[PATCH] D70822: [ARM] Add some VCMP folding and canonicalisation

[Dave Green via Phabricator via llvm-commits]

dmgreen created this revision.
dmgreen added reviewers: samparker, simon_tatham, SjoerdMeijer, ostannard, t.p.northover.
Herald added subscribers: hiraditya, kristof.beyls.
Herald added a project: LLVM.

The VCMP instructions in MVE can accept a register or ZR, but only as the right hand operator. Most of the time this will already be correct because the icmp will have been canonicalised that way already. There are some cases in the lowering of float conditions that this will not apply to though. This code should fix up those cases.


https://reviews.llvm.org/D70822

Files:
  llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp
  llvm/lib/Target/ARM/ARMISelLowering.cpp
  llvm/lib/Target/ARM/Utils/ARMBaseInfo.h
  llvm/test/CodeGen/Thumb2/mve-vcmpfz.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D70822.231423.patch
Type: text/x-patch
Size: 12128 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191128/11dc0943/attachment.bin>