[clang] [llvm] [AMDGPU][clang][CodeGen][opt] Add late-resolved feature identifying predicates (PR #134016)

[Erich Keane via llvm-commits]

================
@@ -15576,6 +15609,38 @@ static bool isOverflowingIntegerType(ASTContext &Ctx, QualType T) {
   return Ctx.getIntWidth(T) >= Ctx.getIntWidth(Ctx.IntTy);
 }
 
+static Expr *ExpandAMDGPUPredicateBI(ASTContext &Ctx, CallExpr *CE) {
+  if (!CE->getBuiltinCallee())
+    return CXXBoolLiteralExpr::Create(Ctx, false, Ctx.BoolTy, CE->getExprLoc());
+
+  if (Ctx.getTargetInfo().getTriple().isSPIRV()) {
+    CE->setType(Ctx.getLogicalOperationType());
+    return CE;
+  }
+
+  bool P = false;
+  auto &TI = Ctx.getTargetInfo();
+
+  if (CE->getDirectCallee()->getName() == "__builtin_amdgcn_processor_is") {
----------------
erichkeane wrote:

This isn't sufficient, you actually have to check that it is the builtin.  If you check just the name it could be a different one, as this doesn't give you the name of namespaces/classes/etc, just the immediate name.

ALSO, `getName` in many cases will assert if this is an operator/other nameless function.

https://github.com/llvm/llvm-project/pull/134016