zequanwu updated this revision to Diff 275558.
zequanwu added a comment.
Enable CGProfilePass for opt with LPM by default, like opt with NPM.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D83013/new/
https://reviews.llvm.org/D83013
Files:
clang/lib/CodeGen/BackendUtil.cpp
llvm/include/llvm/InitializePasses.h
llvm/include/llvm/Transforms/IPO.h
llvm/include/llvm/Transforms/IPO/PassManagerBuilder.h
llvm/include/llvm/Transforms/Instrumentation/CGProfile.h
llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
llvm/lib/Transforms/Instrumentation/CGProfile.cpp
llvm/lib/Transforms/Instrumentation/Instrumentation.cpp
llvm/test/CodeGen/AMDGPU/opt-pipeline.ll
llvm/test/Instrumentation/cgprofile.ll
llvm/test/Other/opt-O2-pipeline.ll
llvm/test/Other/opt-O3-pipeline.ll
llvm/test/Other/opt-Os-pipeline.ll
llvm/tools/opt/opt.cpp
Index: llvm/tools/opt/opt.cpp
===================================================================
--- llvm/tools/opt/opt.cpp
+++ llvm/tools/opt/opt.cpp
@@ -278,6 +278,10 @@
cl::desc("Specify time trace file destination"),
cl::value_desc("filename"));
+static cl::opt<bool> EnableCallGraphProfile(
+ "enable-call-graph-profile", cl::init(true), cl::Hidden,
+ cl::desc("Enable call graph profile pass (default = on)"));
+
static cl::opt<bool> RemarksWithHotness(
"pass-remarks-with-hotness",
cl::desc("With PGO, include profile count in optimization remarks"),
@@ -414,6 +418,8 @@
Builder.SLPVectorize = OptLevel > 1 && SizeLevel < 2;
+ Builder.CallGraphProfile = EnableCallGraphProfile;
+
if (TM)
TM->adjustPassManager(Builder);
Index: llvm/test/Other/opt-Os-pipeline.ll
===================================================================
--- llvm/test/Other/opt-Os-pipeline.ll
+++ llvm/test/Other/opt-Os-pipeline.ll
@@ -266,6 +266,13 @@
; CHECK-NEXT: Strip Unused Function Prototypes
; CHECK-NEXT: Dead Global Elimination
; CHECK-NEXT: Merge Duplicate Global Constants
+; CHECK-NEXT: Call Graph Profile
+; CHECK-NEXT: FunctionPass Manager
+; CHECK-NEXT: Dominator Tree Construction
+; CHECK-NEXT: Natural Loop Information
+; CHECK-NEXT: Post-Dominator Tree Construction
+; CHECK-NEXT: Branch Probability Analysis
+; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Dominator Tree Construction
; CHECK-NEXT: Natural Loop Information
Index: llvm/test/Other/opt-O3-pipeline.ll
===================================================================
--- llvm/test/Other/opt-O3-pipeline.ll
+++ llvm/test/Other/opt-O3-pipeline.ll
@@ -285,6 +285,13 @@
; CHECK-NEXT: Strip Unused Function Prototypes
; CHECK-NEXT: Dead Global Elimination
; CHECK-NEXT: Merge Duplicate Global Constants
+; CHECK-NEXT: Call Graph Profile
+; CHECK-NEXT: FunctionPass Manager
+; CHECK-NEXT: Dominator Tree Construction
+; CHECK-NEXT: Natural Loop Information
+; CHECK-NEXT: Post-Dominator Tree Construction
+; CHECK-NEXT: Branch Probability Analysis
+; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Dominator Tree Construction
; CHECK-NEXT: Natural Loop Information
Index: llvm/test/Other/opt-O2-pipeline.ll
===================================================================
--- llvm/test/Other/opt-O2-pipeline.ll
+++ llvm/test/Other/opt-O2-pipeline.ll
@@ -280,6 +280,13 @@
; CHECK-NEXT: Strip Unused Function Prototypes
; CHECK-NEXT: Dead Global Elimination
; CHECK-NEXT: Merge Duplicate Global Constants
+; CHECK-NEXT: Call Graph Profile
+; CHECK-NEXT: FunctionPass Manager
+; CHECK-NEXT: Dominator Tree Construction
+; CHECK-NEXT: Natural Loop Information
+; CHECK-NEXT: Post-Dominator Tree Construction
+; CHECK-NEXT: Branch Probability Analysis
+; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Dominator Tree Construction
; CHECK-NEXT: Natural Loop Information
Index: llvm/test/Instrumentation/cgprofile.ll
===================================================================
