diff --git a/llvm/lib/Passes/PassBuilderPipelines.cpp b/llvm/lib/Passes/PassBuilderPipelines.cpp
--- a/llvm/lib/Passes/PassBuilderPipelines.cpp
+++ b/llvm/lib/Passes/PassBuilderPipelines.cpp
@@ -1454,6 +1454,9 @@
     MPM.addPass(RequireAnalysisPass<ProfileSummaryAnalysis, Module>());
   }
 
+  // Try to run OpenMP optimizations, quick no-op if no OpenMP metadata present.
+  MPM.addPass(OpenMPOptPass());
+
   // Remove unused virtual tables to improve the quality of code generated by
   // whole-program devirtualization and bitset lowering.
   MPM.addPass(GlobalDCEPass());
@@ -1648,6 +1651,10 @@
 
   addVectorPasses(Level, MainFPM, /* IsFullLTO */ true);
 
+  // Run the OpenMPOpt CGSCC pass again late.
+  MPM.addPass(
+      createModuleToPostOrderCGSCCPassAdaptor(OpenMPOptCGSCCPass()));
+
   invokePeepholeEPCallbacks(MainFPM, Level);
   MainFPM.addPass(JumpThreadingPass(/*InsertFreezeWhenUnfoldingSelect*/ true));
   MPM.addPass(createModuleToFunctionPassAdaptor(std::move(MainFPM),
diff --git a/llvm/test/Other/new-pm-lto-defaults.ll b/llvm/test/Other/new-pm-lto-defaults.ll
--- a/llvm/test/Other/new-pm-lto-defaults.ll
+++ b/llvm/test/Other/new-pm-lto-defaults.ll
@@ -27,6 +27,7 @@
 
 ; CHECK-O: Running pass: Annotation2Metadata
 ; CHECK-O-NEXT: Running pass: CrossDSOCFIPass
+; CHECK-O-NEXT: Running pass: OpenMPOptPass
 ; CHECK-O-NEXT: Running pass: GlobalDCEPass
 ; CHECK-O-NEXT: Running pass: ForceFunctionAttrsPass
 ; CHECK-O-NEXT: Running pass: InferFunctionAttrsPass
@@ -87,6 +88,7 @@
 ; CHECK-O23SZ-NEXT: Running analysis: GlobalsAA on [module]
 ; CHECK-O23SZ-NEXT: Running pass: InvalidateAnalysisPass<{{.*}}AAManager
 ; CHECK-O23SZ-NEXT: Invalidating analysis: AAManager on foo
+; CHECK-O23SZ-NEXT: Running pass: OpenMPOptCGSCCPass on (foo)
 ; CHECK-O23SZ-NEXT: Running pass: LoopSimplifyPass on foo
 ; CHECK-O23SZ-NEXT: Running analysis: LoopAnalysis on foo
 ; CHECK-O23SZ-NEXT: Running pass: LCSSAPass on foo