[PGO] Profile guided code size optimization.
Summary:
Enable some of the existing size optimizations for cold code under PGO.
A ~5% code size saving in big internal app under PGO.
The way it gets BFI/PSI is discussed in the RFC thread
http://lists.llvm.org/pipermail/llvm-dev/2019-March/130894.html
Note it doesn't currently touch loop passes.
Reviewers: davidxl, eraman
Reviewed By: eraman
Subscribers: mgorny, javed.absar, smeenai, mehdi_amini, eraman, zzheng, steven_wu, dexonsmith, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59514
llvm-svn: 358422
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 2cc2e82..d8b188a 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -4178,7 +4178,7 @@
auto InstCombineErase = [this](Instruction *I) {
eraseInstFromFunction(*I);
};
- LibCallSimplifier Simplifier(DL, &TLI, ORE, InstCombineRAUW,
+ LibCallSimplifier Simplifier(DL, &TLI, ORE, BFI, PSI, InstCombineRAUW,
InstCombineErase);
if (Value *With = Simplifier.optimizeCall(CI)) {
++NumSimplified;
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineInternal.h b/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
index ee18536..a42cf95 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
+++ b/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
@@ -52,12 +52,14 @@
class APInt;
class AssumptionCache;
+class BlockFrequencyInfo;
class DataLayout;
class DominatorTree;
class GEPOperator;
class GlobalVariable;
class LoopInfo;
class OptimizationRemarkEmitter;
+class ProfileSummaryInfo;
class TargetLibraryInfo;
class User;
@@ -304,6 +306,8 @@
const DataLayout &DL;
const SimplifyQuery SQ;
OptimizationRemarkEmitter &ORE;
+ BlockFrequencyInfo *BFI;
+ ProfileSummaryInfo *PSI;
// Optional analyses. When non-null, these can both be used to do better
// combining and will be updated to reflect any changes.
@@ -315,11 +319,11 @@
InstCombiner(InstCombineWorklist &Worklist, BuilderTy &Builder,
bool MinimizeSize, bool ExpensiveCombines, AliasAnalysis *AA,
AssumptionCache &AC, TargetLibraryInfo &TLI, DominatorTree &DT,
- OptimizationRemarkEmitter &ORE, const DataLayout &DL,
- LoopInfo *LI)
+ OptimizationRemarkEmitter &ORE, BlockFrequencyInfo *BFI,
+ ProfileSummaryInfo *PSI, const DataLayout &DL, LoopInfo *LI)
: Worklist(Worklist), Builder(Builder), MinimizeSize(MinimizeSize),
ExpensiveCombines(ExpensiveCombines), AA(AA), AC(AC), TLI(TLI), DT(DT),
- DL(DL), SQ(DL, &TLI, &DT, &AC), ORE(ORE), LI(LI) {}
+ DL(DL), SQ(DL, &TLI, &DT, &AC), ORE(ORE), BFI(BFI), PSI(PSI), LI(LI) {}
/// Run the combiner over the entire worklist until it is empty.
///
diff --git a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
index 6ee94a9..7e26dee 100644
--- a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -46,14 +46,17 @@
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/BasicAliasAnalysis.h"
+#include "llvm/Analysis/BlockFrequencyInfo.h"
#include "llvm/Analysis/CFG.h"
#include "llvm/Analysis/ConstantFolding.h"
#include "llvm/Analysis/EHPersonalities.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/InstructionSimplify.h"
+#include "llvm/Analysis/LazyBlockFrequencyInfo.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/MemoryBuiltins.h"
#include "llvm/Analysis/OptimizationRemarkEmitter.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
#include "llvm/Analysis/TargetFolder.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/ValueTracking.h"
@@ -3478,7 +3481,8 @@
static bool combineInstructionsOverFunction(
Function &F, InstCombineWorklist &Worklist, AliasAnalysis *AA,
AssumptionCache &AC, TargetLibraryInfo &TLI, DominatorTree &DT,
- OptimizationRemarkEmitter &ORE, bool ExpensiveCombines = true,
+ OptimizationRemarkEmitter &ORE, BlockFrequencyInfo *BFI,
+ ProfileSummaryInfo *PSI, bool ExpensiveCombines = true,
LoopInfo *LI = nullptr) {
auto &DL = F.getParent()->getDataLayout();
ExpensiveCombines |= EnableExpensiveCombines;
@@ -3509,7 +3513,7 @@
MadeIRChange |= prepareICWorklistFromFunction(F, DL, &TLI, Worklist);
InstCombiner IC(Worklist, Builder, F.hasMinSize(), ExpensiveCombines, AA,
- AC, TLI, DT, ORE, DL, LI);
+ AC, TLI, DT, ORE, BFI, PSI, DL, LI);
IC.MaxArraySizeForCombine = MaxArraySize;
if (!IC.run())
@@ -3529,8 +3533,15 @@
auto *LI = AM.getCachedResult<LoopAnalysis>(F);
auto *AA = &AM.getResult<AAManager>(F);
+ const ModuleAnalysisManager &MAM =
+ AM.getResult<ModuleAnalysisManagerFunctionProxy>(F).getManager();
+ ProfileSummaryInfo *PSI =
+ MAM.getCachedResult<ProfileSummaryAnalysis>(*F.getParent());
+ auto *BFI = (PSI && PSI->hasProfileSummary()) ?
+ &AM.getResult<BlockFrequencyAnalysis>(F) : nullptr;
+
if (!combineInstructionsOverFunction(F, Worklist, AA, AC, TLI, DT, ORE,
- ExpensiveCombines, LI))
+ BFI, PSI, ExpensiveCombines, LI))
// No changes, all analyses are preserved.
return PreservedAnalyses::all();
@@ -3554,6 +3565,8 @@
AU.addPreserved<AAResultsWrapperPass>();
AU.addPreserved<BasicAAWrapperPass>();
AU.addPreserved<GlobalsAAWrapperPass>();
+ AU.addRequired<ProfileSummaryInfoWrapperPass>();
+ LazyBlockFrequencyInfoPass::getLazyBFIAnalysisUsage(AU);
}
bool InstructionCombiningPass::runOnFunction(Function &F) {
@@ -3570,9 +3583,15 @@
// Optional analyses.
auto *LIWP = getAnalysisIfAvailable<LoopInfoWrapperPass>();
auto *LI = LIWP ? &LIWP->getLoopInfo() : nullptr;
+ ProfileSummaryInfo *PSI =
+ &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+ BlockFrequencyInfo *BFI =
+ (PSI && PSI->hasProfileSummary()) ?
+ &getAnalysis<LazyBlockFrequencyInfoPass>().getBFI() :
+ nullptr;
return combineInstructionsOverFunction(F, Worklist, AA, AC, TLI, DT, ORE,
- ExpensiveCombines, LI);
+ BFI, PSI, ExpensiveCombines, LI);
}
char InstructionCombiningPass::ID = 0;
@@ -3585,6 +3604,8 @@
INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
INITIALIZE_PASS_DEPENDENCY(GlobalsAAWrapperPass)
INITIALIZE_PASS_DEPENDENCY(OptimizationRemarkEmitterWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(LazyBlockFrequencyInfoPass)
+INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)
INITIALIZE_PASS_END(InstructionCombiningPass, "instcombine",
"Combine redundant instructions", false, false)