[PATCH] D127710: [SelectionDAG] Enable WidenVecOp_VECREDUCE_SEQ for scalable vector

[WangLian via Phabricator via llvm-commits]

Jimerlife added inline comments.


================
Comment at: llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp:6152
+  if (WideVT.isScalableVector()) {
+    unsigned GCD = greatestCommonDivisor(OrigElts, WideElts);
+    EVT SplatVT = EVT::getVectorVT(*DAG.getContext(), ElemVT,
----------------
craig.topper wrote:
> sdesmalen wrote:
> > I may be missing something here, but I'm not sure I understand the need for a `GCD` or for a loop that generates `WideVT.getVectorMinNumElements()`  `INSERT_SUBVECTOR`s. Should this code not just insert `VecOp` into a `splat(NeutralElem)` of type `WideVT` using INSERT_SUBVECTOR?
> > 
> > i.e.
> > 
> >    vecreduce_seq(<vscale x 10 x half> op)
> >        <=>
> >    vecreduce_seq(
> >        insert_subvector(op, <vscale x 16 x half> splat(%neutral.elem), /*idx=*/0))
> > 
> > where `<vscale x 10 x half>` is `OrigVT` and `<vscale x 16 x half>` is `WideVT`.
> I think you meant `insert_subvector(<vscale x 16 x half> splat(%neutral.elem), op, /*idx=*/0)`. `op` would be the subvector so should be the second argument.
> 
> That would need to go through WidenVecOp_INSERT_SUBVECTOR, but it will fail because `InVec` isn't undef.
If we do like this `vecreduce_seq(insert_subvector(<vscale x 16 x half> splat, vecop, /*idx=*/0))`, that would go through WidenVecOp_INSERT_SUBVECTOR because of `vecop` need to widen. 
But now, WidenVecOp_INSERT_SUBVECTOR only support insert subvector into undefined vector.



Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D127710/new/

https://reviews.llvm.org/D127710