--- llvm/test/Instrumentation/cgprofile.ll
+++ llvm/test/Instrumentation/cgprofile.ll
@@ -1,4 +1,5 @@
; RUN: opt < %s -passes cg-profile -S | FileCheck %s
+; RUN: opt < %s -cg-profile -S | FileCheck %s
declare void @b()
Index: llvm/test/CodeGen/AMDGPU/opt-pipeline.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/opt-pipeline.ll
+++ llvm/test/CodeGen/AMDGPU/opt-pipeline.ll
@@ -276,6 +276,13 @@
; GCN-O1-NEXT: Warn about non-applied transformations
; GCN-O1-NEXT: Alignment from assumptions
; GCN-O1-NEXT: Strip Unused Function Prototypes
+; GCN-O1-NEXT: Call Graph Profile
+; GCN-O1-NEXT: FunctionPass Manager
+; GCN-O1-NEXT: Dominator Tree Construction
+; GCN-O1-NEXT: Natural Loop Information
+; GCN-O1-NEXT: Post-Dominator Tree Construction
+; GCN-O1-NEXT: Branch Probability Analysis
+; GCN-O1-NEXT: Block Frequency Analysis
; GCN-O1-NEXT: FunctionPass Manager
; GCN-O1-NEXT: Dominator Tree Construction
; GCN-O1-NEXT: Natural Loop Information
@@ -623,6 +630,13 @@
; GCN-O2-NEXT: Strip Unused Function Prototypes
; GCN-O2-NEXT: Dead Global Elimination
; GCN-O2-NEXT: Merge Duplicate Global Constants
+; GCN-O2-NEXT: Call Graph Profile
+; GCN-O2-NEXT: FunctionPass Manager
+; GCN-O2-NEXT: Dominator Tree Construction
+; GCN-O2-NEXT: Natural Loop Information
+; GCN-O2-NEXT: Post-Dominator Tree Construction
+; GCN-O2-NEXT: Branch Probability Analysis
+; GCN-O2-NEXT: Block Frequency Analysis
; GCN-O2-NEXT: FunctionPass Manager
; GCN-O2-NEXT: Dominator Tree Construction
; GCN-O2-NEXT: Natural Loop Information
@@ -975,6 +989,13 @@
; GCN-O3-NEXT: Strip Unused Function Prototypes
; GCN-O3-NEXT: Dead Global Elimination
; GCN-O3-NEXT: Merge Duplicate Global Constants
+; GCN-O3-NEXT: Call Graph Profile
+; GCN-O3-NEXT: FunctionPass Manager
+; GCN-O3-NEXT: Dominator Tree Construction
+; GCN-O3-NEXT: Natural Loop Information
+; GCN-O3-NEXT: Post-Dominator Tree Construction
+; GCN-O3-NEXT: Branch Probability Analysis
+; GCN-O3-NEXT: Block Frequency Analysis
; GCN-O3-NEXT: FunctionPass Manager
; GCN-O3-NEXT: Dominator Tree Construction
; GCN-O3-NEXT: Natural Loop Information
Index: llvm/lib/Transforms/Instrumentation/Instrumentation.cpp
===================================================================
--- llvm/lib/Transforms/Instrumentation/Instrumentation.cpp
+++ llvm/lib/Transforms/Instrumentation/Instrumentation.cpp
@@ -112,6 +112,7 @@
initializePGOInstrumentationUseLegacyPassPass(Registry);
initializePGOIndirectCallPromotionLegacyPassPass(Registry);
initializePGOMemOPSizeOptLegacyPassPass(Registry);
+ initializeCGProfileLegacyPassPass(Registry);
initializeInstrOrderFileLegacyPassPass(Registry);
initializeInstrProfilingLegacyPassPass(Registry);
initializeMemorySanitizerLegacyPassPass(Registry);
Index: llvm/lib/Transforms/Instrumentation/CGProfile.cpp
===================================================================
--- llvm/lib/Transforms/Instrumentation/CGProfile.cpp
+++ llvm/lib/Transforms/Instrumentation/CGProfile.cpp
@@ -15,17 +15,42 @@
#include "llvm/IR/Instructions.h"
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/PassManager.h"
+#include "llvm/InitializePasses.h"
#include "llvm/ProfileData/InstrProf.h"
+#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/Instrumentation.h"
#include <array>
using namespace llvm;
-PreservedAnalyses CGProfilePass::run(Module &M, ModuleAnalysisManager &MAM) {
+static bool
+addModuleFlags(Module &M,
+ MapVector<std::pair<Function *, Function *>, uint64_t> &Counts) {
+ if (Counts.empty())
+ return false;
+
+ LLVMContext &Context = M.getContext();
+ MDBuilder MDB(Context);
+ std::vector<Metadata *> Nodes;
+
+ for (auto E : Counts) {
+ Metadata *Vals[] = {ValueAsMetadata::get(E.first.first),
+ ValueAsMetadata::get(E.first.second),
