[clang] [llvm] [AArch64] Add 9.7 CVT data processing intrinsics (PR #186807)

[Martin Wehking via cfe-commits]

================

----------------
MartinWehking wrote:

Yes, I've tried to use it, but it threw errors at compile time. The problem is that it doesn't work with the type conversion from int->float, because 
the output needs to be a LLVMSubdivide2VectorType,
which matches the input type:
`
class LLVMSubdivide2VectorType<int num>
  : LLVMMatchType<num, IIT_SUBDIVIDE2_ARG>;
`

https://github.com/llvm/llvm-project/pull/186807