[PGO][PGSO] SizeOpts changes.
Summary:
(Split of off D67120)
SizeOpts/MachineSizeOpts changes for profile guided size optimization.
Reviewers: davidxl
Subscribers: mgorny, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D69070
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@375254 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/include/llvm/CodeGen/MachineBlockFrequencyInfo.h b/include/llvm/CodeGen/MachineBlockFrequencyInfo.h
index a438ecf..2a826d0 100644
--- a/include/llvm/CodeGen/MachineBlockFrequencyInfo.h
+++ b/include/llvm/CodeGen/MachineBlockFrequencyInfo.h
@@ -38,6 +38,9 @@
static char ID;
MachineBlockFrequencyInfo();
+ explicit MachineBlockFrequencyInfo(MachineFunction &F,
+ MachineBranchProbabilityInfo &MBPI,
+ MachineLoopInfo &MLI);
~MachineBlockFrequencyInfo() override;
void getAnalysisUsage(AnalysisUsage &AU) const override;
diff --git a/include/llvm/CodeGen/MachineDominators.h b/include/llvm/CodeGen/MachineDominators.h
index e4d7a02..9d31232 100644
--- a/include/llvm/CodeGen/MachineDominators.h
+++ b/include/llvm/CodeGen/MachineDominators.h
@@ -81,6 +81,9 @@
static char ID; // Pass ID, replacement for typeid
MachineDominatorTree();
+ explicit MachineDominatorTree(MachineFunction &MF) : MachineFunctionPass(ID) {
+ calculate(MF);
+ }
DomTreeT &getBase() {
if (!DT) DT.reset(new DomTreeT());
@@ -111,6 +114,8 @@
bool runOnMachineFunction(MachineFunction &F) override;
+ void calculate(MachineFunction &F);
+
bool dominates(const MachineDomTreeNode *A,
const MachineDomTreeNode *B) const {
applySplitCriticalEdges();
diff --git a/include/llvm/CodeGen/MachineLoopInfo.h b/include/llvm/CodeGen/MachineLoopInfo.h
index da6df59..1612c8b 100644
--- a/include/llvm/CodeGen/MachineLoopInfo.h
+++ b/include/llvm/CodeGen/MachineLoopInfo.h
@@ -37,6 +37,7 @@
namespace llvm {
+class MachineDominatorTree;
// Implementation in LoopInfoImpl.h
class MachineLoop;
extern template class LoopBase<MachineBasicBlock, MachineLoop>;
@@ -91,6 +92,10 @@
MachineLoopInfo() : MachineFunctionPass(ID) {
initializeMachineLoopInfoPass(*PassRegistry::getPassRegistry());
}
+ explicit MachineLoopInfo(MachineDominatorTree &MDT)
+ : MachineFunctionPass(ID) {
+ calculate(MDT);
+ }
MachineLoopInfo(const MachineLoopInfo &) = delete;
MachineLoopInfo &operator=(const MachineLoopInfo &) = delete;
@@ -133,6 +138,7 @@
/// Calculate the natural loop information.
bool runOnMachineFunction(MachineFunction &F) override;
+ void calculate(MachineDominatorTree &MDT);
void releaseMemory() override { LI.releaseMemory(); }
diff --git a/include/llvm/CodeGen/MachineSizeOpts.h b/include/llvm/CodeGen/MachineSizeOpts.h
new file mode 100644
index 0000000..75e871d
--- /dev/null
+++ b/include/llvm/CodeGen/MachineSizeOpts.h
@@ -0,0 +1,37 @@
+//===- MachineSizeOpts.h - machine size optimization ------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains some shared machine IR code size optimization related
+// code.
+//
+//===----------------------------------------------------------------------===//
+#ifndef LLVM_CODEGEN_MACHINE_SIZEOPTS_H
+#define LLVM_CODEGEN_MACHINE_SIZEOPTS_H
+
+#include "llvm/Transforms/Utils/SizeOpts.h"
+
+namespace llvm {
+
+class ProfileSummaryInfo;
+class MachineBasicBlock;
+class MachineBlockFrequencyInfo;
+class MachineFunction;
+
+/// Returns true if machine function \p MF is suggested to be size-optimized
+/// base on the profile.
+bool shouldOptimizeForSize(const MachineFunction *MF, ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo *BFI);
+/// Returns true if machine basic block \p MBB is suggested to be size-optimized
+/// base on the profile.
