RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 12:41:49 +01:00
Code Issues Projects Releases Wiki Activity

[thinlto] Basic thinlto fdo heuristic

Browse Source 
Summary:
This patch improves thinlto importer
by importing 3x larger functions that are called from hot block.

I compared performance with the trunk on spec, and there
were about 2% on povray and 3.33% on milc. These results seems
to be consistant and match the results Teresa got with her simple
heuristic. Some benchmarks got slower but I think they are just
noisy (mcf, xalancbmki, omnetpp)- running the benchmarks again with
more iterations to confirm. Geomean of all benchmarks including the noisy ones
were about +0.02%.

I see much better improvement on google branch with Easwaran patch
for pgo callsite inlining (the inliner actually inline those big functions)
Over all I see +0.5% improvement, and I get +8.65% on povray.
So I guess we will see much bigger change when Easwaran patch will land
(it depends on new pass manager), but it is still worth putting this to trunk
before it.

Implementation details changes:
- Removed CallsiteCount.
- ProfileCount got replaced by Hotness
- hot-import-multiplier is set to 3.0 for now,
didn't have time to tune it up, but I see that we get most of the interesting
functions with 3, so there is no much performance difference with higher, and
binary size doesn't grow as much as with 10.0.

Reviewers: eraman, mehdi_amini, tejohnson

Subscribers: mehdi_amini, llvm-commits

Differential Revision: https://reviews.llvm.org/D24638

llvm-svn: 282437
This commit is contained in:
Piotr Padlewski 2016-09-26 20:37:32 +00:00
parent 7d0e3e88cb
commit 3152e057e1
21 changed files with 422 additions and 80 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
include/llvm/Analysis/ModuleSummaryAnalysis.h
View File

@ -21,6 +21,7 @@
namespace llvm {
class BlockFrequencyInfo;
class ProfileSummaryInfo;
/// Direct function to compute a \c ModuleSummaryIndex from a given module.
///
@ -30,8 +31,8 @@ class BlockFrequencyInfo;
/// that information.
ModuleSummaryIndex buildModuleSummaryIndex(
const Module &M,
std::function<BlockFrequencyInfo *(const Function &F)> GetBFICallback =
nullptr);
std::function<BlockFrequencyInfo *(const Function &F)> GetBFICallback,
ProfileSummaryInfo *PSI);
/// Analysis pass to provide the ModuleSummaryIndex object.
class ModuleSummaryIndexAnalysis

8
include/llvm/Bitcode/LLVMBitCodes.h
View File

@ -194,20 +194,20 @@ enum ModulePathSymtabCodes {
// and combined index cases.
enum GlobalValueSummarySymtabCodes {
// PERMODULE: [valueid, flags, instcount, numrefs, numrefs x valueid,
// n x (valueid, callsitecount)]
// n x (valueid)]
FS_PERMODULE = 1,
// PERMODULE_PROFILE: [valueid, flags, instcount, numrefs,
// numrefs x valueid,
// n x (valueid, callsitecount, profilecount)]
// n x (valueid, hotness)]
FS_PERMODULE_PROFILE = 2,
// PERMODULE_GLOBALVAR_INIT_REFS: [valueid, flags, n x valueid]
FS_PERMODULE_GLOBALVAR_INIT_REFS = 3,
// COMBINED: [valueid, modid, flags, instcount, numrefs, numrefs x valueid,
// n x (valueid, callsitecount)]
// n x (valueid)]
FS_COMBINED = 4,
// COMBINED_PROFILE: [valueid, modid, flags, instcount, numrefs,
// numrefs x valueid,
// n x (valueid, callsitecount, profilecount)]
// n x (valueid, hotness)]
FS_COMBINED_PROFILE = 5,
// COMBINED_GLOBALVAR_INIT_REFS: [valueid, modid, flags, n x valueid]
FS_COMBINED_GLOBALVAR_INIT_REFS = 6,

20
include/llvm/IR/ModuleSummaryIndex.h
View File

@ -30,18 +30,14 @@ namespace llvm {
/// \brief Class to accumulate and hold information about a callee.
struct CalleeInfo {
/// The static number of callsites calling corresponding function.
unsigned CallsiteCount;
/// The cumulative profile count of calls to corresponding function
/// (if using PGO, otherwise 0).
uint64_t ProfileCount;
CalleeInfo() : CallsiteCount(0), ProfileCount(0) {}
CalleeInfo(unsigned CallsiteCount, uint64_t ProfileCount)
: CallsiteCount(CallsiteCount), ProfileCount(ProfileCount) {}
CalleeInfo &operator+=(uint64_t RHSProfileCount) {
CallsiteCount++;
ProfileCount += RHSProfileCount;
return *this;
enum class HotnessType : uint8_t { Unknown = 0, Cold = 1, None = 2, Hot = 3 };
HotnessType Hotness = HotnessType::Unknown;
CalleeInfo() = default;
explicit CalleeInfo(HotnessType Hotness) : Hotness(Hotness) {}
void updateHotness(const HotnessType OtherHotness) {
Hotness = std::max(Hotness, OtherHotness);
}
};

