[llvm] [LoopVectorize] Add cost of generating tail-folding mask to the loop (PR #130565)

[David Sherwood via llvm-commits]

================
@@ -743,6 +743,22 @@ InstructionCost VPInstruction::computeCost(ElementCount VF,
     return Ctx.TTI.getArithmeticReductionCost(
         Instruction::Or, cast<VectorType>(VecTy), std::nullopt, Ctx.CostKind);
   }
+  case VPInstruction::ActiveLaneMask: {
+    Type *Arg0Ty = Ctx.Types.inferScalarType(getOperand(0));
+    Type *Arg1Ty = Ctx.Types.inferScalarType(getOperand(1));
+    Type *RetTy = toVectorTy(Ctx.Types.inferScalarType(this), VF);
----------------
david-arm wrote:

Yep, you're right. Done!

https://github.com/llvm/llvm-project/pull/130565