From 80787ca12d529b9f61ade17c680b2517c2d1ce33 Mon Sep 17 00:00:00 2001
From: Easwaran Raman <eraman@google.com>
Date: Tue, 10 May 2016 22:03:23 +0000
Subject: [PATCH] Reapply r266477 and r266488
llvm-svn: 269131
---
include/llvm/ProfileData/ProfileCommon.h | 37 ++++++++++-
lib/Analysis/InlineCost.cpp | 6 +-
lib/Analysis/LLVMBuild.txt | 2 +-
lib/ProfileData/ProfileSummary.cpp | 44 +++++++++++++
test/Transforms/Inline/inline-cold-callee.ll | 25 +++++---
test/Transforms/Inline/inline-hot-callee.ll | 25 +++++---
unittests/ProfileData/CMakeLists.txt | 1 +
unittests/ProfileData/ProfileSummaryTest.cpp | 66 ++++++++++++++++++++
8 files changed, 187 insertions(+), 19 deletions(-)
create mode 100644 unittests/ProfileData/ProfileSummaryTest.cpp
diff --git a/include/llvm/ProfileData/ProfileCommon.h b/include/llvm/ProfileData/ProfileCommon.h
index ae196aa5d00..878c7c73449 100644
--- a/include/llvm/ProfileData/ProfileCommon.h
+++ b/include/llvm/ProfileData/ProfileCommon.h
@@ -21,6 +21,8 @@
#include <vector>
#include "llvm/Support/Casting.h"
+#include "llvm/Support/ManagedStatic.h"
+#include "llvm/Support/Mutex.h"
namespace llvm {
class Function;
@@ -35,6 +37,7 @@ class LLVMContext;
class Metadata;
class MDTuple;
class MDNode;
+class Module;
inline const char *getHotSectionPrefix() { return ".hot"; }
inline const char *getUnlikelySectionPrefix() { return ".unlikely"; }
@@ -67,6 +70,14 @@ private:
// appears in the profile. The map is kept sorted in the descending order of
// counts.
std::map<uint64_t, uint32_t, std::greater<uint64_t>> CountFrequencies;
+ // Compute profile summary for a module.
+ static ProfileSummary *computeProfileSummary(Module *M);
+ // Cache of last seen module and its profile summary.
+ static ManagedStatic<std::pair<Module *, std::unique_ptr<ProfileSummary>>>
+ CachedSummary;
+ // Mutex to access summary cache
+ static ManagedStatic<sys::SmartMutex<true>> CacheMutex;
+
protected:
SummaryEntryVector DetailedSummary;
std::vector<uint32_t> DetailedSummaryCutoffs;
@@ -85,14 +96,12 @@ protected:
: PSK(K), DetailedSummary(DetailedSummary), TotalCount(TotalCount),
MaxCount(MaxCount), MaxFunctionCount(MaxFunctionCount),
NumCounts(NumCounts), NumFunctions(NumFunctions) {}
- ~ProfileSummary() = default;
inline void addCount(uint64_t Count);
/// \brief Return metadata specific to the profile format.
/// Derived classes implement this method to return a vector of Metadata.
virtual std::vector<Metadata *> getFormatSpecificMD(LLVMContext &Context) = 0;
/// \brief Return detailed summary as metadata.
Metadata *getDetailedSummaryMD(LLVMContext &Context);
-
public:
static const int Scale = 1000000;
Kind getKind() const { return PSK; }
@@ -111,6 +120,10 @@ public:
static ProfileSummary *getFromMD(Metadata *MD);
uint32_t getNumFunctions() { return NumFunctions; }
uint64_t getMaxFunctionCount() { return MaxFunctionCount; }
+ /// \brief Get profile summary associated with module \p M
+ static inline ProfileSummary *getProfileSummary(Module *M);
+ virtual ~ProfileSummary() = default;
+ virtual bool operator==(ProfileSummary &Other);
};
class InstrProfSummary final : public ProfileSummary {
@@ -140,6 +153,7 @@ public:
uint64_t getTotalCount() { return TotalCount; }
uint64_t getMaxBlockCount() { return MaxCount; }
uint64_t getMaxInternalBlockCount() { return MaxInternalBlockCount; }
+ bool operator==(ProfileSummary &Other) override;
};
class SampleProfileSummary final : public ProfileSummary {
@@ -180,5 +194,24 @@ SummaryEntryVector &ProfileSummary::getDetailedSummary() {
return DetailedSummary;
}
+ProfileSummary *ProfileSummary::getProfileSummary(Module *M) {
+ if (!M)
+ return nullptr;
+ sys::SmartScopedLock<true> Lock(*CacheMutex);
+ // Computing profile summary for a module involves parsing a fairly large
+ // metadata and could be expensive. We use a simple cache of the last seen
+ // module and its profile summary.