54
lib/Analysis/ModuleSummaryAnalysis.cpp
View File

@ -18,6 +18,7 @@
#include "llvm/Analysis/BranchProbabilityInfo.h"
#include "llvm/Analysis/IndirectCallPromotionAnalysis.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/ProfileSummaryInfo.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/InstIterator.h"
@ -63,8 +64,20 @@ static void findRefEdges(const User *CurUser, DenseSet<const Value *> &RefEdges,
}
}
static CalleeInfo::HotnessType getHotness(uint64_t ProfileCount,
ProfileSummaryInfo *PSI) {
if (!PSI)
return CalleeInfo::HotnessType::Unknown;
if (PSI->isHotCount(ProfileCount))
return CalleeInfo::HotnessType::Hot;
if (PSI->isColdCount(ProfileCount))
return CalleeInfo::HotnessType::Cold;
return CalleeInfo::HotnessType::None;
}
static void computeFunctionSummary(ModuleSummaryIndex &Index, const Module &M,
const Function &F, BlockFrequencyInfo *BFI) {
const Function &F, BlockFrequencyInfo *BFI,
ProfileSummaryInfo *PSI) {
// Summary not currently supported for anonymous functions, they must
// be renamed.
if (!F.hasName())
@ -97,7 +110,10 @@ static void computeFunctionSummary(ModuleSummaryIndex &Index, const Module &M,
auto ScaledCount = BFI ? BFI->getBlockProfileCount(&BB) : None;
auto *CalleeId =
M.getValueSymbolTable().lookup(CalledFunction->getName());
CallGraphEdges[CalleeId] += (ScaledCount ? ScaledCount.getValue() : 0);
auto Hotness = ScaledCount ? getHotness(ScaledCount.getValue(), PSI)
: CalleeInfo::HotnessType::Unknown;
CallGraphEdges[CalleeId].updateHotness(Hotness);
} else {
const auto *CI = dyn_cast<CallInst>(&I);
// Skip inline assembly calls.
@ -113,7 +129,8 @@ static void computeFunctionSummary(ModuleSummaryIndex &Index, const Module &M,
ICallAnalysis.getPromotionCandidatesForInstruction(
&I, NumVals, TotalCount, NumCandidates);
for (auto &Candidate : CandidateProfileData)
IndirectCallEdges[Candidate.Value] += Candidate.Count;
IndirectCallEdges[Candidate.Value].updateHotness(
getHotness(Candidate.Count, PSI));
}
}
@ -140,7 +157,8 @@ static void computeVariableSummary(ModuleSummaryIndex &Index,
ModuleSummaryIndex llvm::buildModuleSummaryIndex(
const Module &M,
std::function<BlockFrequencyInfo *(const Function &F)> GetBFICallback) {
std::function<BlockFrequencyInfo *(const Function &F)> GetBFICallback,
ProfileSummaryInfo *PSI) {
ModuleSummaryIndex Index;
// Check if the module can be promoted, otherwise just disable importing from
// it by not emitting any summary.
@ -165,7 +183,7 @@ ModuleSummaryIndex llvm::buildModuleSummaryIndex(
BFI = BFIPtr.get();
}
computeFunctionSummary(Index, M, F, BFI);
computeFunctionSummary(Index, M, F, BFI, PSI);
}
// Compute summaries for all variables defined in module, and save in the
@ -182,10 +200,15 @@ char ModuleSummaryIndexAnalysis::PassID;
ModuleSummaryIndex
ModuleSummaryIndexAnalysis::run(Module &M, ModuleAnalysisManager &AM) {
ProfileSummaryInfo &PSI = AM.getResult<ProfileSummaryAnalysis>(M);
auto &FAM = AM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
return buildModuleSummaryIndex(M, [&FAM](const Function &F) {
return &FAM.getResult<BlockFrequencyAnalysis>(*const_cast<Function *>(&F));
});
return buildModuleSummaryIndex(
M,
[&FAM](const Function &F) {
return &FAM.getResult<BlockFrequencyAnalysis>(
*const_cast<Function *>(&F));
},
&PSI);
}
char ModuleSummaryIndexWrapperPass::ID = 0;
@ -205,11 +228,15 @@ ModuleSummaryIndexWrapperPass::ModuleSummaryIndexWrapperPass()
}
bool ModuleSummaryIndexWrapperPass::runOnModule(Module &M) {
Index = buildModuleSummaryIndex(M, [this](const Function &F) {
return &(this->getAnalysis<BlockFrequencyInfoWrapperPass>(
*const_cast<Function *>(&F))
.getBFI());
});
auto &PSI = *getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI(M);
Index = buildModuleSummaryIndex(
M,
[this](const Function &F) {
return &(this->getAnalysis<BlockFrequencyInfoWrapperPass>(
*const_cast<Function *>(&F))
.getBFI());
},
&PSI);
return false;
}
@ -221,6 +248,7 @@ bool ModuleSummaryIndexWrapperPass::doFinalization(Module &M) {
void ModuleSummaryIndexWrapperPass::getAnalysisUsage(AnalysisUsage &AU) const {
AU.setPreservesAll();
AU.addRequired<BlockFrequencyInfoWrapperPass>();
AU.addRequired<ProfileSummaryInfoWrapperPass>();
}
bool llvm::moduleCanBeRenamedForThinLTO(const Module &M) {

