[HotColdSplit] Schedule splitting late to fix perf regression

With or without PGO data applied, splitting early in the pipeline
(either before the inliner or shortly after it) regresses performance
across SPEC variants. The cause appears to be that splitting hides
context for subsequent optimizations.

Schedule splitting late again, in effect reversing r352080, which
scheduled the splitting pass early for code size benefits (documented in
https://reviews.llvm.org/D57082).

Differential Revision: https://reviews.llvm.org/D58258

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@354158 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Passes/PassBuilder.h

@@ -274,7 +274,8 @@ class PassBuilder {
   /// require some transformations for semantic reasons, they should explicitly
   /// build them.
   ModulePassManager buildModuleOptimizationPipeline(OptimizationLevel Level,
-                                                    bool DebugLogging = false);
+                                                    bool DebugLogging = false,
+                                                    bool LTOPreLink = false);
 
   /// Build a per-module default optimization pipeline.
   ///
@@ -288,7 +289,8 @@ class PassBuilder {
   /// require some transformations for semantic reasons, they should explicitly
   /// build them.
   ModulePassManager buildPerModuleDefaultPipeline(OptimizationLevel Level,
-                                                  bool DebugLogging = false);
+                                                  bool DebugLogging = false,
+                                                  bool LTOPreLink = false);
 
   /// Build a pre-link, ThinLTO-targeting default optimization pipeline to
   /// a pass manager.

lib/Passes/PassBuilder.cpp

@@ -703,14 +703,6 @@ PassBuilder::buildModuleSimplificationPipeline(OptimizationLevel Level,
   if (EnableSyntheticCounts && !PGOOpt)
     MPM.addPass(SyntheticCountsPropagation());
 
-  // Split out cold code. Splitting is done before inlining because 1) the most
-  // common kinds of cold regions can (a) be found before inlining and (b) do
-  // not grow after inlining, and 2) inhibiting inlining of cold code improves
-  // code size & compile time. Split after Mem2Reg to make code model estimates
-  // more accurate, but before InstCombine to allow it to clean things up.
-  if (EnableHotColdSplit && Phase != ThinLTOPhase::PostLink)
-    MPM.addPass(HotColdSplittingPass());
-
   // Require the GlobalsAA analysis for the module so we can query it within
   // the CGSCC pipeline.
   MPM.addPass(RequireAnalysisPass<GlobalsAA, Module>());
@@ -769,9 +761,8 @@ PassBuilder::buildModuleSimplificationPipeline(OptimizationLevel Level,
   return MPM;
 }
 
-ModulePassManager
-PassBuilder::buildModuleOptimizationPipeline(OptimizationLevel Level,
-                                             bool DebugLogging) {
+ModulePassManager PassBuilder::buildModuleOptimizationPipeline(
+    OptimizationLevel Level, bool DebugLogging, bool LTOPreLink) {
   ModulePassManager MPM(DebugLogging);
 
   // Optimize globals now that the module is fully simplified.
@@ -880,6 +871,12 @@ PassBuilder::buildModuleOptimizationPipeline(OptimizationLevel Level,
   // alignment information, try to re-derive it here.
   OptimizePM.addPass(AlignmentFromAssumptionsPass());
 
+  // Split out cold code. Splitting is done late to avoid hiding context from
+  // other optimizations and inadvertently regressing performance. The tradeoff
+  // is that this has a higher code size cost than splitting early.
+  if (EnableHotColdSplit && !LTOPreLink)
+    MPM.addPass(HotColdSplittingPass());
+
   // LoopSink pass sinks instructions hoisted by LICM, which serves as a
   // canonicalization pass that enables other optimizations. As a result,
   // LoopSink pass needs to be a very late IR pass to avoid undoing LICM
@@ -923,7 +920,7 @@ PassBuilder::buildModuleOptimizationPipeline(OptimizationLevel Level,
 
 ModulePassManager
 PassBuilder::buildPerModuleDefaultPipeline(OptimizationLevel Level,
-                                           bool DebugLogging) {
+                                           bool DebugLogging, bool LTOPreLink) {
   assert(Level != O0 && "Must request optimizations for the default pipeline!");
 
   ModulePassManager MPM(DebugLogging);
@@ -943,7 +940,7 @@ PassBuilder::buildPerModuleDefaultPipeline(OptimizationLevel Level,
                                                 DebugLogging));
 
