[AMDGPU] Add an option to run AMDGPUAttributorPass in full LTO

Currently `AMDGPUAttributorPass` is registered in default optimizer pipeline.
This will allow the pass to run in default pipeline as well as at thinLTO post
link stage. However, it will not run in full LTO post link stage. This patch
adds an option to run it in full LTO. It is set to false by default.

Author: shiltian

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

@@ -301,6 +301,11 @@ static cl::opt<bool> EnableSIModeRegisterPass(
   cl::init(true),
   cl::Hidden);
 
+static cl::opt<bool> EnableAMDGPUAttributorInFullLTO(
+    "amdgpu-attributor-enable-full-lto",
+    cl::desc("Enable AMDGPUAttributorPass in full LTO post link stage"),
+    cl::init(false), cl::Hidden);
+
 // Enable GFX11.5+ s_singleuse_vdst insertion
 static cl::opt<bool>
     EnableInsertSingleUseVDST("amdgpu-enable-single-use-vdst",
@@ -734,21 +739,15 @@ void AMDGPUTargetMachine::registerPassBuilderCallbacks(PassBuilder &PB) {
         PM.addPass(createCGSCCToFunctionPassAdaptor(std::move(FPM)));
       });
 
-  // FIXME: Why is AMDGPUAttributor not in CGSCC?
-  PB.registerOptimizerLastEPCallback(
-      [this](ModulePassManager &MPM, OptimizationLevel Level) {
-        if (Level != OptimizationLevel::O0) {
-          MPM.addPass(AMDGPUAttributorPass(*this));
-        }
-      });
-
   PB.registerFullLinkTimeOptimizationLastEPCallback(
       [this](ModulePassManager &PM, OptimizationLevel Level) {
         // We want to support the -lto-partitions=N option as "best effort".
         // For that, we need to lower LDS earlier in the pipeline before the
         // module is partitioned for codegen.
         if (EnableLowerModuleLDS)
           PM.addPass(AMDGPULowerModuleLDSPass(*this));
+
+        PM.addPass(AMDGPUAttributorPass(*this));
       });
 
   PB.registerRegClassFilterParsingCallback(