+bool shouldOptimizeForSize(const MachineBasicBlock *MBB,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo *MBFI);
+
+} // end namespace llvm
+
+#endif // LLVM_CODEGEN_MACHINE_SIZEOPTS_H
diff --git a/include/llvm/Transforms/Utils/SizeOpts.h b/include/llvm/Transforms/Utils/SizeOpts.h
index 1a052c6..1c56da0 100644
--- a/include/llvm/Transforms/Utils/SizeOpts.h
+++ b/include/llvm/Transforms/Utils/SizeOpts.h
@@ -13,6 +13,18 @@
#ifndef LLVM_TRANSFORMS_UTILS_SIZEOPTS_H
#define LLVM_TRANSFORMS_UTILS_SIZEOPTS_H
+#include "llvm/Analysis/BlockFrequencyInfo.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/Support/CommandLine.h"
+
+using namespace llvm;
+
+extern cl::opt<bool> EnablePGSO;
+extern cl::opt<bool> PGSOLargeWorkingSetSizeOnly;
+extern cl::opt<bool> ForcePGSO;
+extern cl::opt<int> PgsoCutoffInstrProf;
+extern cl::opt<int> PgsoCutoffSampleProf;
+
namespace llvm {
class BasicBlock;
@@ -20,13 +32,52 @@
class Function;
class ProfileSummaryInfo;
+template<typename AdapterT, typename FuncT, typename BFIT>
+bool shouldFuncOptimizeForSizeImpl(const FuncT *F, ProfileSummaryInfo *PSI,
+ BFIT *BFI) {
+ assert(F);
+ if (!PSI || !BFI || !PSI->hasProfileSummary())
+ return false;
+ if (ForcePGSO)
+ return true;
+ if (!EnablePGSO)
+ return false;
+ if (PGSOLargeWorkingSetSizeOnly && !PSI->hasLargeWorkingSetSize()) {
+ // Even if the working set size isn't large, size-optimize cold code.
+ return AdapterT::isFunctionColdInCallGraph(F, PSI, *BFI);
+ }
+ return !AdapterT::isFunctionHotInCallGraphNthPercentile(
+ PSI->hasSampleProfile() ? PgsoCutoffSampleProf : PgsoCutoffInstrProf,
+ F, PSI, *BFI);
+}
+
+template<typename AdapterT, typename BlockT, typename BFIT>
+bool shouldOptimizeForSizeImpl(const BlockT *BB, ProfileSummaryInfo *PSI,
+ BFIT *BFI) {
+ assert(BB);
+ if (!PSI || !BFI || !PSI->hasProfileSummary())
+ return false;
+ if (ForcePGSO)
+ return true;
+ if (!EnablePGSO)
+ return false;
+ if (PGSOLargeWorkingSetSizeOnly && !PSI->hasLargeWorkingSetSize()) {
+ // Even if the working set size isn't large, size-optimize cold code.
+ return AdapterT::isColdBlock(BB, PSI, BFI);
+ }
+ return !AdapterT::isHotBlockNthPercentile(
+ PSI->hasSampleProfile() ? PgsoCutoffSampleProf : PgsoCutoffInstrProf,
+ BB, PSI, BFI);
+}
+
/// Returns true if function \p F is suggested to be size-optimized base on the
/// profile.
-bool shouldOptimizeForSize(Function *F, ProfileSummaryInfo *PSI,
+bool shouldOptimizeForSize(const Function *F, ProfileSummaryInfo *PSI,
BlockFrequencyInfo *BFI);
+
/// Returns true if basic block \p BB is suggested to be size-optimized base
/// on the profile.
