[llvm] [LoopVectorizer] Add support for partial reductions (PR #92418)

[Florian Hahn via llvm-commits]

================
@@ -2266,6 +2275,38 @@ class VPReductionPHIRecipe : public VPHeaderPHIRecipe,
   bool isInLoop() const { return IsInLoop; }
 };
 
+/// A recipe for forming partial reductions. In the loop, an accumulator and
+/// vector operand are added together and passed to the next iteration as the
+/// next accumulator. After the loop body, the accumulator is reduced to a
+/// scalar value.
+class VPPartialReductionRecipe : public VPRecipeWithIRFlags {
+  unsigned Opcode;
+  Instruction &Reduction;
+
+public:
+  template <typename IterT>
+  VPPartialReductionRecipe(Instruction &I, iterator_range<IterT> Operands)
+      : VPRecipeWithIRFlags(VPDef::VPPartialReductionSC, Operands, I),
+        Opcode(I.getOpcode()), Reduction(I) {
+    assert(isa<VPReductionPHIRecipe>(getOperand(1)->getDefiningRecipe()) &&
+           "Unexpected operand order for partial reduction recipe");
+  }
+  ~VPPartialReductionRecipe() override = default;
+  VPPartialReductionRecipe *clone() override {
+    auto Ops = operands();
+    return new VPPartialReductionRecipe(Reduction,
+                                        make_range(Ops.begin(), Ops.end()));
+  }
+  VP_CLASSOF_IMPL(VPDef::VPPartialReductionSC)
+  /// Generate the reduction in the loop
+  void execute(VPTransformState &State) override;
----------------
fhahn wrote:

```suggestion

  /// Generate the reduction in the loop
  void execute(VPTransformState &State) override;
  
```

https://github.com/llvm/llvm-project/pull/92418