maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[PGOMemOPSize] Preserve the DominatorTree 

Summary:
PGOMemOPSize only modifies CFG in a couple of places; thus we can preserve the DominatorTree with little effort.
When optimizing SQLite with -O3, this patch can decrease 3.8% of the numbers of nodes traversed by DFS and 5.7% of the times DominatorTreeBase::recalculation is called.

Reviewers: kuhar, davide, dmgreen

Reviewed By: dmgreen

Subscribers: mzolotukhin, vsk, llvm-commits

Differential Revision: https://reviews.llvm.org/D48914

llvm-svn: 336522
This commit is contained in:
Chijun Sima 2018-07-09 08:07:21 +00:00
parent 2dc3dac90c
commit 9e1e0c7b2a
6 changed files with 36 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
llvm/lib/Transforms/Instrumentation/PGOMemOPSizeOpt.cpp
View File

@ -25,6 +25,8 @@
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/DomTreeUpdater.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstVisitor.h"
@ -112,6 +114,7 @@ private:
AU.addRequired<BlockFrequencyInfoWrapperPass>();
AU.addRequired<OptimizationRemarkEmitterWrapperPass>();
AU.addPreserved<GlobalsAAWrapperPass>();
AU.addPreserved<DominatorTreeWrapperPass>();
}
};
} // end anonymous namespace
@ -133,8 +136,8 @@ namespace {
class MemOPSizeOpt : public InstVisitor<MemOPSizeOpt> {
public:
MemOPSizeOpt(Function &Func, BlockFrequencyInfo &BFI,
OptimizationRemarkEmitter &ORE)
: Func(Func), BFI(BFI), ORE(ORE), Changed(false) {
OptimizationRemarkEmitter &ORE, DominatorTree *DT)
: Func(Func), BFI(BFI), ORE(ORE), DT(DT), Changed(false) {
ValueDataArray =
llvm::make_unique<InstrProfValueData[]>(MemOPMaxVersion + 2);
// Get the MemOPSize range information from option MemOPSizeRange,
@ -170,6 +173,7 @@ private:
Function &Func;
BlockFrequencyInfo &BFI;
OptimizationRemarkEmitter &ORE;
DominatorTree *DT;
bool Changed;
std::vector<MemIntrinsic *> WorkList;
// Start of the previse range.
@ -336,15 +340,16 @@ bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
LLVM_DEBUG(dbgs() << *BB << "\n");
auto OrigBBFreq = BFI.getBlockFreq(BB);
BasicBlock *DefaultBB = SplitBlock(BB, MI);
BasicBlock *DefaultBB = SplitBlock(BB, MI, DT);
BasicBlock::iterator It(*MI);
++It;
assert(It != DefaultBB->end());
BasicBlock *MergeBB = SplitBlock(DefaultBB, &(*It));
BasicBlock *MergeBB = SplitBlock(DefaultBB, &(*It), DT);
MergeBB->setName("MemOP.Merge");
BFI.setBlockFreq(MergeBB, OrigBBFreq.getFrequency());
DefaultBB->setName("MemOP.Default");
DomTreeUpdater DTU(DT, DomTreeUpdater::UpdateStrategy::Eager);
auto &Ctx = Func.getContext();
IRBuilder<> IRB(BB);
BB->getTerminator()->eraseFromParent();
@ -361,6 +366,10 @@ bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
LLVM_DEBUG(dbgs() << "\n\n== Basic Block After==\n");
std::vector<DominatorTree::UpdateType> Updates;
if (DT)
Updates.reserve(2 * SizeIds.size());
for (uint64_t SizeId : SizeIds) {
BasicBlock *CaseBB = BasicBlock::Create(
Ctx, Twine("MemOP.Case.") + Twine(SizeId), &Func, DefaultBB);
@ -375,8 +384,15 @@ bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
IRBuilder<> IRBCase(CaseBB);
IRBCase.CreateBr(MergeBB);
SI->addCase(CaseSizeId, CaseBB);
if (DT) {
Updates.push_back({DominatorTree::Insert, CaseBB, MergeBB});
Updates.push_back({DominatorTree::Insert, BB, CaseBB});
}
LLVM_DEBUG(dbgs() << *CaseBB << "\n");
}
DTU.applyUpdates(Updates);
Updates.clear();
setProfMetadata(Func.getParent(), SI, CaseCounts, MaxCount);
LLVM_DEBUG(dbgs() << *BB << "\n");
@ -397,13 +413,14 @@ bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
} // namespace
static bool PGOMemOPSizeOptImpl(Function &F, BlockFrequencyInfo &BFI,
OptimizationRemarkEmitter &ORE) {
OptimizationRemarkEmitter &ORE,
DominatorTree *DT) {
if (DisableMemOPOPT)
return false;
if (F.hasFnAttribute(Attribute::OptimizeForSize))
return false;
MemOPSizeOpt MemOPSizeOpt(F, BFI, ORE);
MemOPSizeOpt MemOPSizeOpt(F, BFI, ORE, DT);
MemOPSizeOpt.perform();
return MemOPSizeOpt.isChanged();
}
@ -412,7 +429,9 @@ bool PGOMemOPSizeOptLegacyPass::runOnFunction(Function &F) {
BlockFrequencyInfo &BFI =
getAnalysis<BlockFrequencyInfoWrapperPass>().getBFI();
auto &ORE = getAnalysis<OptimizationRemarkEmitterWrapperPass>().getORE();
return PGOMemOPSizeOptImpl(F, BFI, ORE);
auto *DTWP = getAnalysisIfAvailable<DominatorTreeWrapperPass>();
DominatorTree *DT = DTWP ? &DTWP->getDomTree() : nullptr;
return PGOMemOPSizeOptImpl(F, BFI, ORE, DT);
}
namespace llvm {
@ -422,11 +441,13 @@ PreservedAnalyses PGOMemOPSizeOpt::run(Function &F,
FunctionAnalysisManager &FAM) {
auto &BFI = FAM.getResult<BlockFrequencyAnalysis>(F);
auto &ORE = FAM.getResult<OptimizationRemarkEmitterAnalysis>(F);
bool Changed = PGOMemOPSizeOptImpl(F, BFI, ORE);
auto *DT = FAM.getCachedResult<DominatorTreeAnalysis>(F);
bool Changed = PGOMemOPSizeOptImpl(F, BFI, ORE, DT);
if (!Changed)
return PreservedAnalyses::all();
auto PA = PreservedAnalyses();
PA.preserve<GlobalsAA>();
PA.preserve<DominatorTreeAnalysis>();
return PA;
}
} // namespace llvm