-bool shouldOptimizeForSize(BasicBlock *BB, ProfileSummaryInfo *PSI,
+bool shouldOptimizeForSize(const BasicBlock *BB, ProfileSummaryInfo *PSI,
BlockFrequencyInfo *BFI);
} // end namespace llvm
diff --git a/lib/CodeGen/CMakeLists.txt b/lib/CodeGen/CMakeLists.txt
index 50b469d..f5c18f8 100644
--- a/lib/CodeGen/CMakeLists.txt
+++ b/lib/CodeGen/CMakeLists.txt
@@ -92,6 +92,7 @@
MachineRegisterInfo.cpp
MachineScheduler.cpp
MachineSink.cpp
+ MachineSizeOpts.cpp
MachineSSAUpdater.cpp
MachineTraceMetrics.cpp
MachineVerifier.cpp
diff --git a/lib/CodeGen/MachineBlockFrequencyInfo.cpp b/lib/CodeGen/MachineBlockFrequencyInfo.cpp
index 53a35b7..889fde6 100644
--- a/lib/CodeGen/MachineBlockFrequencyInfo.cpp
+++ b/lib/CodeGen/MachineBlockFrequencyInfo.cpp
@@ -172,6 +172,13 @@
initializeMachineBlockFrequencyInfoPass(*PassRegistry::getPassRegistry());
}
+MachineBlockFrequencyInfo::MachineBlockFrequencyInfo(
+ MachineFunction &F,
+ MachineBranchProbabilityInfo &MBPI,
+ MachineLoopInfo &MLI) : MachineFunctionPass(ID) {
+ calculate(F, MBPI, MLI);
+}
+
MachineBlockFrequencyInfo::~MachineBlockFrequencyInfo() = default;
void MachineBlockFrequencyInfo::getAnalysisUsage(AnalysisUsage &AU) const {
diff --git a/lib/CodeGen/MachineDominators.cpp b/lib/CodeGen/MachineDominators.cpp
index 706c706..0d57bca 100644
--- a/lib/CodeGen/MachineDominators.cpp
+++ b/lib/CodeGen/MachineDominators.cpp
@@ -49,11 +49,15 @@
}
bool MachineDominatorTree::runOnMachineFunction(MachineFunction &F) {
+ calculate(F);
+ return false;
+}
+
+void MachineDominatorTree::calculate(MachineFunction &F) {
CriticalEdgesToSplit.clear();
NewBBs.clear();
DT.reset(new DomTreeBase<MachineBasicBlock>());
DT->recalculate(F);
- return false;
}
MachineDominatorTree::MachineDominatorTree()
diff --git a/lib/CodeGen/MachineLoopInfo.cpp b/lib/CodeGen/MachineLoopInfo.cpp
index 3b8b430..85822a6 100644
--- a/lib/CodeGen/MachineLoopInfo.cpp
+++ b/lib/CodeGen/MachineLoopInfo.cpp
@@ -36,11 +36,15 @@
char &llvm::MachineLoopInfoID = MachineLoopInfo::ID;
bool MachineLoopInfo::runOnMachineFunction(MachineFunction &) {
- releaseMemory();
- LI.analyze(getAnalysis<MachineDominatorTree>().getBase());
+ calculate(getAnalysis<MachineDominatorTree>());
return false;
}
+void MachineLoopInfo::calculate(MachineDominatorTree &MDT) {
+ releaseMemory();
+ LI.analyze(MDT.getBase());
+}
+
void MachineLoopInfo::getAnalysisUsage(AnalysisUsage &AU) const {
AU.setPreservesAll();
AU.addRequired<MachineDominatorTree>();
diff --git a/lib/CodeGen/MachineSizeOpts.cpp b/lib/CodeGen/MachineSizeOpts.cpp
new file mode 100644
index 0000000..0c2ef33
--- /dev/null
+++ b/lib/CodeGen/MachineSizeOpts.cpp
@@ -0,0 +1,120 @@
+//===- MachineSizeOpts.cpp - code size optimization related code ----------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains some shared machine IR code size optimization related
+// code.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/CodeGen/MachineSizeOpts.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
+
+using namespace llvm;
+
+extern cl::opt<bool> EnablePGSO;
+extern cl::opt<bool> PGSOLargeWorkingSetSizeOnly;
+extern cl::opt<bool> ForcePGSO;
+extern cl::opt<int> PgsoCutoffInstrProf;
+extern cl::opt<int> PgsoCutoffSampleProf;
+
+namespace machine_size_opts_detail {
+
+/// Like ProfileSummaryInfo::isColdBlock but for MachineBasicBlock.
+bool isColdBlock(const MachineBasicBlock *MBB,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo *MBFI) {
+ auto Count = MBFI->getBlockProfileCount(MBB);
+ return Count && PSI->isColdCount(*Count);
+}
+
+/// Like ProfileSummaryInfo::isHotBlockNthPercentile but for MachineBasicBlock.
+static bool isHotBlockNthPercentile(int PercentileCutoff,
+ const MachineBasicBlock *MBB,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo *MBFI) {
+ auto Count = MBFI->getBlockProfileCount(MBB);
+ return Count && PSI->isHotCountNthPercentile(PercentileCutoff, *Count);
+}
+
+/// Like ProfileSummaryInfo::isFunctionColdInCallGraph but for
+/// MachineFunction.
+bool isFunctionColdInCallGraph(
+ const MachineFunction *MF,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo &MBFI) {
+ if (auto FunctionCount = MF->getFunction().getEntryCount())
+ if (!PSI->isColdCount(FunctionCount.getCount()))
+ return false;
+ for (const auto &MBB : *MF)
+ if (!isColdBlock(&MBB, PSI, &MBFI))
+ return false;
+ return true;
+}
+
+/// Like ProfileSummaryInfo::isFunctionHotInCallGraphNthPercentile but for
+/// MachineFunction.