57
lib/Bitcode/Reader/BitcodeReader.cpp
View File

@ -651,6 +651,9 @@ private:
std::pair<GlobalValue::GUID, GlobalValue::GUID>
getGUIDFromValueId(unsigned ValueId);
std::pair<GlobalValue::GUID, CalleeInfo::HotnessType>
readCallGraphEdge(const SmallVector<uint64_t, 64> &Record, unsigned int &I,
bool IsOldProfileFormat, bool HasProfile);
};
} // end anonymous namespace
@ -6218,8 +6221,10 @@ std::error_code ModuleSummaryIndexBitcodeReader::parseEntireSummary() {
return error("Invalid Summary Block: version expected");
}
const uint64_t Version = Record[0];
if (Version != 1)
return error("Invalid summary version " + Twine(Version) + ", 1 expected");
const bool IsOldProfileFormat = Version == 1;
if (!IsOldProfileFormat && Version != 2)
return error("Invalid summary version " + Twine(Version) +
", 1 or 2 expected");
Record.clear();
// Keep around the last seen summary to be used when we see an optional
@ -6264,10 +6269,10 @@ std::error_code ModuleSummaryIndexBitcodeReader::parseEntireSummary() {
default: // Default behavior: ignore.
break;
// FS_PERMODULE: [valueid, flags, instcount, numrefs, numrefs x valueid,
// n x (valueid, callsitecount)]
// n x (valueid)]
// FS_PERMODULE_PROFILE: [valueid, flags, instcount, numrefs,
// numrefs x valueid,
// n x (valueid, callsitecount, profilecount)]
// n x (valueid, hotness)]
case bitc::FS_PERMODULE:
case bitc::FS_PERMODULE_PROFILE: {
unsigned ValueID = Record[0];
@ -6296,12 +6301,11 @@ std::error_code ModuleSummaryIndexBitcodeReader::parseEntireSummary() {
bool HasProfile = (BitCode == bitc::FS_PERMODULE_PROFILE);
for (unsigned I = CallGraphEdgeStartIndex, E = Record.size(); I != E;
++I) {
unsigned CalleeValueId = Record[I];
unsigned CallsiteCount = Record[++I];
uint64_t ProfileCount = HasProfile ? Record[++I] : 0;
GlobalValue::GUID CalleeGUID = getGUIDFromValueId(CalleeValueId).first;
FS->addCallGraphEdge(CalleeGUID,
CalleeInfo(CallsiteCount, ProfileCount));
CalleeInfo::HotnessType Hotness;
GlobalValue::GUID CalleeGUID;
std::tie(CalleeGUID, Hotness) =
readCallGraphEdge(Record, I, IsOldProfileFormat, HasProfile);
FS->addCallGraphEdge(CalleeGUID, CalleeInfo(Hotness));
}
auto GUID = getGUIDFromValueId(ValueID);
FS->setOriginalName(GUID.second);
@ -6356,10 +6360,9 @@ std::error_code ModuleSummaryIndexBitcodeReader::parseEntireSummary() {
break;
}
// FS_COMBINED: [valueid, modid, flags, instcount, numrefs,
// numrefs x valueid, n x (valueid, callsitecount)]
// numrefs x valueid, n x (valueid)]
// FS_COMBINED_PROFILE: [valueid, modid, flags, instcount, numrefs,
// numrefs x valueid,
// n x (valueid, callsitecount, profilecount)]
// numrefs x valueid, n x (valueid, hotness)]
case bitc::FS_COMBINED:
case bitc::FS_COMBINED_PROFILE: {
unsigned ValueID = Record[0];
@ -6385,12 +6388,11 @@ std::error_code ModuleSummaryIndexBitcodeReader::parseEntireSummary() {
bool HasProfile = (BitCode == bitc::FS_COMBINED_PROFILE);
for (unsigned I = CallGraphEdgeStartIndex, E = Record.size(); I != E;
++I) {
unsigned CalleeValueId = Record[I];
unsigned CallsiteCount = Record[++I];
uint64_t ProfileCount = HasProfile ? Record[++I] : 0;
GlobalValue::GUID CalleeGUID = getGUIDFromValueId(CalleeValueId).first;
FS->addCallGraphEdge(CalleeGUID,
CalleeInfo(CallsiteCount, ProfileCount));
CalleeInfo::HotnessType Hotness;
GlobalValue::GUID CalleeGUID;
std::tie(CalleeGUID, Hotness) =
readCallGraphEdge(Record, I, IsOldProfileFormat, HasProfile);
FS->addCallGraphEdge(CalleeGUID, CalleeInfo(Hotness));
}
GlobalValue::GUID GUID = getGUIDFromValueId(ValueID).first;
TheIndex->addGlobalValueSummary(GUID, std::move(FS));
@ -6456,6 +6458,23 @@ std::error_code ModuleSummaryIndexBitcodeReader::parseEntireSummary() {
llvm_unreachable("Exit infinite loop");
}
std::pair<GlobalValue::GUID, CalleeInfo::HotnessType>
ModuleSummaryIndexBitcodeReader::readCallGraphEdge(
const SmallVector<uint64_t, 64> &Record, unsigned int &I,
const bool IsOldProfileFormat, const bool HasProfile) {
auto Hotness = CalleeInfo::HotnessType::Unknown;
unsigned CalleeValueId = Record[I];
GlobalValue::GUID CalleeGUID = getGUIDFromValueId(CalleeValueId).first;
if (IsOldProfileFormat) {
I += 1; // Skip old callsitecount field
if (HasProfile)
I += 1; // Skip old profilecount field
} else if (HasProfile)
Hotness = static_cast<CalleeInfo::HotnessType>(Record[++I]);
return {CalleeGUID, Hotness};
}
// Parse the module string table block into the Index.
// This populates the ModulePathStringTable map in the index.
std::error_code ModuleSummaryIndexBitcodeReader::parseModuleStringTable() {