+ MDB.createConstant(ConstantInt::get(
+ Type::getInt64Ty(Context), E.second))};
+ Nodes.push_back(MDNode::get(Context, Vals));
+ }
+
+ M.addModuleFlag(Module::Append, "CG Profile", MDNode::get(Context, Nodes));
+ return true;
+}
+
+static bool
+runCGProfilePass(Module &M,
+ function_ref<BlockFrequencyInfo &(Function &)> GetBFI,
+ function_ref<TargetTransformInfo &(Function &)> GetTTI) {
MapVector<std::pair<Function *, Function *>, uint64_t> Counts;
- FunctionAnalysisManager &FAM =
- MAM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
InstrProfSymtab Symtab;
auto UpdateCounts = [&](TargetTransformInfo &TTI, Function *F,
Function *CalledF, uint64_t NewCount) {
@@ -35,14 +60,14 @@
Count = SaturatingAdd(Count, NewCount);
};
// Ignore error here. Indirect calls are ignored if this fails.
- (void)(bool)Symtab.create(M);
+ (void)(bool) Symtab.create(M);
for (auto &F : M) {
if (F.isDeclaration())
continue;
- auto &BFI = FAM.getResult<BlockFrequencyAnalysis>(F);
+ auto &BFI = GetBFI(F);
if (BFI.getEntryFreq() == 0)
continue;
- TargetTransformInfo &TTI = FAM.getResult<TargetIRAnalysis>(F);
+ TargetTransformInfo &TTI = GetTTI(F);
for (auto &BB : F) {
Optional<uint64_t> BBCount = BFI.getBlockProfileCount(&BB);
if (!BBCount)
@@ -69,28 +94,56 @@
}
}
- addModuleFlags(M, Counts);
-
- return PreservedAnalyses::all();
+ return addModuleFlags(M, Counts);
}
-void CGProfilePass::addModuleFlags(
- Module &M,
- MapVector<std::pair<Function *, Function *>, uint64_t> &Counts) const {
- if (Counts.empty())
- return;
+namespace {
+struct CGProfileLegacyPass final : public ModulePass {
+ static char ID;
+ CGProfileLegacyPass() : ModulePass(ID) {
+ initializeCGProfileLegacyPassPass(*PassRegistry::getPassRegistry());
+ }
- LLVMContext &Context = M.getContext();
- MDBuilder MDB(Context);
- std::vector<Metadata *> Nodes;
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
+ AU.setPreservesCFG();
+ AU.addRequired<BlockFrequencyInfoWrapperPass>();
+ AU.addRequired<TargetTransformInfoWrapperPass>();
+ }
- for (auto E : Counts) {
- Metadata *Vals[] = {ValueAsMetadata::get(E.first.first),
- ValueAsMetadata::get(E.first.second),
- MDB.createConstant(ConstantInt::get(
- Type::getInt64Ty(Context), E.second))};
- Nodes.push_back(MDNode::get(Context, Vals));
+ bool runOnModule(Module &M) override {
+ auto GetBFI = [this](Function &F) -> BlockFrequencyInfo & {
+ return this->getAnalysis<BlockFrequencyInfoWrapperPass>(F).getBFI();
+ };
+ auto GetTTI = [this](Function &F) -> TargetTransformInfo & {
+ return this->getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
+ };
+
+ return runCGProfilePass(M, GetBFI, GetTTI);
}
+};
- M.addModuleFlag(Module::Append, "CG Profile", MDNode::get(Context, Nodes));
+} // namespace
+
+char CGProfileLegacyPass::ID = 0;
+
+INITIALIZE_PASS(CGProfileLegacyPass, "cg-profile", "Call Graph Profile", false,
+ false)
+
+ModulePass *llvm::createCGProfileLegacyPass() {
+ return new CGProfileLegacyPass();
+}
+
+PreservedAnalyses CGProfilePass::run(Module &M, ModuleAnalysisManager &MAM) {
+ FunctionAnalysisManager &FAM =
+ MAM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
+ auto GetBFI = [&FAM](Function &F) -> BlockFrequencyInfo & {
+ return FAM.getResult<BlockFrequencyAnalysis>(F);
+ };
+ auto GetTTI = [&FAM](Function &F) -> TargetTransformInfo & {
+ return FAM.getResult<TargetIRAnalysis>(F);
+ };
+
+ runCGProfilePass(M, GetBFI, GetTTI);
+
+ return PreservedAnalyses::all();
}
Index: llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
===================================================================
--- llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -834,6 +834,10 @@
if (MergeFunctions)
MPM.add(createMergeFunctionsPass());
+ // Add Module flag "CG Profile" based on Branch Frequency Information.
