[llvm] [KernelInfo] Implement new LLVM IR pass for GPU code analysis (PR #102944)

[Matt Arsenault via llvm-commits]

================
@@ -84,20 +147,21 @@ static void remarkCall(OptimizationRemarkEmitter &ORE, const Function &Caller,
     OptimizationRemark R(DEBUG_TYPE, RemarkKind, &Call);
     R << "in ";
     identifyFunction(R, Caller);
-    R << ", " << CallKind;
-    if (const Function *Callee =
-            dyn_cast_or_null<Function>(Call.getCalledOperand())) {
-      R << ", callee is";
-      StringRef Name = Callee->getName();
-      if (auto *SubProgram = Callee->getSubprogram()) {
+    R << ", " << CallKind << ", callee is";
+    Value *Callee = Call.getCalledOperand();
+    std::string Name;
----------------
arsenm wrote:

SmallString?

https://github.com/llvm/llvm-project/pull/102944