20
lib/Bitcode/Writer/BitcodeWriter.cpp
View File

@ -3293,10 +3293,8 @@ void ModuleBitcodeWriter::writePerModuleFunctionSummaryRecord(
bool HasProfileData = F.getEntryCount().hasValue();
for (auto &ECI : Calls) {
NameVals.push_back(getValueId(ECI.first));
assert(ECI.second.CallsiteCount > 0 && "Expected at least one callsite");
NameVals.push_back(ECI.second.CallsiteCount);
if (HasProfileData)
NameVals.push_back(ECI.second.ProfileCount);
NameVals.push_back(static_cast<uint8_t>(ECI.second.Hotness));
}
unsigned FSAbbrev = (HasProfileData ? FSCallsProfileAbbrev : FSCallsAbbrev);
@ -3336,7 +3334,7 @@ void ModuleBitcodeWriter::writeModuleLevelReferences(
// Current version for the summary.
// This is bumped whenever we introduce changes in the way some record are
// interpreted, like flags for instance.
static const uint64_t INDEX_VERSION = 1;
static const uint64_t INDEX_VERSION = 2;
/// Emit the per-module summary section alongside the rest of
/// the module's bitcode.
@ -3357,7 +3355,7 @@ void ModuleBitcodeWriter::writePerModuleGlobalValueSummary() {
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // flags
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // instcount
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 4)); // numrefs
// numrefs x valueid, n x (valueid, callsitecount)
// numrefs x valueid, n x (valueid)
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array));
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8));
unsigned FSCallsAbbrev = Stream.EmitAbbrev(Abbv);
@ -3369,7 +3367,7 @@ void ModuleBitcodeWriter::writePerModuleGlobalValueSummary() {
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // flags
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // instcount
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 4)); // numrefs
// numrefs x valueid, n x (valueid, callsitecount, profilecount)
// numrefs x valueid, n x (valueid, hotness)
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array));
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8));
unsigned FSCallsProfileAbbrev = Stream.EmitAbbrev(Abbv);
@ -3442,7 +3440,7 @@ void IndexBitcodeWriter::writeCombinedGlobalValueSummary() {
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // flags
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // instcount
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 4)); // numrefs
// numrefs x valueid, n x (valueid, callsitecount)
// numrefs x valueid, n x (valueid)
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array));
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8));
unsigned FSCallsAbbrev = Stream.EmitAbbrev(Abbv);
@ -3455,7 +3453,7 @@ void IndexBitcodeWriter::writeCombinedGlobalValueSummary() {
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // flags
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // instcount
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 4)); // numrefs
// numrefs x valueid, n x (valueid, callsitecount, profilecount)
// numrefs x valueid, n x (valueid, hotness)
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array));
Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8));
unsigned FSCallsProfileAbbrev = Stream.EmitAbbrev(Abbv);
@ -3542,7 +3540,7 @@ void IndexBitcodeWriter::writeCombinedGlobalValueSummary() {
bool HasProfileData = false;
for (auto &EI : FS->calls()) {
HasProfileData |= EI.second.ProfileCount != 0;
HasProfileData |= EI.second.Hotness != CalleeInfo::HotnessType::Unknown;
if (HasProfileData)
break;
}
@ -3553,10 +3551,8 @@ void IndexBitcodeWriter::writeCombinedGlobalValueSummary() {
if (!hasValueId(EI.first.getGUID()))
continue;
NameVals.push_back(getValueId(EI.first.getGUID()));
assert(EI.second.CallsiteCount > 0 && "Expected at least one callsite");
NameVals.push_back(EI.second.CallsiteCount);
if (HasProfileData)
NameVals.push_back(EI.second.ProfileCount);
NameVals.push_back(static_cast<uint8_t>(EI.second.Hotness));
}
unsigned FSAbbrev = (HasProfileData ? FSCallsProfileAbbrev : FSCallsAbbrev);

4
lib/LTO/ThinLTOCodeGenerator.cpp
View File

@ -21,6 +21,7 @@
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/ModuleSummaryAnalysis.h"
#include "llvm/Analysis/ProfileSummaryInfo.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Bitcode/BitcodeWriterPass.h"
@ -377,7 +378,8 @@ ProcessThinLTOModule(Module &TheModule, ModuleSummaryIndex &Index,
SmallVector<char, 128> OutputBuffer;
{
raw_svector_ostream OS(OutputBuffer);
auto Index = buildModuleSummaryIndex(TheModule);
ProfileSummaryInfo PSI(TheModule);
auto Index = buildModuleSummaryIndex(TheModule, nullptr, nullptr);
WriteBitcodeToFile(&TheModule, OS, true, &Index);
}
return make_unique<ObjectMemoryBuffer>(std::move(OutputBuffer));

15
lib/Transforms/IPO/FunctionImport.cpp
View File

@ -48,6 +48,10 @@ static cl::opt<float>
cl::desc("As we import functions, multiply the "
"`import-instr-limit` threshold by this factor "
"before processing newly imported functions"));
static cl::opt<float> ImportHotMultiplier(
"import-hot-multiplier", cl::init(3.0), cl::Hidden, cl::value_desc("x"),
cl::ZeroOrMore, cl::desc("Multiply the `import-instr-limit` threshold for "
"hot callsites"));
static cl::opt<bool> PrintImports("print-imports", cl::init(false), cl::Hidden,
cl::desc("Print imported functions"));
@ -268,7 +272,7 @@ using EdgeInfo = std::pair<const FunctionSummary *, unsigned /* Threshold */>;
/// exported from their source module.
static void computeImportForFunction(
const FunctionSummary &Summary, const ModuleSummaryIndex &Index,
unsigned Threshold, const GVSummaryMapTy &DefinedGVSummaries,
const unsigned Threshold, const GVSummaryMapTy &DefinedGVSummaries,
SmallVectorImpl<EdgeInfo> &Worklist,
FunctionImporter::ImportMapTy &ImportList,
StringMap<FunctionImporter::ExportSetTy> *ExportLists = nullptr) {
@ -281,7 +285,12 @@ static void computeImportForFunction(
continue;
}
auto *CalleeSummary = selectCallee(GUID, Threshold, Index);
// FIXME: Also lower the threshold for cold callsites.
const auto NewThreshold =
Edge.second.Hotness == CalleeInfo::HotnessType::Hot
? Threshold * ImportHotMultiplier
: Threshold;
auto *CalleeSummary = selectCallee(GUID, NewThreshold, Index);
if (!CalleeSummary) {
DEBUG(dbgs() << "ignored! No qualifying callee with summary found.\n");
continue;
@ -297,7 +306,7 @@ static void computeImportForFunction(
} else
ResolvedCalleeSummary = cast<FunctionSummary>(CalleeSummary);
assert(ResolvedCalleeSummary->instCount() <= Threshold &&
assert(ResolvedCalleeSummary->instCount() <= NewThreshold &&
"selectCallee() didn't honor the threshold");
auto ExportModulePath = ResolvedCalleeSummary->modulePath();

BIN
test/Bitcode/Inputs/thinlto-function-summary-callgraph-combined.1.bc Normal file
View File

Binary file not shown.

