[clang] [llvm] [SPIRV] GPU intrinsics (PR #131190)

[Joseph Huber via llvm-commits]

================
@@ -4770,6 +4770,35 @@ def GetDeviceSideMangledName : LangBuiltin<"CUDA_LANG"> {
   let Prototype = "char const*(...)";
 }
 
+// GPU intrinsics
+class GPUBuiltin<string prototype> : Builtin {
----------------
jhuber6 wrote:

We need a way to make these only emitted on 'gpu' compilations.

https://github.com/llvm/llvm-project/pull/131190