[PATCH] D141870: [DAG] Fold Op(vecreduce(a), vecreduce(b)) into vecreduce(Op(a,b))

[Dave Green via Phabricator via llvm-commits]

dmgreen updated this revision to Diff 494826.
dmgreen retitled this revision from "[DAG] Fold fadd(vecreduce(a), vecreduce(b)) into vecreduce(fadd(a,b))" to "[DAG] Fold Op(vecreduce(a), vecreduce(b)) into vecreduce(Op(a,b))".
dmgreen edited the summary of this revision.
dmgreen added a comment.
Herald added subscribers: luke, pcwang-thead, frasercrmck, luismarques, apazos, sameer.abuasal, s.egerton, Jim, jocewei, PkmX, the_o, brucehoult, MartinMosbeck, rogfer01, edward-jones, zzheng, MaskRay, jrtc27, niosHD, sabuasal, simoncook, johnrusso, rbar, asb.

I've update this to now handle all the reduction types, and added tests for various architectures.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D141870/new/

https://reviews.llvm.org/D141870

Files:
  llvm/include/llvm/CodeGen/TargetLowering.h
  llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
  llvm/lib/Target/ARM/ARMISelLowering.h
  llvm/test/CodeGen/AArch64/aarch64-addv.ll
  llvm/test/CodeGen/AArch64/double_reduct.ll
  llvm/test/CodeGen/AArch64/sve-doublereduct.ll
  llvm/test/CodeGen/AArch64/sve-fp-reduce.ll
  llvm/test/CodeGen/AArch64/vecreduce-add.ll
  llvm/test/CodeGen/AArch64/vecreduce-fadd.ll
  llvm/test/CodeGen/RISCV/double_reduct.ll
  llvm/test/CodeGen/Thumb2/mve-doublereduct.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D141870.494826.patch
Type: text/x-patch
Size: 56177 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230204/dc3743b5/attachment.bin>