[PATCH] D127710: [SelectionDAG] Make WidenVecOp_VECREDUCE_SEQ enbale for scalable vector

[WangLian via Phabricator via llvm-commits]

Jimerlife created this revision.
Jimerlife added reviewers: craig.topper, frasercrmck, sdesmalen, benshi001.
Jimerlife added a project: LLVM.
Herald added subscribers: luke957, StephenFan, ecnelises, luismarques, apazos, sameer.abuasal, s.egerton, Jim, jocewei, PkmX, the_o, brucehoult, MartinMosbeck, rogfer01, edward-jones, zzheng, jrtc27, niosHD, sabuasal, simoncook, johnrusso, rbar, asb, hiraditya.
Herald added a project: All.
Jimerlife requested review of this revision.
Herald added subscribers: llvm-commits, alextsao1999, pcwang-thead, jacquesguan, MaskRay.

Make WidenVecOp_VECREDUCE_SEQ enbale for scalable vector by inserting some splated neutral vectors.
e.g.
when widen <vscale x 10 x half> to <vscale x 16 x half> in index (10, 12, 14) inserted nxv2f16:splat<neutral element>


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D127710

Files:
  llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
  llvm/test/CodeGen/RISCV/rvv/vreductions-fp-sdnode.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D127710.436631.patch
Type: text/x-patch
Size: 6262 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220614/42a05471/attachment.bin>