[PGO] Enable preinline and cleanup when optimize for size

Differential Revision: https://reviews.llvm.org/D91673

llvm/lib/Passes/PassBuilder.cpp

@@ -838,20 +838,16 @@ void PassBuilder::addPGOInstrPasses(ModulePassManager &MPM,
                                     std::string ProfileFile,
                                     std::string ProfileRemappingFile) {
   assert(Level != OptimizationLevel::O0 && "Not expecting O0 here!");
-  // Generally running simplification passes and the inliner with an high
-  // threshold results in smaller executables, but there may be cases where
-  // the size grows, so let's be conservative here and skip this simplification
-  // at -Os/Oz. We will not do this  inline for context sensistive PGO (when
-  // IsCS is true).
-  if (!Level.isOptimizingForSize() && !IsCS && !DisablePreInliner) {
+  if (!IsCS && !DisablePreInliner) {
     InlineParams IP;
 
     IP.DefaultThreshold = PreInlineThreshold;
 
-    // FIXME: The hint threshold has the same value used by the regular inliner.
-    // This should probably be lowered after performance testing.
+    // FIXME: The hint threshold has the same value used by the regular inliner
+    // when not optimzing for size. This should probably be lowered after
+    // performance testing.
     // FIXME: this comment is cargo culted from the old pass manager, revisit).
-    IP.HintThreshold = 325;
+    IP.HintThreshold = Level.isOptimizingForSize() ? PreInlineThreshold : 325;
     ModuleInlinerWrapperPass MIWP(IP, DebugLogging);
     CGSCCPassManager &CGPipeline = MIWP.getPM();
 

llvm/lib/Transforms/IPO/PassManagerBuilder.cpp

@@ -330,19 +330,21 @@ void PassManagerBuilder::addPGOInstrPasses(legacy::PassManagerBase &MPM,
     return;
 
   // Perform the preinline and cleanup passes for O1 and above.
-  // And avoid doing them if optimizing for size.
   // We will not do this inline for context sensitive PGO (when IsCS is true).
-  if (OptLevel > 0 && SizeLevel == 0 && !DisablePreInliner &&
-      PGOSampleUse.empty() && !IsCS) {
+  if (OptLevel > 0 && !DisablePreInliner && PGOSampleUse.empty() && !IsCS) {
     // Create preinline pass. We construct an InlineParams object and specify
     // the threshold here to avoid the command line options of the regular
     // inliner to influence pre-inlining. The only fields of InlineParams we
     // care about are DefaultThreshold and HintThreshold.
     InlineParams IP;
     IP.DefaultThreshold = PreInlineThreshold;
-    // FIXME: The hint threshold has the same value used by the regular inliner.
-    // This should probably be lowered after performance testing.
-    IP.HintThreshold = 325;
+    // FIXME: The hint threshold has the same value used by the regular inliner
+    // when not optimzing for size. This should probably be lowered after
+    // performance testing.
+    // Use PreInlineThreshold for both -Os and -Oz. Not running preinliner makes
+    // the instrumented binary unusably large. Even if PreInlineThreshold is not
+    // correct thresold for -Oz, it is better than not running preinliner.
+    IP.HintThreshold = SizeLevel > 0 ? PreInlineThreshold : 325;
 
     MPM.add(createFunctionInliningPass(IP));
     MPM.add(createSROAPass());

llvm/test/Other/new-pm-pgo-preinline.ll

@@ -0,0 +1,24 @@
+; RUN: opt -disable-verify -debug-pass-manager -pgo-kind=pgo-instr-gen-pipeline -passes='default<Os>' -S %s 2>&1 | FileCheck %s --check-prefixes=CHECK-Osz
+; RUN: opt -disable-verify -debug-pass-manager -pgo-kind=pgo-instr-gen-pipeline -passes='default<Oz>' -S %s 2>&1 | FileCheck %s --check-prefixes=CHECK-Osz
+
+; CHECK-Osz: Running pass: ModuleInlinerWrapperPass
+; CHECK-Osz-NEXT: Running analysis: InlineAdvisorAnalysis
+; CHECK-Osz-NEXT: Starting {{.*}}Module pass manager run.
+; CHECK-Osz-NEXT: Running analysis: InnerAnalysisManagerProxy
+; CHECK-Osz-NEXT: Running analysis: LazyCallGraphAnalysis
+; CHECK-Osz-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy on (foo)
+; CHECK-Osz-NEXT: Running analysis: OuterAnalysisManagerProxy
+; CHECK-Osz-NEXT: Starting CGSCC pass manager run.
+; CHECK-Osz-NEXT: Running pass: InlinerPass on (foo)
+; CHECK-Osz-NEXT: Running pass: SROA on foo
+; CHECK-Osz-NEXT: Running pass: EarlyCSEPass on foo
+; CHECK-Osz-NEXT: Running pass: SimplifyCFGPass on foo
+; CHECK-Osz-NEXT: Running pass: InstCombinePass on foo
+; CHECK-Osz-NEXT: Finished CGSCC pass manager run.
+; CHECK-Osz-NEXT: Finished {{.*}}Module pass manager run.
+; CHECK-Osz-NEXT: Running pass: GlobalDCEPass
+; CHECK-Osz-NEXT: Running pass: PGOInstrumentationGen
+
+define void @foo() {
+  ret void
+}

llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll

@@ -5,27 +5,27 @@
 ; RUN: opt -disable-verify -debug-pass-manager \
 ; RUN:     -pgo-kind=pgo-instr-use-pipeline -profile-file='%t.profdata' \
 ; RUN:     -passes='thinlto-pre-link<O1>' -S %s 2>&1 \
-; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O1,CHECK-O123
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O1,CHECK-O123SZ
 ; RUN: opt -disable-verify -debug-pass-manager \
 ; RUN:     -pgo-kind=pgo-instr-use-pipeline -profile-file='%t.profdata' \
 ; RUN:     -passes='thinlto-pre-link<O2>' -S  %s 2>&1 \
-; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O2,CHECK-O23SZ,CHECK-O123
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O2,CHECK-O23SZ,CHECK-O123SZ
 ; RUN: opt -disable-verify -debug-pass-manager \
 ; RUN:     -pgo-kind=pgo-instr-use-pipeline -profile-file='%t.profdata' \
 ; RUN:     -passes='thinlto-pre-link<O3>' -S -passes-ep-pipeline-start='no-op-module' %s 2>&1 \
-; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O3,CHECK-O23SZ,CHECK-O123,CHECK-EP-PIPELINE-START
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O3,CHECK-O23SZ,CHECK-O123SZ,CHECK-EP-PIPELINE-START
 ; RUN: opt -disable-verify -debug-pass-manager \
 ; RUN:     -pgo-kind=pgo-instr-use-pipeline -profile-file='%t.profdata' \
 ; RUN:     -passes='thinlto-pre-link<Os>' -S %s 2>&1 \
-; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-Os,CHECK-O23SZ
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O123SZ,CHECK-Os,CHECK-O23SZ
 ; RUN: opt -disable-verify -debug-pass-manager \
 ; RUN:     -pgo-kind=pgo-instr-use-pipeline -profile-file='%t.profdata' \
 ; RUN:     -passes='thinlto-pre-link<Oz>' -S %s 2>&1 \
-; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-Oz,CHECK-O23SZ
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O123SZ,CHECK-Oz,CHECK-O23SZ
 ; RUN: opt -disable-verify -debug-pass-manager -new-pm-debug-info-for-profiling \
 ; RUN:     -pgo-kind=pgo-instr-use-pipeline -profile-file='%t.profdata' \
 ; RUN:     -passes='thinlto-pre-link<O2>' -S  %s 2>&1 \
-; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O2,CHECK-O23SZ,CHECK-O123
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O2,CHECK-O23SZ,CHECK-O123SZ
 ;
 ; CHECK-O: Starting {{.*}}Module pass manager run.
 ; CHECK-O-NEXT: Running pass: Annotation2Metadata
@@ -57,22 +57,22 @@
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
 ; CHECK-O-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-O-NEXT: Finished {{.*}}Function pass manager run.
-; CHECK-O123-NEXT: Running pass: ModuleInlinerWrapperPass
-; CHECK-O123-NEXT: Running analysis: InlineAdvisorAnalysis
-; CHECK-O123-NEXT: Starting {{.*}}Module pass manager run.
-; CHECK-O123-NEXT: Running analysis: InnerAnalysisManagerProxy
-; CHECK-O123-NEXT: Running analysis: LazyCallGraphAnalysis
-; CHECK-O123-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy on (foo)
-; CHECK-O123-NEXT: Running analysis: OuterAnalysisManagerProxy
-; CHECK-O123-NEXT: Starting CGSCC pass manager run.
-; CHECK-O123-NEXT: Running pass: InlinerPass on (foo)
-; CHECK-O123-NEXT: Running pass: SROA on foo
-; CHECK-O123-NEXT: Running pass: EarlyCSEPass on foo
-; CHECK-O123-NEXT: Running pass: SimplifyCFGPass on foo
-; CHECK-O123-NEXT: Running pass: InstCombinePass on foo
-; CHECK-O123-NEXT: Finished CGSCC pass manager run.
-; CHECK-O123-NEXT: Finished {{.*}}Module pass manager run.
-; CHECK-O123-NEXT: Running pass: GlobalDCEPass
+; CHECK-O123SZ-NEXT: Running pass: ModuleInlinerWrapperPass
+; CHECK-O123SZ-NEXT: Running analysis: InlineAdvisorAnalysis
+; CHECK-O123SZ-NEXT: Starting {{.*}}Module pass manager run.
+; CHECK-O123SZ-NEXT: Running analysis: InnerAnalysisManagerProxy
+; CHECK-O123SZ-NEXT: Running analysis: LazyCallGraphAnalysis
+; CHECK-O123SZ-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy on (foo)
+; CHECK-O123SZ-NEXT: Running analysis: OuterAnalysisManagerProxy
+; CHECK-O123SZ-NEXT: Starting CGSCC pass manager run.
+; CHECK-O123SZ-NEXT: Running pass: InlinerPass on (foo)
+; CHECK-O123SZ-NEXT: Running pass: SROA on foo
+; CHECK-O123SZ-NEXT: Running pass: EarlyCSEPass on foo
+; CHECK-O123SZ-NEXT: Running pass: SimplifyCFGPass on foo
+; CHECK-O123SZ-NEXT: Running pass: InstCombinePass on foo
+; CHECK-O123SZ-NEXT: Finished CGSCC pass manager run.
+; CHECK-O123SZ-NEXT: Finished {{.*}}Module pass manager run.
+; CHECK-O123SZ-NEXT: Running pass: GlobalDCEPass
 ; CHECK-O-NEXT: Running pass: PGOInstrumentationUse
 ; These next two can appear in any order since they are accessed as parameters
 ; on the same call to BlockFrequencyInfo::calculate.
@@ -81,15 +81,13 @@
 ; CHECK-O-DAG: Running analysis: LoopAnalysis on foo
 ; CHECK-O-NEXT: Running analysis: BlockFrequencyAnalysis on foo
 ; CHECK-O-NEXT: Invalidating analysis: InnerAnalysisManagerProxy
-; CHECK-O123-NEXT: Invalidating analysis: LazyCallGraphAnalysis on
-; CHECK-O123-NEXT: Invalidating analysis: InnerAnalysisManagerProxy
+; CHECK-O123SZ-NEXT: Invalidating analysis: LazyCallGraphAnalysis on
+; CHECK-O123SZ-NEXT: Invalidating analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}ProfileSummaryAnalysis
 ; CHECK-O-NEXT: Running pass: PGOIndirectCallPromotion on
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis on foo
 ; CHECK-O-NEXT: Running pass: ModuleInlinerWrapperPass
-; CHECK-Os-NEXT: Running analysis: InlineAdvisorAnalysis
-; CHECK-Oz-NEXT: Running analysis: InlineAdvisorAnalysis
 ; CHECK-O-NEXT: Starting {{.*}}Module pass manager run.
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Running analysis: LazyCallGraphAnalysis