+bool isFunctionHotInCallGraphNthPercentile(
+ int PercentileCutoff,
+ const MachineFunction *MF,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo &MBFI) {
+ if (auto FunctionCount = MF->getFunction().getEntryCount())
+ if (PSI->isHotCountNthPercentile(PercentileCutoff,
+ FunctionCount.getCount()))
+ return true;
+ for (const auto &MBB : *MF)
+ if (isHotBlockNthPercentile(PercentileCutoff, &MBB, PSI, &MBFI))
+ return true;
+ return false;
+}
+} // namespace machine_size_opts_detail
+
+namespace {
+struct MachineBasicBlockBFIAdapter {
+ static bool isFunctionColdInCallGraph(const MachineFunction *MF,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo &MBFI) {
+ return machine_size_opts_detail::isFunctionColdInCallGraph(MF, PSI, MBFI);
+ }
+ static bool isFunctionHotInCallGraphNthPercentile(
+ int CutOff,
+ const MachineFunction *MF,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo &MBFI) {
+ return machine_size_opts_detail::isFunctionHotInCallGraphNthPercentile(
+ CutOff, MF, PSI, MBFI);
+ }
+ static bool isColdBlock(const MachineBasicBlock *MBB,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo *MBFI) {
+ return machine_size_opts_detail::isColdBlock(MBB, PSI, MBFI);
+ }
+ static bool isHotBlockNthPercentile(int CutOff,
+ const MachineBasicBlock *MBB,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo *MBFI) {
+ return machine_size_opts_detail::isHotBlockNthPercentile(
+ CutOff, MBB, PSI, MBFI);
+ }
+};
+} // end anonymous namespace
+
+bool llvm::shouldOptimizeForSize(const MachineFunction *MF,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo *MBFI) {
+ return shouldFuncOptimizeForSizeImpl<MachineBasicBlockBFIAdapter>(
+ MF, PSI, MBFI);
+}
+
+bool llvm::shouldOptimizeForSize(const MachineBasicBlock *MBB,
+ ProfileSummaryInfo *PSI,
+ const MachineBlockFrequencyInfo *MBFI) {
+ return shouldOptimizeForSizeImpl<MachineBasicBlockBFIAdapter>(
+ MBB, PSI, MBFI);
+}
diff --git a/lib/Transforms/Utils/SizeOpts.cpp b/lib/Transforms/Utils/SizeOpts.cpp
index 1519751..f819c67 100644
--- a/lib/Transforms/Utils/SizeOpts.cpp
+++ b/lib/Transforms/Utils/SizeOpts.cpp
@@ -10,28 +10,66 @@
//
//===----------------------------------------------------------------------===//
-#include "llvm/Analysis/BlockFrequencyInfo.h"
-#include "llvm/Analysis/ProfileSummaryInfo.h"
-#include "llvm/Support/CommandLine.h"
#include "llvm/Transforms/Utils/SizeOpts.h"
+
using namespace llvm;
-static cl::opt<bool> ProfileGuidedSizeOpt(
+cl::opt<bool> EnablePGSO(
"pgso", cl::Hidden, cl::init(true),
- cl::desc("Enable the profile guided size optimization. "));
+ cl::desc("Enable the profile guided size optimizations. "));
-bool llvm::shouldOptimizeForSize(Function *F, ProfileSummaryInfo *PSI,
+cl::opt<bool> PGSOLargeWorkingSetSizeOnly(
+ "pgso-lwss-only", cl::Hidden, cl::init(true),
+ cl::desc("Apply the profile guided size optimizations only "
+ "if the working set size is large (except for cold code.)"));
+
+cl::opt<bool> ForcePGSO(
+ "force-pgso", cl::Hidden, cl::init(false),
+ cl::desc("Force the (profiled-guided) size optimizations. "));
+
+cl::opt<int> PgsoCutoffInstrProf(
+ "pgso-cutoff-instr-prof", cl::Hidden, cl::init(250000), cl::ZeroOrMore,
+ cl::desc("The profile guided size optimization profile summary cutoff "
+ "for instrumentation profile."));
+
+cl::opt<int> PgsoCutoffSampleProf(
+ "pgso-cutoff-sample-prof", cl::Hidden, cl::init(800000), cl::ZeroOrMore,
+ cl::desc("The profile guided size optimization profile summary cutoff "
+ "for sample profile."));
+
+namespace {
+struct BasicBlockBFIAdapter {
+ static bool isFunctionColdInCallGraph(const Function *F,
+ ProfileSummaryInfo *PSI,
+ BlockFrequencyInfo &BFI) {
