[AMDGPU] Respect existing glue when lowering convergence tokens

Author: ssahasra

llvm/lib/Target/AMDGPU/SIISelLowering.cpp

@@ -3859,20 +3859,19 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
   assert(Mask && "Missing call preserved mask for calling convention");
   Ops.push_back(DAG.getRegisterMask(Mask));
 
-  if (InGlue.getNode())
-    Ops.push_back(InGlue);
-
-  // NOTE: This potentially results in *two* glue operands, and the wrong one
-  // might possibly show up where the other was intended. In particular,
-  // Emitter::EmitMachineNode() expects only the glued convergence token if it
-  // exists. Similarly, the selection of the call expects to match only the
-  // InGlue operand if it exists.
   if (SDValue Token = CLI.ConvergenceControlToken) {
-    Ops.push_back(SDValue(DAG.getMachineNode(TargetOpcode::CONVERGENCECTRL_GLUE,
-                                             DL, MVT::Glue, Token),
-                          0));
+    SmallVector<SDValue, 2> GlueOps;
+    GlueOps.push_back(Token);
+    if (InGlue.getNode())
+      GlueOps.push_back(InGlue);
+
+    InGlue = SDValue(DAG.getMachineNode(TargetOpcode::CONVERGENCECTRL_GLUE,
+                                       DL, MVT::Glue, GlueOps), 0);
   }
 
+  if (InGlue.getNode())
+    Ops.push_back(InGlue);
+
   SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);
 
   // If we're doing a tall call, use a TC_RETURN here rather than an