+ if (CachedSummary->first != M) {
+ auto *Summary = computeProfileSummary(M);
+ // Do not cache if the summary is empty. This is because a later pass
+ // (sample profile loader, for example) could attach the summary metadata on
+ // the module.
+ if (!Summary)
+ return nullptr;
+ CachedSummary->first = M;
+ CachedSummary->second.reset(Summary);
+ }
+ return CachedSummary->second.get();
+}
} // end namespace llvm
#endif
diff --git a/lib/Analysis/InlineCost.cpp b/lib/Analysis/InlineCost.cpp
index d3b2930d7ea..87dac729367 100644
--- a/lib/Analysis/InlineCost.cpp
+++ b/lib/Analysis/InlineCost.cpp
@@ -30,6 +30,7 @@
#include "llvm/IR/InstVisitor.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Operator.h"
+#include "llvm/ProfileData/ProfileCommon.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
@@ -630,10 +631,11 @@ void CallAnalyzer::updateThreshold(CallSite CS, Function &Callee) {
// a well-tuned heuristic based on *callsite* hotness and not callee hotness.
uint64_t FunctionCount = 0, MaxFunctionCount = 0;
bool HasPGOCounts = false;
- if (Callee.getEntryCount() && Callee.getParent()->getMaximumFunctionCount()) {
+ ProfileSummary *PS = ProfileSummary::getProfileSummary(Callee.getParent());
+ if (Callee.getEntryCount() && PS) {
HasPGOCounts = true;
FunctionCount = Callee.getEntryCount().getValue();
- MaxFunctionCount = Callee.getParent()->getMaximumFunctionCount().getValue();
+ MaxFunctionCount = PS->getMaxFunctionCount();
}
// Listen to the inlinehint attribute or profile based hotness information
diff --git a/lib/Analysis/LLVMBuild.txt b/lib/Analysis/LLVMBuild.txt
index bddf1a3ac20..4678cba28dc 100644
--- a/lib/Analysis/LLVMBuild.txt
+++ b/lib/Analysis/LLVMBuild.txt
@@ -19,4 +19,4 @@
type = Library
name = Analysis
parent = Libraries
-required_libraries = Core Support
+required_libraries = Core ProfileData Support
diff --git a/lib/ProfileData/ProfileSummary.cpp b/lib/ProfileData/ProfileSummary.cpp
index dfe44e32bbe..4e94138f0bf 100644
--- a/lib/ProfileData/ProfileSummary.cpp
+++ b/lib/ProfileData/ProfileSummary.cpp
@@ -15,6 +15,7 @@
#include "llvm/IR/Constants.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/Metadata.h"
+#include "llvm/IR/Module.h"
#include "llvm/IR/Type.h"
#include "llvm/ProfileData/InstrProf.h"
#include "llvm/ProfileData/ProfileCommon.h"
@@ -32,6 +33,10 @@ const std::vector<uint32_t> ProfileSummary::DefaultCutoffs(
900000, 950000, 990000, 999000, 999900, 999990, 999999});
const char *ProfileSummary::KindStr[2] = {"InstrProf", "SampleProfile"};
+ManagedStatic<std::pair<Module *, std::unique_ptr<ProfileSummary>>>
+ ProfileSummary::CachedSummary;
+ManagedStatic<sys::SmartMutex<true>> ProfileSummary::CacheMutex;
+
void InstrProfSummary::addRecord(const InstrProfRecord &R) {
// The first counter is not necessarily an entry count for IR
// instrumentation profiles.
@@ -86,6 +91,39 @@ void ProfileSummary::computeDetailedSummary() {
}
}
+bool ProfileSummary::operator==(ProfileSummary &Other) {
+ if (getKind() != Other.getKind())
+ return false;
+ if (TotalCount != Other.TotalCount)
+ return false;
+ if (MaxCount != Other.MaxCount)
+ return false;
+ if (MaxFunctionCount != Other.MaxFunctionCount)
+ return false;
+ if (NumFunctions != Other.NumFunctions)
+ return false;
+ if (NumCounts != Other.NumCounts)
+ return false;
+ std::vector<ProfileSummaryEntry> DS1 = getDetailedSummary();
+ std::vector<ProfileSummaryEntry> DS2 = Other.getDetailedSummary();
+ auto CompareSummaryEntry = [](ProfileSummaryEntry &E1,
+ ProfileSummaryEntry &E2) {
+ return E1.Cutoff == E2.Cutoff && E1.MinCount == E2.MinCount &&
+ E1.NumCounts == E2.NumCounts;
+ };
+ if (!std::equal(DS1.begin(), DS1.end(), DS2.begin(), CompareSummaryEntry))
+ return false;
+ return true;
+}
+
+bool InstrProfSummary::operator==(ProfileSummary &Other) {
+ InstrProfSummary *OtherIPS = dyn_cast<InstrProfSummary>(&Other);
+ if (!OtherIPS)
+ return false;
+ return MaxInternalBlockCount == OtherIPS->MaxInternalBlockCount &&
+ ProfileSummary::operator==(Other);
+}
+
// Returns true if the function is a hot function.
bool ProfileSummary::isFunctionHot(const Function *F) {
// FIXME: update when summary data is stored in module's metadata.