+ return PSI->isFunctionColdInCallGraph(F, BFI);
+ }
+ static bool isFunctionHotInCallGraphNthPercentile(int CutOff,
+ const Function *F,
+ ProfileSummaryInfo *PSI,
+ BlockFrequencyInfo &BFI) {
+ return PSI->isFunctionHotInCallGraphNthPercentile(CutOff, F, BFI);
+ }
+ static bool isColdBlock(const BasicBlock *BB,
+ ProfileSummaryInfo *PSI,
+ BlockFrequencyInfo *BFI) {
+ return PSI->isColdBlock(BB, BFI);
+ }
+ static bool isHotBlockNthPercentile(int CutOff,
+ const BasicBlock *BB,
+ ProfileSummaryInfo *PSI,
+ BlockFrequencyInfo *BFI) {
+ return PSI->isHotBlockNthPercentile(CutOff, BB, BFI);
+ }
+};
+} // end anonymous namespace
+
+bool llvm::shouldOptimizeForSize(const Function *F, ProfileSummaryInfo *PSI,
BlockFrequencyInfo *BFI) {
- assert(F);
- if (!PSI || !BFI || !PSI->hasProfileSummary())
- return false;
- return ProfileGuidedSizeOpt && PSI->isFunctionColdInCallGraph(F, *BFI);
+ return shouldFuncOptimizeForSizeImpl<BasicBlockBFIAdapter>(F, PSI, BFI);
}
-bool llvm::shouldOptimizeForSize(BasicBlock *BB, ProfileSummaryInfo *PSI,
+bool llvm::shouldOptimizeForSize(const BasicBlock *BB, ProfileSummaryInfo *PSI,
BlockFrequencyInfo *BFI) {
- assert(BB);
- if (!PSI || !BFI || !PSI->hasProfileSummary())
- return false;
- return ProfileGuidedSizeOpt && PSI->isColdBlock(BB, BFI);
+ return shouldOptimizeForSizeImpl<BasicBlockBFIAdapter>(BB, PSI, BFI);
}
diff --git a/unittests/CodeGen/CMakeLists.txt b/unittests/CodeGen/CMakeLists.txt
index 706a65b..1553641 100644
--- a/unittests/CodeGen/CMakeLists.txt
+++ b/unittests/CodeGen/CMakeLists.txt
@@ -18,6 +18,7 @@
MachineInstrBundleIteratorTest.cpp
MachineInstrTest.cpp
MachineOperandTest.cpp
+ MachineSizeOptsTest.cpp
ScalableVectorMVTsTest.cpp
TypeTraitsTest.cpp
TargetOptionsTest.cpp
diff --git a/unittests/CodeGen/MachineSizeOptsTest.cpp b/unittests/CodeGen/MachineSizeOptsTest.cpp
new file mode 100644
index 0000000..f8b0c23
--- /dev/null
+++ b/unittests/CodeGen/MachineSizeOptsTest.cpp
@@ -0,0 +1,234 @@
+//===- MachineSizeOptsTest.cpp --------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/CodeGen/MachineSizeOpts.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/Analysis/BlockFrequencyInfo.h"
+#include "llvm/Analysis/BranchProbabilityInfo.h"
+#include "llvm/Analysis/LoopInfo.h"
+#include "llvm/CodeGen/MIRParser/MIRParser.h"
+#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
+#include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
+#include "llvm/CodeGen/MachineDominators.h"
+#include "llvm/CodeGen/MachineLoopInfo.h"
+#include "llvm/CodeGen/MachineModuleInfo.h"
+#include "llvm/Support/TargetRegistry.h"
+#include "llvm/Support/TargetSelect.h"
+#include "llvm/Target/TargetMachine.h"
+#include "gtest/gtest.h"
+
+using namespace llvm;
+
+namespace {
+
+std::unique_ptr<LLVMTargetMachine> createTargetMachine() {
+ auto TT(Triple::normalize("x86_64--"));
+ std::string Error;
+ const Target *TheTarget = TargetRegistry::lookupTarget(TT, Error);
+ return std::unique_ptr<LLVMTargetMachine>(static_cast<LLVMTargetMachine*>(
+ TheTarget->createTargetMachine(TT, "", "", TargetOptions(), None, None,
+ CodeGenOpt::Default)));
+}
+
+class MachineSizeOptsTest : public testing::Test {
+ protected:
+ static const char* MIRString;
+ LLVMContext Context;
+ std::unique_ptr<LLVMTargetMachine> TM;
+ std::unique_ptr<MachineModuleInfo> MMI;
+ std::unique_ptr<MIRParser> Parser;
+ std::unique_ptr<Module> M;
+ struct BFIData {
+ std::unique_ptr<MachineDominatorTree> MDT;
+ std::unique_ptr<MachineLoopInfo> MLI;
+ std::unique_ptr<MachineBranchProbabilityInfo> MBPI;
+ std::unique_ptr<MachineBlockFrequencyInfo> MBFI;
+ BFIData(MachineFunction &MF) {
+ MDT.reset(new MachineDominatorTree(MF));