1
llvm/test/Other/opt-O2-pipeline.ll
View File

@ -80,7 +80,6 @@
; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: PGOMemOPSize
; CHECK-NEXT: Dominator Tree Construction
; CHECK-NEXT: Basic Alias Analysis (stateless AA impl)
; CHECK-NEXT: Function Alias Analysis Results
; CHECK-NEXT: Natural Loop Information

1
llvm/test/Other/opt-O3-pipeline.ll
View File

@ -84,7 +84,6 @@
; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: PGOMemOPSize
; CHECK-NEXT: Dominator Tree Construction
; CHECK-NEXT: Basic Alias Analysis (stateless AA impl)
; CHECK-NEXT: Function Alias Analysis Results
; CHECK-NEXT: Natural Loop Information

2
llvm/test/Transforms/PGOProfile/memop_clone.ll
View File

@ -1,4 +1,4 @@
; RUN: opt < %s -pgo-memop-opt -S | FileCheck %s
; RUN: opt < %s -pgo-memop-opt -verify-dom-info -S | FileCheck %s
define i32 @test(i8* %a, i8* %b) !prof !1 {
; CHECK_LABEL: test

8
llvm/test/Transforms/PGOProfile/memop_size_opt.ll
View File

@ -1,8 +1,8 @@
; RUN: opt < %s -pgo-memop-opt -pgo-memop-count-threshold=90 -pgo-memop-percent-threshold=15 -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: opt < %s -passes=pgo-memop-opt -pgo-memop-count-threshold=90 -pgo-memop-percent-threshold=15 -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: opt < %s -pgo-memop-opt -pgo-memop-count-threshold=90 -pgo-memop-percent-threshold=15 -pass-remarks-with-hotness -pass-remarks-output=%t.opt.yaml -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: opt < %s -pgo-memop-opt -verify-dom-info -pgo-memop-count-threshold=90 -pgo-memop-percent-threshold=15 -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: opt < %s -passes=pgo-memop-opt -verify-dom-info -pgo-memop-count-threshold=90 -pgo-memop-percent-threshold=15 -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: opt < %s -pgo-memop-opt -verify-dom-info -pgo-memop-count-threshold=90 -pgo-memop-percent-threshold=15 -pass-remarks-with-hotness -pass-remarks-output=%t.opt.yaml -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: FileCheck %s -input-file=%t.opt.yaml --check-prefix=YAML
; RUN: opt < %s -passes=pgo-memop-opt -pgo-memop-count-threshold=90 -pgo-memop-percent-threshold=15 -pass-remarks-with-hotness -pass-remarks-output=%t.opt.yaml -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: opt < %s -passes=pgo-memop-opt -verify-dom-info -pgo-memop-count-threshold=90 -pgo-memop-percent-threshold=15 -pass-remarks-with-hotness -pass-remarks-output=%t.opt.yaml -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: FileCheck %s -input-file=%t.opt.yaml --check-prefix=YAML

4
llvm/test/Transforms/PGOProfile/memop_size_opt_zero.ll
View File

@ -1,7 +1,7 @@
; Test to ensure the pgo memop optimization pass doesn't try to scale
; up a value profile with a 0 count, which would lead to divide by 0.
; RUN: opt < %s -passes=pgo-memop-opt -pgo-memop-count-threshold=1 -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: opt < %s -pgo-memop-opt -pgo-memop-count-threshold=1 -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: opt < %s -passes=pgo-memop-opt -verify-dom-info -pgo-memop-count-threshold=1 -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: opt < %s -pgo-memop-opt -verify-dom-info -pgo-memop-count-threshold=1 -S | FileCheck %s --check-prefix=MEMOP_OPT
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"