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

[Joel E. Denny via llvm-commits]

================
@@ -238,6 +239,15 @@ void NVPTXTargetMachine::registerPassBuilderCallbacks(PassBuilder &PB) {
         FPM.addPass(NVVMIntrRangePass());
         PM.addPass(createModuleToFunctionPassAdaptor(std::move(FPM)));
       });
+
+  PB.registerFullLinkTimeOptimizationLastEPCallback(
+      [](ModulePassManager &PM, OptimizationLevel Level) {
+        if (KernelInfoEndLTO) {
----------------
jdenny-ornl wrote:

 Done.

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