+ MLI.reset(new MachineLoopInfo(*MDT));
+ MBPI.reset(new MachineBranchProbabilityInfo());
+ MBFI.reset(new MachineBlockFrequencyInfo(MF, *MBPI, *MLI));
+ }
+ MachineBlockFrequencyInfo *get() { return MBFI.get(); }
+ };
+
+ static void SetUpTestCase() {
+ InitializeAllTargets();
+ InitializeAllTargetMCs();
+ }
+
+ void SetUp() override {
+ TM = createTargetMachine();
+ std::unique_ptr<MemoryBuffer> MBuffer =
+ MemoryBuffer::getMemBuffer(MIRString);
+ Parser = createMIRParser(std::move(MBuffer), Context);
+ if (!Parser)
+ report_fatal_error("null MIRParser");
+ M = Parser->parseIRModule();
+ if (!M)
+ report_fatal_error("parseIRModule failed");
+ M->setTargetTriple(TM->getTargetTriple().getTriple());
+ M->setDataLayout(TM->createDataLayout());
+ MMI = std::make_unique<MachineModuleInfo>(TM.get());
+ if (Parser->parseMachineFunctions(*M, *MMI.get()))
+ report_fatal_error("parseMachineFunctions failed");
+ }
+
+ MachineFunction *getMachineFunction(Module *M, StringRef Name) {
+ auto F = M->getFunction(Name);
+ if (!F)
+ report_fatal_error("null Function");
+ auto &MF = MMI->getOrCreateMachineFunction(*F);
+ return &MF;
+ }
+};
+
+TEST_F(MachineSizeOptsTest, Test) {
+ MachineFunction *F = getMachineFunction(M.get(), "f");
+ ASSERT_TRUE(F != nullptr);
+ MachineFunction *G = getMachineFunction(M.get(), "g");
+ ASSERT_TRUE(G != nullptr);
+ MachineFunction *H = getMachineFunction(M.get(), "h");
+ ASSERT_TRUE(H != nullptr);
+ ProfileSummaryInfo PSI = ProfileSummaryInfo(*M.get());
+ ASSERT_TRUE(PSI.hasProfileSummary());
+ BFIData BFID_F(*F);
+ BFIData BFID_G(*G);
+ BFIData BFID_H(*H);
+ MachineBlockFrequencyInfo *MBFI_F = BFID_F.get();
+ MachineBlockFrequencyInfo *MBFI_G = BFID_G.get();
+ MachineBlockFrequencyInfo *MBFI_H = BFID_H.get();
+ MachineBasicBlock &BB0 = F->front();
+ auto iter = BB0.succ_begin();
+ MachineBasicBlock *BB1 = *iter;
+ iter++;
+ MachineBasicBlock *BB2 = *iter;
+ iter++;
+ ASSERT_TRUE(iter == BB0.succ_end());
+ MachineBasicBlock *BB3 = *BB1->succ_begin();
+ ASSERT_TRUE(BB3 == *BB2->succ_begin());
+ EXPECT_FALSE(shouldOptimizeForSize(F, &PSI, MBFI_F));
+ EXPECT_TRUE(shouldOptimizeForSize(G, &PSI, MBFI_G));
+ EXPECT_FALSE(shouldOptimizeForSize(H, &PSI, MBFI_H));
+ EXPECT_FALSE(shouldOptimizeForSize(&BB0, &PSI, MBFI_F));
+ EXPECT_FALSE(shouldOptimizeForSize(BB1, &PSI, MBFI_F));
+ EXPECT_TRUE(shouldOptimizeForSize(BB2, &PSI, MBFI_F));
+ EXPECT_FALSE(shouldOptimizeForSize(BB3, &PSI, MBFI_F));
+}
+
+const char* MachineSizeOptsTest::MIRString = R"MIR(
+--- |
+ define i32 @g(i32 %x) !prof !14 {
+ ret i32 0
+ }
+
+ define i32 @h(i32 %x) !prof !15 {
+ ret i32 0
+ }
+
+ define i32 @f(i32 %x) !prof !16 {
+ bb0:
+ %y1 = icmp eq i32 %x, 0
+ br i1 %y1, label %bb1, label %bb2, !prof !17
+
+ bb1: ; preds = %bb0
+ %z1 = call i32 @g(i32 %x)
+ br label %bb3
+
+ bb2: ; preds = %bb0
+ %z2 = call i32 @h(i32 %x)
+ br label %bb3
+
+ bb3: ; preds = %bb2, %bb1
+ %y2 = phi i32 [ 0, %bb1 ], [ 1, %bb2 ]
+ ret i32 %y2
+ }
+
+ !llvm.module.flags = !{!0}
+
+ !0 = !{i32 1, !"ProfileSummary", !1}
+ !1 = !{!2, !3, !4, !5, !6, !7, !8, !9}
+ !2 = !{!"ProfileFormat", !"InstrProf"}
+ !3 = !{!"TotalCount", i64 10000}
+ !4 = !{!"MaxCount", i64 10}
+ !5 = !{!"MaxInternalCount", i64 1}
+ !6 = !{!"MaxFunctionCount", i64 1000}
+ !7 = !{!"NumCounts", i64 3}
+ !8 = !{!"NumFunctions", i64 3}
+ !9 = !{!"DetailedSummary", !10}
+ !10 = !{!11, !12, !13}
+ !11 = !{i32 10000, i64 1000, i32 1}
+ !12 = !{i32 999000, i64 300, i32 3}
+ !13 = !{i32 999999, i64 5, i32 10}
+ !14 = !{!"function_entry_count", i64 1}
+ !15 = !{!"function_entry_count", i64 100}
+ !16 = !{!"function_entry_count", i64 400}
+ !17 = !{!"branch_weights", i32 100, i32 1}
+
+...