   // Now add the optimization pipeline.
-  MPM.addPass(buildModuleOptimizationPipeline(Level, DebugLogging));
+  MPM.addPass(buildModuleOptimizationPipeline(Level, DebugLogging, LTOPreLink));
 
   return MPM;
 }
@@ -1027,7 +1024,8 @@ PassBuilder::buildLTOPreLinkDefaultPipeline(OptimizationLevel Level,
                                             bool DebugLogging) {
   assert(Level != O0 && "Must request optimizations for the default pipeline!");
   // FIXME: We should use a customized pre-link pipeline!
-  return buildPerModuleDefaultPipeline(Level, DebugLogging);
+  return buildPerModuleDefaultPipeline(Level, DebugLogging,
+                                       /*LTOPreLink=*/true);
 }
 
 ModulePassManager
@@ -1208,6 +1206,11 @@ PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level, bool DebugLogging,
   // 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()));

lib/Transforms/IPO/PassManagerBuilder.cpp

@@ -529,11 +529,6 @@ void PassManagerBuilder::populateModulePassManager(
   if (DefaultOrPreLinkPipeline && !PrepareForThinLTOUsingPGOSampleProfile)
     addPGOInstrPasses(MPM);
 
-  // Split out cold code before inlining. See comment in the new PM
-  // (\ref buildModuleSimplificationPipeline).
-  if (EnableHotColdSplit && DefaultOrPreLinkPipeline)
-    MPM.add(createHotColdSplittingPass());
-
   // We add a module alias analysis pass here. In part due to bugs in the
   // analysis infrastructure this "works" in that the analysis stays alive
   // for the entire SCC pass run below.
@@ -730,6 +725,11 @@ void PassManagerBuilder::populateModulePassManager(
     MPM.add(createConstantMergePass());     // Merge dup global constants
   }
 
+  // See comment in the new PM for justification of scheduling splitting at
+  // this stage (\ref buildModuleSimplificationPipeline).
+  if (EnableHotColdSplit && !(PrepareForLTO || PrepareForThinLTO))
+    MPM.add(createHotColdSplittingPass());
+
   if (MergeFunctions)
     MPM.add(createMergeFunctionsPass());
 
@@ -918,6 +918,11 @@ void PassManagerBuilder::addLTOOptimizationPasses(legacy::PassManagerBase &PM) {
 
 void PassManagerBuilder::addLateLTOOptimizationPasses(
     legacy::PassManagerBase &PM) {
+  // See comment in the new PM for justification of scheduling splitting at
+  // this stage (\ref buildLTODefaultPipeline).
+  if (EnableHotColdSplit)
+    PM.add(createHotColdSplittingPass());
+
   // Delete basic blocks, which optimization passes may have killed.
   PM.add(createCFGSimplificationPass());
 

test/Other/X86/lto-hot-cold-split.ll

@@ -1,10 +1,10 @@
 ; RUN: opt -module-summary %s -o %t.bc
-; RUN: llvm-lto -hot-cold-split=true -thinlto-action=run %t.bc -debug-pass=Structure 2>&1 | FileCheck %s -check-prefix=OLDPM-THINLTO-POSTLINK-Os
+; RUN: llvm-lto -hot-cold-split=true -thinlto-action=run %t.bc -debug-pass=Structure 2>&1 | FileCheck %s -check-prefix=OLDPM-ANYLTO-POSTLINK-Os
+; RUN: llvm-lto -hot-cold-split=true %t.bc -debug-pass=Structure 2>&1 | FileCheck %s -check-prefix=OLDPM-ANYLTO-POSTLINK-Os
 
 ; REQUIRES: asserts
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
-; OLDPM-THINLTO-POSTLINK-Os-LABEL: Pass Arguments
-; OLDPM-THINLTO-POSTLINK-Os-NOT: Hot Cold Splitting
+; OLDPM-ANYLTO-POSTLINK-Os: Hot Cold Splitting

