[PATCH] D111555: [LoopVectorize] Add strict reduction support for fmuladd intrinsic

[Dave Green via Phabricator via llvm-commits]

dmgreen added inline comments.


================
Comment at: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp:9622
+      }
+      VPReductionRecipe *RedRecipe =
+          new VPReductionRecipe(&RdxDesc, R, ChainOp, VecOps, CondOp, TTI);
----------------
RosieSumpter wrote:
> fhahn wrote:
> > dmgreen wrote:
> > > Would it be possible to create a FMul VPInstruction and a VPReductionRecipe? That way the VPlan better represents the final instructions.
> > +1, that should hopefully help to remove some of the special handling for the `FMulAdd` from codegen.
> Hi @dmgreen, thanks for the suggestion. Would you (or @fhahn) mind elaborating a bit on what you would expect this to look like? I see the point about wanting the FMul instruction to be present in the VPlan, but having spoken to @david-arm about it it seems this might mean the VPReductionRecipe having two underlying instructions - is this what you would expect? Any pointers you have would be very useful!
I think there would be two VPRecipes, a VPReductionRecipe and a VPInstruction representing the fmul. That way the VPReductionRecipe is not trying to represent both, and it should remove some of the extra complexity from VPReductionRecipe because it won't need multiple vector inputs. The fmul VPInstruction creates the final fmul instruction, which will have the two inputs.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D111555/new/

https://reviews.llvm.org/D111555