[PATCH] D87276: [ARM] Recognize "double extend" reduction patterns

[Dave Green via Phabricator via llvm-commits]

dmgreen created this revision.
dmgreen added reviewers: simon_tatham, SjoerdMeijer, samparker, efriedma, samtebbs.
Herald added subscribers: danielkiss, hiraditya, kristof.beyls.
Herald added a project: LLVM.
dmgreen requested review of this revision.

We can sometimes get code that does:

  xe = zext i16 x to i32
  ye = zext i16 y to i32
  m = mul i32 xe, ye
  me = zext i32 m to i64
  r = vecreduce.add(me)

This "double extend" can trip up the reduction identification, but should give identical results.

This extends the pattern matching to handle them.


https://reviews.llvm.org/D87276

Files:
  llvm/lib/Target/ARM/ARMISelLowering.cpp
  llvm/test/CodeGen/Thumb2/mve-vecreduce-mla.ll
  llvm/test/CodeGen/Thumb2/mve-vecreduce-mlapred.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D87276.290444.patch
Type: text/x-patch
Size: 89877 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200908/82a4b6ce/attachment.bin>