[llvm] [VectorCombine][RISCV] Convert VPIntrinsics with splat operands to splats (PR #65706)

[Michael Maitland via llvm-commits]

================
@@ -729,6 +730,112 @@ bool VectorCombine::foldBitcastShuf(Instruction &I) {
   return true;
 }
 
+/// VP Intrinsics whose vector operands are both splat values may be simplified
+/// into the scalar version of the operation and the result splatted. This
+/// can lead to scalarization down the line.
+bool VectorCombine::scalarizeVPIntrinsic(VPIntrinsic &VPI) {
+  Value *Op0 = VPI.getArgOperand(0);
+  Value *Op1 = VPI.getArgOperand(1);
+
+  if (!isSplatValue(Op0) || !isSplatValue(Op1))
+    return false;
+
+  // For the binary VP intrinsics supported here, the result on disabled lanes
+  // is a poison value. For now, only do this simplification if all lanes
+  // are active.
+  // TODO: Relax the condition that all lanes are active by using insertelement
+  // on inactive lanes.
+  auto IsAllTrueMask = [](Value *MaskVal) {
+    if (Value *SplattedVal = getSplatValue(MaskVal))
+      if (auto *ConstValue = dyn_cast<Constant>(SplattedVal))
+        return ConstValue->isAllOnesValue();
+    return false;
+  };
+  if (!IsAllTrueMask(VPI.getArgOperand(2)))
+    return false;
+
+  // Check to make sure we support scalarization of the intrinsic
+  Intrinsic::ID IntrID = VPI.getIntrinsicID();
+  if (!VPBinOpIntrinsic::isVPBinOp(IntrID))
+    return false;
+
+  // Calculate cost of splatting both operands into vectors and the vector
+  // intrinsic
+  VectorType *VecTy = cast<VectorType>(VPI.getType());
+  TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
+  InstructionCost SplatCost =
+      TTI.getVectorInstrCost(Instruction::InsertElement, VecTy, CostKind, 0) +
+      TTI.getShuffleCost(TargetTransformInfo::SK_Broadcast, VecTy);
+
+  // Calculate the cost of the VP Intrinsic
+  SmallVector<Type *, 4> Args;
+  for (Value *V : VPI.args())
+    Args.push_back(V->getType());
+  IntrinsicCostAttributes Attrs(IntrID, VecTy, Args);
+  InstructionCost VectorOpCost = TTI.getIntrinsicInstrCost(Attrs, CostKind);
+  InstructionCost OldCost = 2 * SplatCost + VectorOpCost;
+
+  // Determine scalar opcode
+  std::optional<unsigned> FunctionalOpcode =
+      VPI.getFunctionalOpcode();
+  bool ScalarIsIntr = false;
+  std::optional<Intrinsic::ID> ScalarIntrID;
+  if (!FunctionalOpcode) {
+    ScalarIntrID = VPI.getFunctionalIntrinsicID();
+    if (!ScalarIntrID)
+      return false;
+    ScalarIsIntr = true;
----------------
michaelmaitland wrote:

Updated.

https://github.com/llvm/llvm-project/pull/65706