BIN
test/Bitcode/Inputs/thinlto-function-summary-callgraph-pgo-combined.1.bc Normal file
View File

Binary file not shown.

BIN
test/Bitcode/Inputs/thinlto-function-summary-callgraph-pgo.1.bc Normal file
View File

Binary file not shown.

27
test/Bitcode/Inputs/thinlto-function-summary-callgraph-profile-summary.ll Normal file
View File

@ -0,0 +1,27 @@
; ModuleID = 'thinlto-function-summary-callgraph-profile-summary2.ll'
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
define void @hot1() #1 {
ret void
}
define void @hot2() #1 {
ret void
}
define void @hot3() #1 {
ret void
}
define void @cold() #1 {
ret void
}
define void @none1() #1 {
ret void
}
define void @none2() #1 {
ret void
}
define void @none3() #1 {
ret void
}

BIN
test/Bitcode/Inputs/thinlto-function-summary-callgraph.1.bc Normal file
View File

Binary file not shown.

2
test/Bitcode/summary_version.ll
View File

@ -2,7 +2,7 @@
; RUN: opt -module-summary %s -o - | llvm-bcanalyzer -dump | FileCheck %s
; CHECK: <GLOBALVAL_SUMMARY_BLOCK
; CHECK: <VERSION op0=1/>
; CHECK: <VERSION op0=2/>

4
test/Bitcode/thinlto-alias.ll
View File

@ -9,7 +9,7 @@
; CHECK-NEXT: <VERSION
; See if the call to func is registered, using the expected callsite count
; and value id matching the subsequent value symbol table.
; CHECK-NEXT: <PERMODULE {{.*}} op4=[[FUNCID:[0-9]+]] op5=1/>
; CHECK-NEXT: <PERMODULE {{.*}} op4=[[FUNCID:[0-9]+]]/>
; CHECK-NEXT: </GLOBALVAL_SUMMARY_BLOCK>
; CHECK-NEXT: <VALUE_SYMTAB
; CHECK-NEXT: <FNENTRY {{.*}} record string = 'main'
@ -21,7 +21,7 @@
; COMBINED-NEXT: <VERSION
; See if the call to analias is registered, using the expected callsite count
; and value id matching the subsequent value symbol table.
; COMBINED-NEXT: <COMBINED {{.*}} op5=[[ALIASID:[0-9]+]] op6=1/>
; COMBINED-NEXT: <COMBINED {{.*}} op5=[[ALIASID:[0-9]+]]/>
; Followed by the alias and aliasee
; COMBINED-NEXT: <COMBINED {{.*}}
; COMBINED-NEXT: <COMBINED_ALIAS {{.*}} op3=[[ALIASEEID:[0-9]+]]

17
test/Bitcode/thinlto-function-summary-callgraph-pgo.ll
View File

@ -1,15 +1,20 @@
; Test to check the callgraph in summary when there is PGO
; RUN: opt -module-summary %s -o %t.o
; RUN: llvm-bcanalyzer -dump %t.o | FileCheck %s
; RUN: opt -module-summary %p/Inputs/thinlto-function-summary-callgraph.ll -o %t2.o
; RUN: llvm-lto -thinlto -o %t3 %t.o %t2.o
; RUN: llvm-bcanalyzer -dump %t3.thinlto.bc | FileCheck %s --check-prefix=COMBINED
; Check parsing for old summary versions generated from this file.
; RUN: llvm-lto -thinlto-index-stats %p/Inputs/thinlto-function-summary-callgraph-pgo.1.bc | FileCheck %s --check-prefix=OLD
; RUN: llvm-lto -thinlto-index-stats %p/Inputs/thinlto-function-summary-callgraph-pgo-combined.1.bc | FileCheck %s --check-prefix=OLD-COMBINED
; CHECK: <GLOBALVAL_SUMMARY_BLOCK
; CHECK-NEXT: <VERSION
; See if the call to func is registered, using the expected callsite count
; and profile count, with value id matching the subsequent value symbol table.
; CHECK-NEXT: <PERMODULE_PROFILE {{.*}} op4=[[FUNCID:[0-9]+]] op5=1 op6=1/>
; and hotness type, with value id matching the subsequent value symbol table.
; CHECK-NEXT: <PERMODULE_PROFILE {{.*}} op4=[[FUNCID:[0-9]+]] op5=2/>
; CHECK-NEXT: </GLOBALVAL_SUMMARY_BLOCK>
; CHECK-NEXT: <VALUE_SYMTAB
; CHECK-NEXT: <FNENTRY {{.*}} record string = 'main'
@ -21,8 +26,9 @@
; COMBINED-NEXT: <VERSION
; COMBINED-NEXT: <COMBINED
; See if the call to func is registered, using the expected callsite count
; and profile count, with value id matching the subsequent value symbol table.
; COMBINED-NEXT: <COMBINED_PROFILE {{.*}} op5=[[FUNCID:[0-9]+]] op6=1 op7=1/>
; and hotness type, with value id matching the subsequent value symbol table.
; op6=2 which is hotnessType::None.
; COMBINED-NEXT: <COMBINED_PROFILE {{.*}} op5=[[FUNCID:[0-9]+]] op6=2/>
; COMBINED-NEXT: </GLOBALVAL_SUMMARY_BLOCK>
; COMBINED-NEXT: <VALUE_SYMTAB
; Entry for function func should have entry with value id FUNCID
@ -44,3 +50,6 @@ entry:
declare void @func(...) #1
!2 = !{!"function_entry_count", i64 1}
; OLD: Index {{.*}} contains 1 nodes (1 functions, 0 alias, 0 globals) and 1 edges (0 refs and 1 calls)
; OLD-COMBINED: Index {{.*}} contains 2 nodes (2 functions, 0 alias, 0 globals) and 1 edges (0 refs and 1 calls)