llvm/test/Other/pm-pgo-preinline.ll

@@ -0,0 +1,24 @@
+; RUN: opt -disable-verify -enable-new-pm=0 -pgo-kind=pgo-instr-gen-pipeline -mtriple=x86_64-- -Os -debug-pass=Structure < %s -o /dev/null 2>&1 | FileCheck %s --check-prefix=CHECK-Osz
+; RUN: opt -disable-verify -enable-new-pm=0 -pgo-kind=pgo-instr-gen-pipeline -mtriple=x86_64-- -Oz -debug-pass=Structure < %s -o /dev/null 2>&1 | FileCheck %s --check-prefix=CHECK-Osz
+
+
+; CHECK-Osz: CallGraph Construction
+; CHECK-Osz-NEXT: Call Graph SCC Pass Manager
+; CHECK-Osz-NEXT: Function Integration/Inlining
+; CHECK-Osz-NEXT: FunctionPass Manager
+; CHECK-Osz-NEXT: Dominator Tree Construction
+; CHECK-Osz-NEXT: SROA
+; CHECK-Osz-NEXT: Early CSE
+; CHECK-Osz-NEXT: Simplify the CFG
+; CHECK-Osz-NEXT: Dominator Tree Construction
+; CHECK-Osz-NEXT: Basic Alias Analysis (stateless AA impl)
+; CHECK-Osz-NEXT: Function Alias Analysis Results
+; CHECK-Osz-NEXT: Natural Loop Information
+; CHECK-Osz-NEXT: Lazy Branch Probability Analysis
+; CHECK-Osz-NEXT: Lazy Block Frequency Analysis
+; CHECK-Osz-NEXT: Optimization Remark Emitter
+; CHECK-Osz-NEXT: Combine redundant instructions
+
+define void @foo() {
+  ret void
+}