Make post-link regular LTO pipelines match between new and old PM

[tejohnson]

Summary

As discussed in the D61022, the regular LTO post link new PM pipeline
is doing less optimizations than in the old PM. It was simpler to
refactor those passes into another PassBuilder routine, and invoke it
also on the O1 early return path. The alternative is copying a bunch of
code, or guarding a lot more code under a check that the opt level >O1.

[tejohnson]

ping

llvm/include/llvm/Passes/PassBuilder.h

public:
   /// Note that \p Level cannot be `O0` here. The pipelines produced are
   /// only intended for use when attempting to optimize code. If frontends
   /// require some transformations for semantic reasons, they should explicitly
   /// build them.
   ModulePassManager buildLTODefaultPipeline(OptimizationLevel Level,
                                             bool DebugLogging,
                                             ModuleSummaryIndex *ExportSummary);
 
+  void addLateLTOOptimizationPasses(ModulePassManager &MPM,
+                                    ModuleSummaryIndex *ExportSummary);
+
   /// Build the default `AAManager` with the default alias analysis pipeline
   /// registered.
   AAManager buildDefaultAAPipeline();
 
   /// Parse a textual pass pipeline description into a \c
   /// ModulePassManager.
   ///
   /// The format of the textual pass pipeline description looks something like:

llvm/lib/Passes/PassBuilder.cpp

PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level, bool DebugLogging,
   MPM.addPass(GlobalSplitPass());
 
   // Run whole program optimization of virtual call when the list of callees
   // is fixed.
   MPM.addPass(WholeProgramDevirtPass(ExportSummary, nullptr));
 
   // Stop here at -O1.
   if (Level == 1) {
-    // The LowerTypeTestsPass needs to run to lower type metadata and the
-    // type.test intrinsics. The pass does nothing if CFI is disabled.
-    MPM.addPass(LowerTypeTestsPass(ExportSummary, nullptr));
+    addLateLTOOptimizationPasses(MPM, ExportSummary);
     return MPM;
   }
 
   // Optimize globals to try and fold them into constants.
   MPM.addPass(GlobalOptPass());
 
   // Promote any localized globals to SSA registers.
   MPM.addPass(createModuleToFunctionPassAdaptor(PromotePass()));
#endif
   invokePeepholeEPCallbacks(MainFPM, Level);
   MainFPM.addPass(JumpThreadingPass());
   MPM.addPass(createModuleToFunctionPassAdaptor(std::move(MainFPM)));
 
   // Create a function that performs CFI checks for cross-DSO calls with
   // targets in the current module.
   MPM.addPass(CrossDSOCFIPass());
 
+  addLateLTOOptimizationPasses(MPM, ExportSummary);
+
+  return MPM;
+}
+
+void PassBuilder::addLateLTOOptimizationPasses(
+    ModulePassManager &MPM, ModuleSummaryIndex *ExportSummary) {
   // Lower type metadata and the type.test intrinsic. This pass supports
   // clang's control flow integrity mechanisms (-fsanitize=cfi*) and needs
   // to be run at link time if CFI is enabled. This pass does nothing if
   // CFI is disabled.
   MPM.addPass(LowerTypeTestsPass(ExportSummary, nullptr));
 
   // Enable splitting late in the FullLTO post-link pipeline. This is done in
   // the same stage in the old pass manager (\ref addLateLTOOptimizationPasses).
   if (EnableHotColdSplit)
     MPM.addPass(HotColdSplittingPass());
 
   // Add late LTO optimization passes.
   // Delete basic blocks, which optimization passes may have killed.
   MPM.addPass(createModuleToFunctionPassAdaptor(SimplifyCFGPass()));
 
   // Drop bodies of available eternally objects to improve GlobalDCE.
   MPM.addPass(EliminateAvailableExternallyPass());
 
   // Now that we have optimized the program, discard unreachable functions.
   MPM.addPass(GlobalDCEPass());
 
   // FIXME: Enable MergeFuncs, conditionally, after ported, maybe.
-  return MPM;
 }
 
 AAManager PassBuilder::buildDefaultAAPipeline() {
   AAManager AA;
 
   // The order in which these are registered determines their priority when
   // being queried.
 

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

 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}LazyCallGraph{{.*}}>
 ; CHECK-O-NEXT: Running analysis: AAManager
 ; CHECK-O1-NEXT: Running analysis: PassInstrumentationAnalysis
 ; CHECK-O1-NEXT: Running analysis: TargetLibraryAnalysis
 ; CHECK-O-NEXT: Running pass: ReversePostOrderFunctionAttrsPass
 ; CHECK-O-NEXT: Running analysis: CallGraphAnalysis
 ; CHECK-O-NEXT: Running pass: GlobalSplitPass
 ; CHECK-O-NEXT: Running pass: WholeProgramDevirtPass
-; CHECK-O1-NEXT: Running pass: LowerTypeTestsPass
 ; CHECK-O2-NEXT: Running pass: GlobalOptPass
 ; CHECK-O2-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}PromotePass>
 ; CHECK-O2-NEXT: Running pass: ConstantMergePass
 ; CHECK-O2-NEXT: Running pass: DeadArgumentEliminationPass
 ; CHECK-O2-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}PassManager{{.*}}>
 ; CHECK-O2-NEXT: Starting llvm::Function pass manager run.
 ; CHECK-O3-NEXT: Running pass: AggressiveInstCombinePass
 ; CHECK-O2-NEXT: Running pass: InstCombinePass