+ if (CallGraphProfile)
+ MPM.add(createCGProfileLegacyPass());
+
// 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
Index: llvm/include/llvm/Transforms/Instrumentation/CGProfile.h
===================================================================
--- llvm/include/llvm/Transforms/Instrumentation/CGProfile.h
+++ llvm/include/llvm/Transforms/Instrumentation/CGProfile.h
@@ -19,11 +19,6 @@
class CGProfilePass : public PassInfoMixin<CGProfilePass> {
public:
PreservedAnalyses run(Module &M, ModuleAnalysisManager &AM);
-
-private:
- void addModuleFlags(
- Module &M,
- MapVector<std::pair<Function *, Function *>, uint64_t> &Counts) const;
};
} // end namespace llvm
Index: llvm/include/llvm/Transforms/IPO/PassManagerBuilder.h
===================================================================
--- llvm/include/llvm/Transforms/IPO/PassManagerBuilder.h
+++ llvm/include/llvm/Transforms/IPO/PassManagerBuilder.h
@@ -156,6 +156,7 @@
bool DisableTailCalls;
bool DisableUnrollLoops;
+ bool CallGraphProfile;
bool SLPVectorize;
bool LoopVectorize;
bool LoopsInterleaved;
Index: llvm/include/llvm/Transforms/IPO.h
===================================================================
--- llvm/include/llvm/Transforms/IPO.h
+++ llvm/include/llvm/Transforms/IPO.h
@@ -282,6 +282,8 @@
ModulePass *createWriteThinLTOBitcodePass(raw_ostream &Str,
raw_ostream *ThinLinkOS = nullptr);
+ModulePass *createCGProfileLegacyPass();
+
} // End llvm namespace
#endif
Index: llvm/include/llvm/InitializePasses.h
===================================================================
--- llvm/include/llvm/InitializePasses.h
+++ llvm/include/llvm/InitializePasses.h
@@ -102,6 +102,7 @@
void initializeCFIInstrInserterPass(PassRegistry&);
void initializeCFLAndersAAWrapperPassPass(PassRegistry&);
void initializeCFLSteensAAWrapperPassPass(PassRegistry&);
+void initializeCGProfileLegacyPassPass(PassRegistry &);
void initializeCallGraphDOTPrinterPass(PassRegistry&);
void initializeCallGraphPrinterLegacyPassPass(PassRegistry&);
void initializeCallGraphViewerPass(PassRegistry&);
Index: clang/lib/CodeGen/BackendUtil.cpp
===================================================================
--- clang/lib/CodeGen/BackendUtil.cpp
+++ clang/lib/CodeGen/BackendUtil.cpp
@@ -620,6 +620,7 @@
PMBuilder.SizeLevel = CodeGenOpts.OptimizeSize;
PMBuilder.SLPVectorize = CodeGenOpts.VectorizeSLP;
PMBuilder.LoopVectorize = CodeGenOpts.VectorizeLoop;
+ PMBuilder.CallGraphProfile = CodeGenOpts.CallGraphProfile;
PMBuilder.DisableUnrollLoops = !CodeGenOpts.UnrollLoops;
// Loop interleaving in the loop vectorizer has historically been set to be
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