+---
+name: g
+body: |
+ bb.0:
+ %1:gr32 = MOV32r0 implicit-def dead $eflags
+ $eax = COPY %1
+ RET 0, $eax
+
+...
+---
+name: h
+body: |
+ bb.0:
+ %1:gr32 = MOV32r0 implicit-def dead $eflags
+ $eax = COPY %1
+ RET 0, $eax
+
+...
+---
+name: f
+tracksRegLiveness: true
+body: |
+ bb.0:
+ successors: %bb.1(0x7ebb907a), %bb.2(0x01446f86)
+ liveins: $edi
+
+ %1:gr32 = COPY $edi
+ TEST32rr %1, %1, implicit-def $eflags
+ JCC_1 %bb.2, 5, implicit $eflags
+ JMP_1 %bb.1
+
+ bb.1:
+ successors: %bb.3(0x80000000)
+
+ ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+ $edi = COPY %1
+ CALL64pcrel32 @g, csr_64, implicit $rsp, implicit $ssp, implicit $edi, implicit-def $rsp, implicit-def $ssp, implicit-def $eax
+ ADJCALLSTACKUP64 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+ %5:gr32 = COPY $eax
+ %4:gr32 = MOV32r0 implicit-def dead $eflags
+ JMP_1 %bb.3
+
+ bb.2:
+ successors: %bb.3(0x80000000)
+
+ ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+ $edi = COPY %1
+ CALL64pcrel32 @h, csr_64, implicit $rsp, implicit $ssp, implicit $edi, implicit-def $rsp, implicit-def $ssp, implicit-def $eax
+ ADJCALLSTACKUP64 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+ %3:gr32 = COPY $eax
+ %2:gr32 = MOV32ri 1
+
+ bb.3:
+ %0:gr32 = PHI %2, %bb.2, %4, %bb.1
+ $eax = COPY %0
+ RET 0, $eax
+
+...
+)MIR";
+
+} // anonymous namespace
diff --git a/unittests/Transforms/Utils/CMakeLists.txt b/unittests/Transforms/Utils/CMakeLists.txt
index 785b798..bc993a8 100644
--- a/unittests/Transforms/Utils/CMakeLists.txt
+++ b/unittests/Transforms/Utils/CMakeLists.txt
@@ -14,6 +14,7 @@
FunctionComparatorTest.cpp
IntegerDivisionTest.cpp
LocalTest.cpp
+ SizeOptsTest.cpp
SSAUpdaterBulkTest.cpp
UnrollLoopTest.cpp
ValueMapperTest.cpp
diff --git a/unittests/Transforms/Utils/SizeOptsTest.cpp b/unittests/Transforms/Utils/SizeOptsTest.cpp
new file mode 100644
index 0000000..55ca786
--- /dev/null
+++ b/unittests/Transforms/Utils/SizeOptsTest.cpp
@@ -0,0 +1,129 @@
+//===- SizeOptsTest.cpp - SizeOpts unit tests -----------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Transforms/Utils/SizeOpts.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/Analysis/BlockFrequencyInfo.h"
+#include "llvm/Analysis/BranchProbabilityInfo.h"
+#include "llvm/Analysis/LoopInfo.h"
+#include "llvm/AsmParser/Parser.h"
+#include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/Dominators.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/Module.h"
+#include "llvm/Support/FormatVariadic.h"
+#include "llvm/Support/SourceMgr.h"
+#include "gtest/gtest.h"
+
+using namespace llvm;
+
+namespace {
+
+class SizeOptsTest : public testing::Test {
+protected:
+ static const char* IRString;
+ LLVMContext C;
+ std::unique_ptr<Module> M;
+ struct BFIData {
