +0000)
commit5a1af3657c51ec2b5d2a71b3dd877acc4a4d60aa
treeed9f6a2265b1f1a7a1525b63de8c4268fa2d7220
parentba54a70bf36c446d5eefbbd4e1cd615b19423743
[ARM] Add instruction selection patterns for vmin/vmax

Summary:
The mid-end was generating vector smin/smax/umin/umax nodes, but
we were using vbsl to generatate the code. This adds the vmin/vmax
patterns and a test to check that we are now generating vmin/vmax
instructions.

Reviewers: rengolin, jmolloy

Subscribers: aemerson, rengolin, llvm-commits

Differential Revision: http://reviews.llvm.org/D12105

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@245439 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/ARM/ARMISelLowering.cpp
lib/Target/ARM/ARMInstrNEON.td
test/CodeGen/ARM/minmax.ll [new file with mode: 0644]
test/CodeGen/ARM/vselect_imax.ll