[LoopRotate][NPM] Disable header duplication under -Oz

[aeubanks]

Summary

It was already disabled under -Oz in
buildFunctionSimplificationPipeline(), but not in
buildModuleOptimizationPipeline()/addPGOInstrPasses().

[fhahn]

LGTM, thanks! This should be in-line with the behavior of the legacy PM pipeline.

llvm/lib/Passes/PassBuilder.cpp

838

might be good to add a comment like Header duplication is disabled for Oz, like in the legacy PM.

[aeubanks]

add comments

llvm/lib/Passes/PassBuilder.cpp

PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
   LoopPassManager LPM1(DebugLogging), LPM2(DebugLogging);
 
   // Simplify the loop body. We do this initially to clean up after other loop
   // passes run, either when iterating on a loop or on inner loops with
   // implications on the outer loop.
   LPM1.addPass(LoopInstSimplifyPass());
   LPM1.addPass(LoopSimplifyCFGPass());
 
-  // Rotate Loop - disable header duplication at -Oz
+  // Disable header duplication in loop rotation at -Oz.
   LPM1.addPass(LoopRotatePass(Level != OptimizationLevel::Oz));
   // TODO: Investigate promotion cap for O1.
   LPM1.addPass(LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap));
   LPM1.addPass(SimpleLoopUnswitchPass());
   LPM2.addPass(IndVarSimplifyPass());
   LPM2.addPass(LoopIdiomRecognizePass());
 
   for (auto &C : LateLoopOptimizationsEPCallbacks)
if (!RunProfileGen) {
     MPM.addPass(RequireAnalysisPass<ProfileSummaryAnalysis, Module>());
     return;
   }
 
   // Perform PGO instrumentation.
   MPM.addPass(PGOInstrumentationGen(IsCS));
 
   FunctionPassManager FPM;
+  // Disable header duplication in loop rotation at -Oz.
   FPM.addPass(createFunctionToLoopPassAdaptor(
-      LoopRotatePass(), EnableMSSALoopDependency,
+      LoopRotatePass(Level != OptimizationLevel::Oz), EnableMSSALoopDependency,
       /*UseBlockFrequencyInfo=*/false, DebugLogging));
   MPM.addPass(createModuleToFunctionPassAdaptor(std::move(FPM)));
 
   // Add the profile lowering pass.
   InstrProfOptions Options;
   if (!ProfileFile.empty())
     Options.InstrProfileOutput = ProfileFile;
   // Do counter promotion at Level greater than O0.
ModulePassManager PassBuilder::buildModuleOptimizationPipeline(
   // Optimize the loop execution. These passes operate on entire loop nests
   // rather than on each loop in an inside-out manner, and so they are actually
   // function passes.
 
   for (auto &C : VectorizerStartEPCallbacks)
     C(OptimizePM, Level);
 
   // First rotate loops that may have been un-rotated by prior passes.
+  // Disable header duplication at -Oz.
   OptimizePM.addPass(createFunctionToLoopPassAdaptor(
-      LoopRotatePass(), EnableMSSALoopDependency,
+      LoopRotatePass(Level != OptimizationLevel::Oz), EnableMSSALoopDependency,
       /*UseBlockFrequencyInfo=*/false, DebugLogging));
 
   // Distribute loops to allow partial vectorization.  I.e. isolate dependences
   // into separate loop that would otherwise inhibit vectorization.  This is
   // currently only performed for loops marked with the metadata
   // llvm.loop.distribute=true or when -enable-loop-distribute is specified.
   OptimizePM.addPass(LoopDistributePass());
 

llvm/test/Transforms/LoopRotate/oz-disable.ll

 ; REQUIRES: asserts
 ; RUN: opt < %s -S -Os -debug -debug-only=loop-rotate 2>&1 | FileCheck %s -check-prefix=OS
 ; RUN: opt < %s -S -Oz -debug -debug-only=loop-rotate 2>&1 | FileCheck %s -check-prefix=OZ
+; RUN: opt < %s -S -passes='default<Os>' -debug -debug-only=loop-rotate 2>&1 | FileCheck %s -check-prefix=OS
+; RUN: opt < %s -S -passes='default<Oz>' -debug -debug-only=loop-rotate 2>&1 | FileCheck %s -check-prefix=OZ
 
 ; Loop should be rotated for -Os but not for -Oz.
 ; OS: rotating Loop at depth 1
 ; OZ-NOT: rotating Loop at depth 1
 
 @e = global i32 10
 
 declare void @use(i32)