[llvm] [NVPTX] Add mix precision arith intrinsics (PR #136657)

[Alex MacLean via llvm-commits]

================
@@ -1306,6 +1306,48 @@ let TargetPrefix = "nvvm" in {
       DefaultAttrsIntrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
         [IntrNoMem, IntrSpeculatable, Commutative]>;
 
+  // Mixed-precision add intrinsics for half and bfloat16 to float
----------------
AlexMaclean wrote:

Do we really need these new intrinsics? It seems like just calling `fpext` on the 16-bit operand before adding or multiplying it would be semantically equivalent. An idiom like this is also fairly concise and seems likely to be preserved through general optimizations, while still allowing for things like constant-folding and fma-fusion.

https://github.com/llvm/llvm-project/pull/136657