98
test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll Normal file
View File

@ -0,0 +1,98 @@
; Test to check the callgraph in summary when there is PGO
; RUN: opt -module-summary %s -o %t.o
; RUN: llvm-bcanalyzer -dump %t.o | FileCheck %s
; RUN: opt -module-summary %p/Inputs/thinlto-function-summary-callgraph-profile-summary.ll -o %t2.o
; RUN: llvm-lto -thinlto -o %t3 %t.o %t2.o
; RUN: llvm-bcanalyzer -dump %t3.thinlto.bc | FileCheck %s --check-prefix=COMBINED
; CHECK-LABEL: <GLOBALVAL_SUMMARY_BLOCK
; CHECK-NEXT: <VERSION
; See if the call to func is registered, using the expected callsite count
; and profile count, with value id matching the subsequent value symbol table.
; CHECK-NEXT: <PERMODULE_PROFILE {{.*}} op4=[[HOT1:.*]] op5=3 op6=[[HOT2:.*]] op7=3 op8=[[HOT3:.*]] op9=3 op10=[[COLD:.*]] op11=1 op12=[[NONE1:.*]] op13=2 op14=[[NONE2:.*]] op15=2 op16=[[NONE3:.*]] op17=2/>
; CHECK-NEXT: </GLOBALVAL_SUMMARY_BLOCK>
; CHECK-LABEL: <VALUE_SYMTAB
; CHECK-NEXT: <FNENTRY {{.*}} record string = 'hot_function
; CHECK-DAG: <ENTRY abbrevid=6 op0=[[NONE1]] {{.*}} record string = 'none1'
; CHECK-DAG: <ENTRY abbrevid=6 op0=[[COLD]] {{.*}} record string = 'cold'
; CHECK-DAG: <ENTRY abbrevid=6 op0=[[NONE2]] {{.*}} record string = 'none2'
; CHECK-DAG: <ENTRY abbrevid=6 op0=[[NONE3]] {{.*}} record string = 'none3'
; CHECK-DAG: <ENTRY abbrevid=6 op0=[[HOT1]] {{.*}} record string = 'hot1'
; CHECK-DAG: <ENTRY abbrevid=6 op0=[[HOT2]] {{.*}} record string = 'hot2'
; CHECK-DAG: <ENTRY abbrevid=6 op0=[[HOT3]] {{.*}} record string = 'hot3'
; CHECK-LABEL: </VALUE_SYMTAB>
; COMBINED: <GLOBALVAL_SUMMARY_BLOCK
; COMBINED-NEXT: <VERSION
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED_PROFILE {{.*}} op5=[[HOT1:.*]] op6=3 op7=[[HOT2:.*]] op8=3 op9=[[HOT3:.*]] op10=3 op11=[[COLD:.*]] op12=1 op13=[[NONE1:.*]] op14=2 op15=[[NONE2:.*]] op16=2 op17=[[NONE3:.*]] op18=2/>
; COMBINED_NEXT: <COMBINED abbrevid=
; COMBINED_NEXT: </GLOBALVAL_SUMMARY_BLOCK>
; ModuleID = 'thinlto-function-summary-callgraph.ll'
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
; This function have high profile count, so entry block is hot.
define void @hot_function(i1 %a, i1 %a2) !prof !20 {
entry:
call void @hot1()
br i1 %a, label %Cold, label %Hot, !prof !41
Cold: ; 1/1000 goes here
call void @cold()
call void @hot2()
call void @none1()
br label %exit
Hot: ; 999/1000 goes here
call void @hot2()
call void @hot3()
br i1 %a2, label %None1, label %None2, !prof !42
None1: ; half goes here
call void @none1()
call void @none2()
br label %exit
None2: ; half goes here
call void @none3()
br label %exit
exit:
ret void
}
declare void @hot1() #1
declare void @hot2() #1
declare void @hot3() #1
declare void @cold() #1
declare void @none1() #1
declare void @none2() #1
declare void @none3() #1
!41 = !{!"branch_weights", i32 1, i32 1000}
!42 = !{!"branch_weights", i32 1, i32 1}
!llvm.module.flags = !{!1}
!20 = !{!"function_entry_count", i64 110}
!1 = !{i32 1, !"ProfileSummary", !2}
!2 = !{!3, !4, !5, !6, !7, !8, !9, !10}
!3 = !{!"ProfileFormat", !"InstrProf"}
!4 = !{!"TotalCount", i64 10000}
!5 = !{!"MaxCount", i64 10}
!6 = !{!"MaxInternalCount", i64 1}
!7 = !{!"MaxFunctionCount", i64 1000}
!8 = !{!"NumCounts", i64 3}
!9 = !{!"NumFunctions", i64 3}
!10 = !{!"DetailedSummary", !11}
!11 = !{!12, !13, !14}
!12 = !{i32 10000, i64 100, i32 1}
!13 = !{i32 999000, i64 100, i32 1}
!14 = !{i32 999999, i64 1, i32 2}

