[clang] [llvm] [AMDGPU] Add `wave_id` and `wave_shuffle` Clang builtins. (PR #179492)

[via cfe-commits]

================
@@ -449,6 +449,10 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
     llvm::Function *F = CGM.getIntrinsic(IID, {Value->getType()});
     return Builder.CreateCall(F, {Value, Strategy});
   }
+  case AMDGPU::BI__builtin_amdgcn_wave_shuffle:
+    // TODO: can we unify this with wave_reduce?
----------------
easyonaadit wrote:

I didn't really understand this comment, what idea did you have to unify wave_reduce and shuffle?

https://github.com/llvm/llvm-project/pull/179492