+ std::unique_ptr<DominatorTree> DT;
+ std::unique_ptr<LoopInfo> LI;
+ std::unique_ptr<BranchProbabilityInfo> BPI;
+ std::unique_ptr<BlockFrequencyInfo> BFI;
+ BFIData(Function &F) {
+ DT.reset(new DominatorTree(F));
+ LI.reset(new LoopInfo(*DT));
+ BPI.reset(new BranchProbabilityInfo(F, *LI));
+ BFI.reset(new BlockFrequencyInfo(F, *BPI, *LI));
+ }
+ BlockFrequencyInfo *get() { return BFI.get(); }
+ };
+
+ void SetUp() override {
+ SMDiagnostic Err;
+ M = parseAssemblyString(IRString, Err, C);
+ }
+};
+
+TEST_F(SizeOptsTest, Test) {
+ Function *F = M->getFunction("f");
+ Function *G = M->getFunction("g");
+ Function *H = M->getFunction("h");
+
+ ProfileSummaryInfo PSI(*M.get());
+ BFIData BFID_F(*F);
+ BFIData BFID_G(*G);
+ BFIData BFID_H(*H);
+ BlockFrequencyInfo *BFI_F = BFID_F.get();
+ BlockFrequencyInfo *BFI_G = BFID_G.get();
+ BlockFrequencyInfo *BFI_H = BFID_H.get();
+ BasicBlock &BB0 = F->getEntryBlock();
+ BasicBlock *BB1 = BB0.getTerminator()->getSuccessor(0);
+ BasicBlock *BB2 = BB0.getTerminator()->getSuccessor(1);
+ BasicBlock *BB3 = BB1->getSingleSuccessor();
+
+ EXPECT_TRUE(PSI.hasProfileSummary());
+ EXPECT_FALSE(shouldOptimizeForSize(F, &PSI, BFI_F));
+ EXPECT_TRUE(shouldOptimizeForSize(G, &PSI, BFI_G));
+ EXPECT_FALSE(shouldOptimizeForSize(H, &PSI, BFI_H));
+ EXPECT_FALSE(shouldOptimizeForSize(&BB0, &PSI, BFI_F));
+ EXPECT_FALSE(shouldOptimizeForSize(BB1, &PSI, BFI_F));
+ EXPECT_TRUE(shouldOptimizeForSize(BB2, &PSI, BFI_F));
+ EXPECT_FALSE(shouldOptimizeForSize(BB3, &PSI, BFI_F));
+}
+
+const char* SizeOptsTest::IRString = R"IR(
+ define i32 @g(i32 %x) !prof !14 {
+ ret i32 0
+ }
+
+ define i32 @h(i32 %x) !prof !15 {
+ ret i32 0
+ }
+
+ define i32 @f(i32 %x) !prof !16 {
+ bb0:
+ %y1 = icmp eq i32 %x, 0
+ br i1 %y1, label %bb1, label %bb2, !prof !17
+
+ bb1: ; preds = %bb0
+ %z1 = call i32 @g(i32 %x)
+ br label %bb3
+
+ bb2: ; preds = %bb0
+ %z2 = call i32 @h(i32 %x)
+ br label %bb3
+
+ bb3: ; preds = %bb2, %bb1
+ %y2 = phi i32 [ 0, %bb1 ], [ 1, %bb2 ]
+ ret i32 %y2
+ }
+
+ !llvm.module.flags = !{!0}
+
+ !0 = !{i32 1, !"ProfileSummary", !1}
+ !1 = !{!2, !3, !4, !5, !6, !7, !8, !9}
+ !2 = !{!"ProfileFormat", !"InstrProf"}
+ !3 = !{!"TotalCount", i64 10000}
+ !4 = !{!"MaxCount", i64 10}
+ !5 = !{!"MaxInternalCount", i64 1}
+ !6 = !{!"MaxFunctionCount", i64 1000}
+ !7 = !{!"NumCounts", i64 3}
+ !8 = !{!"NumFunctions", i64 3}
+ !9 = !{!"DetailedSummary", !10}
+ !10 = !{!11, !12, !13}
+ !11 = !{i32 10000, i64 1000, i32 1}
+ !12 = !{i32 999000, i64 300, i32 3}
+ !13 = !{i32 999999, i64 5, i32 10}
+ !14 = !{!"function_entry_count", i64 1}
+ !15 = !{!"function_entry_count", i64 100}
+ !16 = !{!"function_entry_count", i64 400}
+ !17 = !{!"branch_weights", i32 100, i32 1}
+)IR";
+
+} // end anonymous namespace
