[llvm] [AArch64][SVE] Add optimisation for SVE intrinsics with no active lanes (PR #73964)

[Mark Harley via llvm-commits]

================
@@ -1523,9 +1540,8 @@ static std::optional<Instruction *> instCombineSVEVectorMul(InstCombiner &IC,
   auto *OpMultiplicand = II.getOperand(1);
   auto *OpMultiplier = II.getOperand(2);
 
-  // Canonicalise a non _u intrinsic only.
   if (II.getIntrinsicID() != IID)
----------------
MarkAHarley wrote:

This check can be moved outside of this function if preferred.

https://github.com/llvm/llvm-project/pull/73964