[NewPM] Fix CGSCCOptimizerLateEPCallbacks place in pipeline

[aeubanks]

Summary

CGSCCOptimizerLateEPCallbacks are supposed to be run before the function
simplification pipeline, like in the legacy PM and as specified in the
comments for registerCGSCCOptimizerLateEPCallback().

[ychen]

LGTM

llvm/lib/Passes/PassBuilder.cpp

PassBuilder::buildInlinerPipeline(OptimizationLevel Level, ThinLTOPhase Phase,
   if (Level == OptimizationLevel::O3)
     MainCGPipeline.addPass(ArgumentPromotionPass());
 
   // Try to perform OpenMP specific optimizations. This is a (quick!) no-op if
   // there are no OpenMP runtime calls present in the module.
   if (Level == OptimizationLevel::O2 || Level == OptimizationLevel::O3)
     MainCGPipeline.addPass(OpenMPOptPass());
 
+  for (auto &C : CGSCCOptimizerLateEPCallbacks)
+    C(MainCGPipeline, Level);
+
   // Lastly, add the core function simplification pipeline nested inside the
   // CGSCC walk.
   MainCGPipeline.addPass(createCGSCCToFunctionPassAdaptor(
       buildFunctionSimplificationPipeline(Level, Phase)));
 
-  for (auto &C : CGSCCOptimizerLateEPCallbacks)
-    C(MainCGPipeline, Level);
-
   return MIWP;
 }
 
 ModulePassManager
 PassBuilder::buildModuleSimplificationPipeline(OptimizationLevel Level,
                                                ThinLTOPhase Phase) {
   ModulePassManager MPM(DebugLogging);
 
ModulePassManager PassBuilder::buildO0DefaultPipeline(OptimizationLevel Level,
 
   if (PTO.MergeFunctions)
     MPM.addPass(MergeFunctionsPass());
 
   if (EnableMatrix)
     MPM.addPass(
         createModuleToFunctionPassAdaptor(LowerMatrixIntrinsicsPass(true)));
 
+  if (!CGSCCOptimizerLateEPCallbacks.empty()) {
+    CGSCCPassManager CGPM(DebugLogging);
+    for (auto &C : CGSCCOptimizerLateEPCallbacks)
+      C(CGPM, Level);
+    if (!CGPM.isEmpty())
+      MPM.addPass(createModuleToPostOrderCGSCCPassAdaptor(std::move(CGPM)));
+  }
   if (!LateLoopOptimizationsEPCallbacks.empty()) {
     LoopPassManager LPM(DebugLogging);
     for (auto &C : LateLoopOptimizationsEPCallbacks)
       C(LPM, Level);
     if (!LPM.isEmpty()) {
       MPM.addPass(createModuleToFunctionPassAdaptor(
           createFunctionToLoopPassAdaptor(std::move(LPM))));
     }
ModulePassManager PassBuilder::buildO0DefaultPipeline(OptimizationLevel Level,
   }
   if (!ScalarOptimizerLateEPCallbacks.empty()) {
     FunctionPassManager FPM(DebugLogging);
     for (auto &C : ScalarOptimizerLateEPCallbacks)
       C(FPM, Level);
     if (!FPM.isEmpty())
       MPM.addPass(createModuleToFunctionPassAdaptor(std::move(FPM)));
   }
-  if (!CGSCCOptimizerLateEPCallbacks.empty()) {
-    CGSCCPassManager CGPM(DebugLogging);
-    for (auto &C : CGSCCOptimizerLateEPCallbacks)
-      C(CGPM, Level);
-    if (!CGPM.isEmpty())
-      MPM.addPass(createModuleToPostOrderCGSCCPassAdaptor(std::move(CGPM)));
-  }
   if (!VectorizerStartEPCallbacks.empty()) {
     FunctionPassManager FPM(DebugLogging);
     for (auto &C : VectorizerStartEPCallbacks)
       C(FPM, Level);
     if (!FPM.isEmpty())
       MPM.addPass(createModuleToFunctionPassAdaptor(std::move(FPM)));
   }
 

llvm/test/Other/new-pm-defaults.ll

 ; CHECK-O-NEXT: Running analysis: ProfileSummaryAnalysis
 ; CHECK-O-NEXT: Running pass: DevirtSCCRepeatedPass
 ; CHECK-O-NEXT: Starting CGSCC pass manager run.
 ; CHECK-O-NEXT: Running pass: InlinerPass
 ; CHECK-O-NEXT: Running pass: PostOrderFunctionAttrsPass
 ; CHECK-O3-NEXT: Running pass: ArgumentPromotionPass
 ; CHECK-O2-NEXT: Running pass: OpenMPOptPass on (foo)
 ; CHECK-O3-NEXT: Running pass: OpenMPOptPass on (foo)
+; CHECK-EP-CGSCC-LATE-NEXT: Running pass: NoOpCGSCCPass
 ; CHECK-O-NEXT: Starting llvm::Function pass manager run.
 ; CHECK-O-NEXT: Running pass: SROA
 ; CHECK-O-NEXT: Running pass: EarlyCSEPass
 ; CHECK-O-NEXT: Running analysis: MemorySSAAnalysis
 ; CHECK-O23SZ-NEXT: Running pass: SpeculativeExecutionPass
 ; CHECK-O23SZ-NEXT: Running pass: JumpThreadingPass
 ; CHECK-O23SZ-NEXT: Running analysis: LazyValueAnalysis
 ; CHECK-O23SZ-NEXT: Running pass: CorrelatedValuePropagationPass

 ; CHECK-O23SZ-NEXT: Running pass: LCSSAPass
 ; CHECK-O23SZ-NEXT: Finished llvm::Function pass manager run.
 ; CHECK-O23SZ-NEXT: Running pass: LICMPass
 ; CHECK-EP-SCALAR-LATE-NEXT: Running pass: NoOpFunctionPass
 ; CHECK-O-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-EP-PEEPHOLE-NEXT: Running pass: NoOpFunctionPass
 ; CHECK-O-NEXT: Finished llvm::Function pass manager run.
-; CHECK-EP-CGSCC-LATE-NEXT: Running pass: NoOpCGSCCPass
 ; CHECK-O-NEXT: Finished CGSCC pass manager run.
 ; CHECK-O-NEXT: Finished llvm::Module pass manager run.
 ; CHECK-O-NEXT: Running pass: GlobalOptPass
 ; CHECK-O-NEXT: Running pass: GlobalDCEPass
 ; CHECK-DEFAULT-NEXT: Running pass: EliminateAvailableExternallyPass
 ; CHECK-LTO-NOT: Running pass: EliminateAvailableExternallyPass
 ; CHECK-O-NEXT: Running pass: ReversePostOrderFunctionAttrsPass
 ; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}GlobalsAA