12
test/Bitcode/thinlto-function-summary-callgraph.ll
View File

@ -1,15 +1,20 @@
; Test to check the callgraph in summary
; RUN: opt -module-summary %s -o %t.o
; RUN: llvm-bcanalyzer -dump %t.o | FileCheck %s
; RUN: opt -module-summary %p/Inputs/thinlto-function-summary-callgraph.ll -o %t2.o
; RUN: llvm-lto -thinlto -o %t3 %t.o %t2.o
; RUN: llvm-bcanalyzer -dump %t3.thinlto.bc | FileCheck %s --check-prefix=COMBINED
; Check parsing for old summary versions generated from this file.
; RUN: llvm-lto -thinlto-index-stats %p/Inputs/thinlto-function-summary-callgraph.1.bc | FileCheck %s --check-prefix=OLD
; RUN: llvm-lto -thinlto-index-stats %p/Inputs/thinlto-function-summary-callgraph-combined.1.bc | FileCheck %s --check-prefix=OLD-COMBINED
; CHECK: <GLOBALVAL_SUMMARY_BLOCK
; CHECK-NEXT: <VERSION
; See if the call to func is registered, using the expected callsite count
; and value id matching the subsequent value symbol table.
; CHECK-NEXT: <PERMODULE {{.*}} op4=[[FUNCID:[0-9]+]] op5=1/>
; CHECK-NEXT: <PERMODULE {{.*}} op4=[[FUNCID:[0-9]+]]/>
; CHECK-NEXT: </GLOBALVAL_SUMMARY_BLOCK>
; CHECK-NEXT: <VALUE_SYMTAB
; CHECK-NEXT: <FNENTRY {{.*}} record string = 'main'
@ -22,7 +27,7 @@
; COMBINED-NEXT: <COMBINED
; See if the call to func is registered, using the expected callsite count
; and value id matching the subsequent value symbol table.
; COMBINED-NEXT: <COMBINED {{.*}} op5=[[FUNCID:[0-9]+]] op6=1/>
; COMBINED-NEXT: <COMBINED {{.*}} op5=[[FUNCID:[0-9]+]]/>
; COMBINED-NEXT: </GLOBALVAL_SUMMARY_BLOCK>
; COMBINED-NEXT: <VALUE_SYMTAB
; Entry for function func should have entry with value id FUNCID
@ -42,3 +47,6 @@ entry:
}
declare void @func(...) #1
; OLD: Index {{.*}} contains 1 nodes (1 functions, 0 alias, 0 globals) and 1 edges (0 refs and 1 calls)
; OLD-COMBINED: Index {{.*}} contains 2 nodes (2 functions, 0 alias, 0 globals) and 1 edges (0 refs and 1 calls)

10
test/Bitcode/thinlto-function-summary-refgraph.ll
View File

@ -11,20 +11,20 @@
; llvm.ctpop.i8.
; CHECK: <GLOBALVAL_SUMMARY_BLOCK
; Function main contains call to func, as well as address reference to func:
; CHECK-DAG: <PERMODULE {{.*}} op0=[[MAINID:[0-9]+]] op1=0 {{.*}} op3=1 op4=[[FUNCID:[0-9]+]] op5=[[FUNCID]] op6=1/>
; CHECK-DAG: <PERMODULE {{.*}} op0=[[MAINID:[0-9]+]] op1=0 {{.*}} op3=1 op4=[[FUNCID:[0-9]+]] op5=[[FUNCID]]/>
; Function W contains a call to func3 as well as a reference to globalvar:
; CHECK-DAG: <PERMODULE {{.*}} op0=[[WID:[0-9]+]] op1=5 {{.*}} op3=1 op4=[[GLOBALVARID:[0-9]+]] op5=[[FUNC3ID:[0-9]+]] op6=1/>
; CHECK-DAG: <PERMODULE {{.*}} op0=[[WID:[0-9]+]] op1=5 {{.*}} op3=1 op4=[[GLOBALVARID:[0-9]+]] op5=[[FUNC3ID:[0-9]+]]/>
; Function X contains call to foo, as well as address reference to foo
; which is in the same instruction as the call:
; CHECK-DAG: <PERMODULE {{.*}} op0=[[XID:[0-9]+]] op1=1 {{.*}} op3=1 op4=[[FOOID:[0-9]+]] op5=[[FOOID]] op6=1/>
; CHECK-DAG: <PERMODULE {{.*}} op0=[[XID:[0-9]+]] op1=1 {{.*}} op3=1 op4=[[FOOID:[0-9]+]] op5=[[FOOID]]/>
; Function Y contains call to func2, and ensures we don't incorrectly add
; a reference to it when reached while earlier analyzing the phi using its
; return value:
; CHECK-DAG: <PERMODULE {{.*}} op0=[[YID:[0-9]+]] op1=8 {{.*}} op3=0 op4=[[FUNC2ID:[0-9]+]] op5=1/>
; CHECK-DAG: <PERMODULE {{.*}} op0=[[YID:[0-9]+]] op1=8 {{.*}} op3=0 op4=[[FUNC2ID:[0-9]+]]/>
; Function Z contains call to func2, and ensures we don't incorrectly add
; a reference to it when reached while analyzing subsequent use of its return
; value:
; CHECK-DAG: <PERMODULE {{.*}} op0=[[ZID:[0-9]+]] op1=3 {{.*}} op3=0 op4=[[FUNC2ID:[0-9]+]] op5=1/>
; CHECK-DAG: <PERMODULE {{.*}} op0=[[ZID:[0-9]+]] op1=3 {{.*}} op3=0 op4=[[FUNC2ID:[0-9]+]]/>
; Variable bar initialization contains address reference to func:
; CHECK-DAG: <PERMODULE_GLOBALVAR_INIT_REFS {{.*}} op0=[[BARID:[0-9]+]] op1=0 op2=[[FUNCID]]/>
; CHECK: </GLOBALVAL_SUMMARY_BLOCK>

43
test/Transforms/FunctionImport/Inputs/hotness_based_import.ll Normal file
View File