@@ -366,3 +404,9 @@ ProfileSummary *ProfileSummary::getFromMD(Metadata *MD) {
else
return nullptr;
}
+
+ProfileSummary *ProfileSummary::computeProfileSummary(Module *M) {
+ if (Metadata *MD = M->getProfileSummary())
+ return getFromMD(MD);
+ return nullptr;
+}
diff --git a/test/Transforms/Inline/inline-cold-callee.ll b/test/Transforms/Inline/inline-cold-callee.ll
index 1fd9f105db5..0543a5a9cd6 100644
--- a/test/Transforms/Inline/inline-cold-callee.ll
+++ b/test/Transforms/Inline/inline-cold-callee.ll
@@ -5,7 +5,7 @@
; A callee with identical body does gets inlined because cost fits within the
; inline-threshold
-define i32 @callee1(i32 %x) !prof !1 {
+define i32 @callee1(i32 %x) !prof !21 {
%x1 = add i32 %x, 1
%x2 = add i32 %x1, 1
%x3 = add i32 %x2, 1
@@ -13,7 +13,7 @@ define i32 @callee1(i32 %x) !prof !1 {
ret i32 %x3
}
-define i32 @callee2(i32 %x) !prof !2 {
+define i32 @callee2(i32 %x) !prof !22 {
; CHECK-LABEL: @callee2(
%x1 = add i32 %x, 1
%x2 = add i32 %x1, 1
@@ -22,7 +22,7 @@ define i32 @callee2(i32 %x) !prof !2 {
ret i32 %x3
}
-define i32 @caller2(i32 %y1) !prof !2 {
+define i32 @caller2(i32 %y1) !prof !22 {
; CHECK-LABEL: @caller2(
; CHECK: call i32 @callee2
; CHECK-NOT: call i32 @callee1
@@ -32,8 +32,19 @@ define i32 @caller2(i32 %y1) !prof !2 {
ret i32 %y3
}
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"MaxFunctionCount", i32 1000}
-!1 = !{!"function_entry_count", i64 100}
-!2 = !{!"function_entry_count", i64 1}
+!llvm.module.flags = !{!1}
+!21 = !{!"function_entry_count", i64 100}
+!22 = !{!"function_entry_count", i64 1}
+!1 = !{i32 1, !"ProfileSummary", !2}
+!2 = !{!3, !4, !5, !6, !7, !8, !9, !10}
+!3 = !{!"ProfileFormat", !"InstrProf"}
+!4 = !{!"TotalCount", i64 10000}
+!5 = !{!"MaxBlockCount", i64 1000}
+!6 = !{!"MaxInternalBlockCount", i64 1}
+!7 = !{!"MaxFunctionCount", i64 1000}
+!8 = !{!"NumBlocks", i64 3}
+!9 = !{!"NumFunctions", i64 3}
+!10 = !{!"DetailedSummary", !11}
+!11 = !{!12}
+!12 = !{i32 10000, i64 0, i32 0}
diff --git a/test/Transforms/Inline/inline-hot-callee.ll b/test/Transforms/Inline/inline-hot-callee.ll
index 93ea9d43c78..905625e286d 100644
--- a/test/Transforms/Inline/inline-hot-callee.ll
+++ b/test/Transforms/Inline/inline-hot-callee.ll
@@ -5,7 +5,7 @@
; A cold callee with identical body does not get inlined because cost exceeds the
; inline-threshold
-define i32 @callee1(i32 %x) !prof !1 {
+define i32 @callee1(i32 %x) !prof !20 {
%x1 = add i32 %x, 1
%x2 = add i32 %x1, 1
%x3 = add i32 %x2, 1
@@ -13,7 +13,7 @@ define i32 @callee1(i32 %x) !prof !1 {
ret i32 %x3
}
-define i32 @callee2(i32 %x) !prof !2 {
+define i32 @callee2(i32 %x) !prof !21 {
; CHECK-LABEL: @callee2(
%x1 = add i32 %x, 1
%x2 = add i32 %x1, 1
@@ -22,7 +22,7 @@ define i32 @callee2(i32 %x) !prof !2 {
ret i32 %x3
}
-define i32 @caller2(i32 %y1) !prof !2 {
+define i32 @caller2(i32 %y1) !prof !21 {
; CHECK-LABEL: @caller2(
; CHECK: call i32 @callee2
; CHECK-NOT: call i32 @callee1
@@ -32,8 +32,19 @@ define i32 @caller2(i32 %y1) !prof !2 {
ret i32 %y3
}
