[clang] [CUDA][Win32] Add `fma(long double,..)` to math forward declares. (PR #73756)

[Evgeny Mankov via cfe-commits]

================
@@ -70,6 +70,9 @@ __DEVICE__ double floor(double);
 __DEVICE__ float floor(float);
 __DEVICE__ double fma(double, double, double);
 __DEVICE__ float fma(float, float, float);
+#ifdef _MSC_VER
+__DEVICE__ long double fma(long double, long double, long double);
----------------
emankov wrote:

That is it, it is only a compile-time story, and the situation when the successfully compiled code "fails somewhere in ptxas" on runtime would never happen till CUDA implementation of `long double fma` appears, or am I missing something?

https://github.com/llvm/llvm-project/pull/73756