[llvm] [AArch64] Add @llvm.experimental.vector.match (PR #101974)

[David Sherwood via llvm-commits]

================
@@ -1352,6 +1352,11 @@ bool TargetTransformInfo::hasActiveVectorLength(unsigned Opcode, Type *DataType,
   return TTIImpl->hasActiveVectorLength(Opcode, DataType, Alignment);
 }
 
+bool TargetTransformInfo::hasVectorMatch(VectorType *VT,
+                                         unsigned SegSize) const {
----------------
david-arm wrote:

I think normally when the target does not have efficient support for an intrinsic we provide a generic lowering mechanism, which will be slow but functionally correct. Have you taken this approach because you believe it's simply not worth providing generic lowering due to the cost or because there is no easy way to lower this using generic ISD nodes?

https://github.com/llvm/llvm-project/pull/101974