@ -0,0 +1,43 @@
; ModuleID = 'thinlto-function-summary-callgraph-profile-summary2.ll'
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
define void @hot1() #1 {
ret void
}
define void @hot2() #1 {
call void @externalFunction()
call void @externalFunction()
ret void
}
define void @hot3() #1 {
call void @externalFunction()
call void @externalFunction()
call void @externalFunction()
ret void
}
define void @cold() #1 {
ret void
}
define void @cold2() #1 {
call void @externalFunction()
call void @externalFunction()
ret void
}
define void @none1() #1 {
ret void
}
define void @none2() #1 {
call void @externalFunction()
ret void
}
define void @none3() #1 {
call void @externalFunction()
call void @externalFunction()
ret void
}
declare void @externalFunction()

106
test/Transforms/FunctionImport/hotness_based_import.ll Normal file
View File

@ -0,0 +1,106 @@
; Test to check the callgraph in summary when there is PGO
; RUN: opt -module-summary %s -o %t.bc
; RUN: opt -module-summary %p/Inputs/hotness_based_import.ll -o %t2.bc
; RUN: llvm-lto -thinlto -o %t3 %t.bc %t2.bc
; Test import with default hot multiplier (3)
; RUN: opt -function-import -summary-file %t3.thinlto.bc %t.bc -import-instr-limit=1 --S | FileCheck %s --check-prefix=CHECK --check-prefix=HOT-DEFAULT
; RUN: opt -function-import -summary-file %t3.thinlto.bc %t.bc -import-instr-limit=1 --S -import-hot-multiplier=3.0 | FileCheck %s --check-prefix=CHECK --check-prefix=HOT-DEFAULT
; HOT-DEFAULT-DAG: define available_externally void @hot1()
; HOT-DEFAULT-DAG: define available_externally void @hot2()
; HOT-DEFAULT-DAG: define available_externally void @cold()
; HOT-DEFAULT-DAG: define available_externally void @none1()
; HOT-DEFAULT-NOT: define available_externally void @hot3()
; HOT-DEFAULT-NOT: define available_externally void @none2()
; HOT-DEFAULT-NOT: define available_externally void @none3()
; HOT-DEFAULT-NOT: define available_externally void @cold2()
; Test import with hot multiplier 1.0 - treat hot callsites as normal.
; RUN: opt -function-import -summary-file %t3.thinlto.bc %t.bc -import-instr-limit=1 -import-hot-multiplier=1.0 --S | FileCheck %s --check-prefix=CHECK --check-prefix=HOT-ONE
; HOT-ONE-DAG: define available_externally void @hot1()
; HOT-ONE-DAG: define available_externally void @cold()
; HOT-ONE-DAG: define available_externally void @none1()
; HOT-ONE-NOT: define available_externally void @hot2()
; HOT-ONE-NOT: define available_externally void @hot3()
; HOT-ONE-NOT: define available_externally void @none2()
; HOT-ONE-NOT: define available_externally void @none3()
; HOT-ONE-NOT: define available_externally void @cold2()
; Test import with hot multiplier 0.0 and high threshold - don't import functions called from hot callsite.
; RUN: opt -function-import -summary-file %t3.thinlto.bc %t.bc -import-instr-limit=10 -import-hot-multiplier=0.0 --S | FileCheck %s --check-prefix=CHECK --check-prefix=HOT-ZERO
; HOT-ZERO-DAG: define available_externally void @cold()
; HOT-ZERO-DAG: define available_externally void @none1()
; HOT-ZERO-DAG: define available_externally void @none2()
; HOT-ZERO-DAG: define available_externally void @none3()
; HOT-ZERO-DAG: define available_externally void @cold2()
; HOT-ZERO-NOT: define available_externally void @hot2()
; HOT-ZERO-NOT: define available_externally void @hot1()
; HOT-ZERO-NOT: define available_externally void @hot3()
; ModuleID = 'thinlto-function-summary-callgraph.ll'
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
; This function have high profile count, so entry block is hot.
define void @hot_function(i1 %a, i1 %a2) !prof !20 {
entry:
call void @hot1()
br i1 %a, label %Cold, label %Hot, !prof !41
Cold: ; 1/1000 goes here
call void @cold()
call void @cold2()
call void @hot2()
call void @none1()
br label %exit
Hot: ; 999/1000 goes here
call void @hot2()
call void @hot3()
br i1 %a2, label %None1, label %None2, !prof !42
None1: ; half goes here
call void @none1()
call void @none2()
br label %exit
None2: ; half goes here
call void @none3()
br label %exit
exit:
ret void
}
declare void @hot1() #1
declare void @hot2() #1
declare void @hot3() #1
declare void @cold() #1
declare void @cold2() #1
declare void @none1() #1
declare void @none2() #1
declare void @none3() #1
!41 = !{!"branch_weights", i32 1, i32 1000}
!42 = !{!"branch_weights", i32 1, i32 1}
!llvm.module.flags = !{!1}
!20 = !{!"function_entry_count", i64 110}
!1 = !{i32 1, !"ProfileSummary", !2}
!2 = !{!3, !4, !5, !6, !7, !8, !9, !10}
!3 = !{!"ProfileFormat", !"InstrProf"}
!4 = !{!"TotalCount", i64 10000}
!5 = !{!"MaxCount", i64 10}
!6 = !{!"MaxInternalCount", i64 1}
!7 = !{!"MaxFunctionCount", i64 1000}
!8 = !{!"NumCounts", i64 3}
!9 = !{!"NumFunctions", i64 3}
!10 = !{!"DetailedSummary", !11}
!11 = !{!12, !13, !14}
!12 = !{i32 10000, i64 100, i32 1}
!13 = !{i32 999000, i64 100, i32 1}
!14 = !{i32 999999, i64 1, i32 2}