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"MaxFunctionCount", i32 10}
-!1 = !{!"function_entry_count", i64 10}
-!2 = !{!"function_entry_count", i64 1}
+!llvm.module.flags = !{!1}
+!20 = !{!"function_entry_count", i64 10}
+!21 = !{!"function_entry_count", i64 1}
+!1 = !{i32 1, !"ProfileSummary", !2}
+!2 = !{!3, !4, !5, !6, !7, !8, !9, !10}
+!3 = !{!"ProfileFormat", !"InstrProf"}
+!4 = !{!"TotalCount", i64 10000}
+!5 = !{!"MaxBlockCount", i64 10}
+!6 = !{!"MaxInternalBlockCount", i64 1}
+!7 = !{!"MaxFunctionCount", i64 10}
+!8 = !{!"NumBlocks", i64 3}
+!9 = !{!"NumFunctions", i64 3}
+!10 = !{!"DetailedSummary", !11}
+!11 = !{!12}
+!12 = !{i32 10000, i64 0, i32 0}
diff --git a/unittests/ProfileData/CMakeLists.txt b/unittests/ProfileData/CMakeLists.txt
index dd39ca7da3a..820c0185508 100644
--- a/unittests/ProfileData/CMakeLists.txt
+++ b/unittests/ProfileData/CMakeLists.txt
@@ -8,5 +8,6 @@ set(LLVM_LINK_COMPONENTS
add_llvm_unittest(ProfileDataTests
CoverageMappingTest.cpp
InstrProfTest.cpp
+ ProfileSummaryTest.cpp
SampleProfTest.cpp
)
diff --git a/unittests/ProfileData/ProfileSummaryTest.cpp b/unittests/ProfileData/ProfileSummaryTest.cpp
new file mode 100644
index 00000000000..46d7162f743
--- /dev/null
+++ b/unittests/ProfileData/ProfileSummaryTest.cpp
@@ -0,0 +1,66 @@
+//===- unittest/ProfileData/ProfileSummaryTest.cpp --------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/IR/Module.h"
+#include "llvm/ProfileData/InstrProf.h"
+#include "llvm/ProfileData/ProfileCommon.h"
+#include "llvm/ProfileData/SampleProf.h"
+#include "gtest/gtest.h"
+
+using namespace llvm;
+using namespace sampleprof;
+
+struct ProfileSummaryTest : ::testing::Test {
+ InstrProfSummary IPS;
+ SampleProfileSummary SPS;
+
+ ProfileSummaryTest()
+ : IPS({100000, 900000, 999999}), SPS({100000, 900000, 999999}) {}
+ void SetUp() {
+ InstrProfRecord Record1("func1", 0x1234, {97531, 5, 99999});
+ InstrProfRecord Record2("func2", 0x1234, {57341, 10000, 10, 1});
+ IPS.addRecord(Record1);
+ IPS.addRecord(Record2);
+
+ IPS.computeDetailedSummary();
+
+ FunctionSamples FooSamples;
+ FooSamples.addTotalSamples(7711);
+ FooSamples.addHeadSamples(610);
+ FooSamples.addBodySamples(1, 0, 610);
+ FooSamples.addBodySamples(2, 0, 600);
+ FooSamples.addBodySamples(4, 0, 60000);
+ FooSamples.addBodySamples(8, 0, 60351);
+ FooSamples.addBodySamples(10, 0, 605);
+
+ FunctionSamples BarSamples;
+ BarSamples.addTotalSamples(20301);
+ BarSamples.addHeadSamples(1437);
+ BarSamples.addBodySamples(1, 0, 1437);
+
+ SPS.addRecord(FooSamples);
+ SPS.addRecord(BarSamples);
+
+ SPS.computeDetailedSummary();
+ }
+
+};
+
+TEST_F(ProfileSummaryTest, summary_from_module) {
+ LLVMContext Context;
+ Module M1("M1", Context);
+ EXPECT_FALSE(ProfileSummary::getProfileSummary(&M1));
+ M1.setProfileSummary(IPS.getMD(Context));
+ EXPECT_TRUE(IPS == *ProfileSummary::getProfileSummary(&M1));
+
+ Module M2("M2", Context);
+ EXPECT_FALSE(ProfileSummary::getProfileSummary(&M2));
+ M2.setProfileSummary(SPS.getMD(Context));
+ EXPECT_TRUE(SPS == *ProfileSummary::getProfileSummary(&M2));
+}