 ; CHECK-O2-NEXT: Running pass: TailCallElimPass on foo
 ; CHECK-O2-NEXT: Finished llvm::Function pass manager run.
 ; CHECK-O2-NEXT: Running pass: ModuleToPostOrderCGSCCPassAdaptor<{{.*}}PostOrderFunctionAttrsPass>
 ; CHECK-O2-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}PassManager{{.*}}>
 ; CHECK-O2-NEXT: Running analysis: MemoryDependenceAnalysis
 ; CHECK-O2-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O2-NEXT: Running analysis: DemandedBitsAnalysis
 ; CHECK-O2-NEXT: Running pass: CrossDSOCFIPass
-; CHECK-O2-NEXT: Running pass: LowerTypeTestsPass
-; CHECK-O2-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}SimplifyCFGPass>
-; CHECK-O2-NEXT: Running pass: EliminateAvailableExternallyPass
-; CHECK-O2-NEXT: Running pass: GlobalDCEPass
+; CHECK-O-NEXT: Running pass: LowerTypeTestsPass
+; CHECK-O-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}SimplifyCFGPass>
+; CHECK-O1-NEXT: Running analysis: TargetIRAnalysis on foo
+; CHECK-O1-NEXT: Running analysis: AssumptionAnalysis on foo
+; CHECK-O-NEXT: Running pass: EliminateAvailableExternallyPass
+; CHECK-O-NEXT: Running pass: GlobalDCEPass
 ; CHECK-O-NEXT: Finished llvm::Module pass manager run.
 ; CHECK-O-NEXT: Running pass: PrintModulePass
 
 ; Make sure we get the IR back out without changes when we print the module.
 ; CHECK-O-LABEL: define void @foo(i32 %n) local_unnamed_addr {
 ; CHECK-O-NEXT: entry:
 ; CHECK-O-NEXT:   br label %loop
 ; CHECK-O:      loop:

llvm/test/tools/gold/X86/opt-level.ll

 ; RUN: llvm-as -o %t.bc %s
 ; RUN: %gold -plugin %llvmshlibdir/LLVMgold%shlibext -plugin-opt=save-temps \
 ; RUN:    -m elf_x86_64 \
 ; RUN:    -plugin-opt=O0 -r -o %t.o %t.bc
 ; RUN: llvm-dis < %t.o.0.4.opt.bc -o - | FileCheck --check-prefix=CHECK-O0 %s
 ; RUN: %gold -plugin %llvmshlibdir/LLVMgold%shlibext -plugin-opt=save-temps \
 ; RUN:    -m elf_x86_64 \
 ; RUN:    -plugin-opt=O1 -r -o %t.o %t.bc
-; RUN: llvm-dis < %t.o.0.4.opt.bc -o - | FileCheck --check-prefix=CHECK-O1 --check-prefix=CHECK-O1-OLDPM %s
+; RUN: llvm-dis < %t.o.0.4.opt.bc -o - | FileCheck --check-prefix=CHECK-O1 %s
 ; RUN: %gold -plugin %llvmshlibdir/LLVMgold%shlibext -plugin-opt=save-temps \
 ; RUN:    -m elf_x86_64 \
 ; RUN:    -plugin-opt=O2 -r -o %t.o %t.bc
 ; RUN: llvm-dis < %t.o.0.4.opt.bc -o - | FileCheck --check-prefix=CHECK-O2 %s
 
 ; RUN: %gold -plugin %llvmshlibdir/LLVMgold%shlibext -plugin-opt=save-temps \
 ; RUN:    -m elf_x86_64 --plugin-opt=new-pass-manager \
 ; RUN:    -plugin-opt=O0 -r -o %t.o %t.bc
 ; RUN: llvm-dis < %t.o.0.4.opt.bc -o - | FileCheck --check-prefix=CHECK-O0 %s
 ; RUN: %gold -plugin %llvmshlibdir/LLVMgold%shlibext -plugin-opt=save-temps \
 ; RUN:    -m elf_x86_64 --plugin-opt=new-pass-manager \
 ; RUN:    -plugin-opt=O1 -r -o %t.o %t.bc
-; RUN: llvm-dis < %t.o.0.4.opt.bc -o - | FileCheck --check-prefix=CHECK-O1 --check-prefix=CHECK-O1-NEWPM %s
+; RUN: llvm-dis < %t.o.0.4.opt.bc -o - | FileCheck --check-prefix=CHECK-O1 %s
 ; RUN: %gold -plugin %llvmshlibdir/LLVMgold%shlibext -plugin-opt=save-temps \
 ; RUN:    -m elf_x86_64 --plugin-opt=new-pass-manager \
 ; RUN:    -plugin-opt=O2 -r -o %t.o %t.bc
 ; RUN: llvm-dis < %t.o.0.4.opt.bc -o - | FileCheck --check-prefix=CHECK-O2 %s
 
 ; CHECK-O0: define internal void @foo(
 ; CHECK-O1: define internal void @foo(
 ; CHECK-O2-NOT: define internal void @foo(

 t:
   br label %end
 
 f:
   br label %end
 
 end:
   ; CHECK-O0: phi
-  ; CHECK-O1-OLDPM: select
-  ; The new PM does not do as many optimizations at O1
-  ; CHECK-O1-NEWPM: phi
+  ; CHECK-O1: select
   %r = phi i32 [ 1, %t ], [ 2, %f ]
   ret i32 %r
 }
 
 define i1 @baz() {
   call void @foo()
   %c = call i32 @bar(i1 true)
   %p = call i1 @llvm.type.test(i8* undef, metadata !"typeid1")