[llvm] [AMDGPU] Tail call support for whole wave functions (PR #145860)

[Matt Arsenault via llvm-commits]

================
@@ -7977,13 +7977,18 @@ void SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I,
   }
   case Intrinsic::amdgcn_call_whole_wave: {
     TargetLowering::ArgListTy Args;
+    bool isTailCall = I.isTailCall();
 
     // The first argument is the callee. Skip it when assembling the call args.
     TargetLowering::ArgListEntry Arg;
     for (unsigned Idx = 1; Idx < I.arg_size(); ++Idx) {
       Arg.Node = getValue(I.getArgOperand(Idx));
       Arg.Ty = I.getArgOperand(Idx)->getType();
       Arg.setAttributes(&I, Idx);
+
+      if (Arg.IsSRet && isa<Instruction>(I.getArgOperand(Idx)))
+        isTailCall = false;
+
----------------
arsenm wrote:

Isn't that the whole point of the tail marker?

https://github.com/llvm/llvm-project/pull/145860