test/Other/new-pm-pgo.ll

@@ -13,7 +13,6 @@
 ; GEN: Running pass: PGOInstrumentationGen
 ; USE: Running pass: PGOInstrumentationUse
 ; USE: Running pass: PGOIndirectCallPromotion
-; SPLIT: Running pass: HotColdSplittingPass
 ; USE: Running pass: PGOMemOPSizeOpt
 ; SAMPLE_USE_O: Running pass: ModuleToFunctionPassAdaptor<{{.*}}AddDiscriminatorsPass{{.*}}>
 ; SAMPLE_USE_PRE_LINK: Running pass: ModuleToFunctionPassAdaptor<{{.*}}AddDiscriminatorsPass{{.*}}>
@@ -27,6 +26,7 @@
 ; SAMPLE_USE_POST_LINK-NOT: Running pass: GlobalOptPass
 ; SAMPLE_USE_POST_LINK: Running pass: PGOIndirectCallPromotion
 ; SAMPLE_GEN: Running pass: ModuleToFunctionPassAdaptor<{{.*}}AddDiscriminatorsPass{{.*}}>
+; SPLIT: Running pass: HotColdSplittingPass
 
 define void @foo() {
   ret void

test/Other/opt-hot-cold-split.ll

@@ -1,22 +1,19 @@
 ; RUN: opt -mtriple=x86_64-- -Os -hot-cold-split=true -debug-pass=Structure < %s -o /dev/null 2>&1 | FileCheck %s -check-prefix=DEFAULT-Os
 ; RUN: opt -mtriple=x86_64-- -Os -hot-cold-split=true -passes='lto-pre-link<Os>' -debug-pass-manager < %s -o /dev/null 2>&1 | FileCheck %s -check-prefix=LTO-PRELINK-Os
 ; RUN: opt -mtriple=x86_64-- -Os -hot-cold-split=true -passes='thinlto-pre-link<Os>' -debug-pass-manager < %s -o /dev/null 2>&1 | FileCheck %s -check-prefix=THINLTO-PRELINK-Os
+; RUN: opt -mtriple=x86_64-- -Os -hot-cold-split=true -passes='lto<Os>' -debug-pass-manager < %s -o /dev/null 2>&1 | FileCheck %s -check-prefix=LTO-POSTLINK-Os
 ; RUN: opt -mtriple=x86_64-- -Os -hot-cold-split=true -passes='thinlto<Os>' -debug-pass-manager < %s -o /dev/null 2>&1 | FileCheck %s -check-prefix=THINLTO-POSTLINK-Os
 
 ; REQUIRES: asserts
 
-; Splitting should occur after Mem2Reg and should be followed by InstCombine.
+; Splitting should occur late.
 
-; DEFAULT-Os: Promote Memory to Register
 ; DEFAULT-Os: Hot Cold Splitting
-; DEFAULT-Os: Combine redundant instructions
+; DEFAULT-Os: Simplify the CFG
 
-; LTO-PRELINK-Os-LABEL: Starting llvm::Module pass manager run.
-; LTO-PRELINK-Os: Running pass: {{.*}}PromotePass
-; LTO-PRELINK-Os: Running pass: HotColdSplittingPass
+; LTO-PRELINK-Os-NOT: pass: HotColdSplittingPass
 
-; THINLTO-PRELINK-Os-LABEL: Running analysis: PassInstrumentationAnalysis
-; THINLTO-PRELINK-Os: Running pass: {{.*}}PromotePass
-; THINLTO-PRELINK-Os: Running pass: HotColdSplittingPass
+; THINLTO-PRELINK-Os-NOT: Running pass: HotColdSplittingPass
 
-; THINLTO-POSTLINK-Os-NOT: HotColdSplitting
+; LTO-POSTLINK-Os: HotColdSplitting
+; THINLTO-POSTLINK-Os: HotColdSplitting

test/Other/pass-pipelines.ll

@@ -41,7 +41,6 @@
 ; PGOUSE:      Function Integration/Inlining
 ; PGOUSE: PGOInstrumentationUsePass
 ; PGOUSE: PGOIndirectCallPromotion
-; SPLIT: Hot Cold Splitting
 ; PGOUSE: CallGraph Construction
 ; CHECK-O2-NEXT: Globals Alias Analysis
 ; CHECK-O2-NEXT: Call Graph SCC Pass Manager
@@ -100,6 +99,7 @@
 ; the runtime unrolling though.
 ; CHECK-O2: Loop Pass Manager
 ; CHECK-O2-NEXT: Loop Invariant Code Motion
+; SPLIT: Hot Cold Splitting
 ; CHECK-O2: FunctionPass Manager
 ; CHECK-O2: Loop Pass Manager
 ; CHECK-O2-NEXT: Loop Sink