[clang] [Clang] Support fp16 in libdevice for CUDA 13.3 (PR #174005)

[Yonah Goldberg via cfe-commits]

================
@@ -458,6 +458,196 @@ __DEVICE__ float __nv_y1f(float __a);
 __DEVICE__ float __nv_ynf(int __a, float __b);
 __DEVICE__ double __nv_yn(int __a, double __b);
 
+#if CUDA_VERSION >= 13030
+typedef _Float16 _Float16x2 __attribute__((ext_vector_type(2)));
----------------
YonahGoldberg wrote:

Yeah it will, these declarations accurately reflect the signature of the functions in libdevice.

https://github.com/llvm/llvm-project/pull/174005