[llvm] [VPlan] Implement VPExtendedReduction, VPMulAccumulateReductionRecipe and corresponding vplan transformations. (PR #137746)

[Elvis Wang via llvm-commits]

================
@@ -2474,6 +2544,181 @@ class VPReductionEVLRecipe : public VPReductionRecipe {
   }
 };
 
+/// A recipe to represent inloop extended reduction operations, performing a
+/// reduction on a extended vector operand into a scalar value, and adding the
+/// result to a chain. This recipe is abstract and needs to be lowered to
+/// concrete recipes before codegen. The operands are {ChainOp, VecOp,
+/// [Condition]}.
+class VPExtendedReductionRecipe : public VPReductionRecipe {
+  /// Opcode of the extend recipe will be lowered to.
+  Instruction::CastOps ExtOp;
+
+  Type *ResultTy;
+
+  /// For cloning VPExtendedReductionRecipe.
+  VPExtendedReductionRecipe(VPExtendedReductionRecipe *ExtRed)
+      : VPReductionRecipe(
+            VPDef::VPExtendedReductionSC, ExtRed->getRecurrenceKind(),
+            {ExtRed->getChainOp(), ExtRed->getVecOp()}, ExtRed->getCondOp(),
+            ExtRed->isOrdered(), ExtRed->getDebugLoc()),
+        ExtOp(ExtRed->getExtOpcode()), ResultTy(ExtRed->getResultType()) {
+    transferFlags(*ExtRed);
+  }
+
+public:
+  VPExtendedReductionRecipe(VPReductionRecipe *R, VPWidenCastRecipe *Ext)
+      : VPReductionRecipe(VPDef::VPExtendedReductionSC, R->getRecurrenceKind(),
+                          {R->getChainOp(), Ext->getOperand(0)}, R->getCondOp(),
+                          R->isOrdered(), Ext->getDebugLoc()),
+        ExtOp(Ext->getOpcode()), ResultTy(Ext->getResultType()) {
+    assert((ExtOp == Instruction::CastOps::ZExt ||
+            ExtOp == Instruction::CastOps::SExt) &&
+           "VPExtendedReductionRecipe only support zext and sext.");
+
+    // Not all WidenCastRecipes contain nneg flag. Need to transfer flags from
+    // the original recipe to prevent setting wrong flags.
+    transferFlags(*Ext);
+    setUnderlyingValue(R->getUnderlyingValue());
+  }
+
+  ~VPExtendedReductionRecipe() override = default;
+
+  VPExtendedReductionRecipe *clone() override {
+    return new VPExtendedReductionRecipe(this);
+  }
+
+  VP_CLASSOF_IMPL(VPDef::VPExtendedReductionSC);
+
+  void execute(VPTransformState &State) override {
+    llvm_unreachable("VPExtendedReductionRecipe should be transform to "
+                     "VPExtendedRecipe + VPReductionRecipe before execution.");
+  };
+
+#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
+  /// Print the recipe.
+  void print(raw_ostream &O, const Twine &Indent,
+             VPSlotTracker &SlotTracker) const override;
+#endif
+
+  /// The scalar type after extending.
+  Type *getResultType() const { return ResultTy; }
+
+  /// Is the extend ZExt?
+  bool isZExt() const { return getExtOpcode() == Instruction::ZExt; }
+
+  /// The opcode of extend recipe.
+  Instruction::CastOps getExtOpcode() const { return ExtOp; }
+};
+
+/// A recipe to represent inloop MulAccumulateReduction operations, performing a
+/// reduction.add on the result of vector operands (might be extended)
+/// multiplication into a scalar value, and adding the result to a chain. This
+/// recipe is abstract and needs to be lowered to concrete recipes before
+/// codegen. The operands are {ChainOp, VecOp1, VecOp2, [Condition]}.
+class VPMulAccumulateReductionRecipe : public VPReductionRecipe {
+  /// Opcode of the extend recipe.
+  Instruction::CastOps ExtOp;
+
+  /// Non-neg flag of the extend recipe.
+  bool IsNonNeg = false;
+
+  Type *ResultTy;
----------------
ElvisWang123 wrote:

Updated, thanks!

https://github.com/llvm/llvm-project/pull/137746