Use ProfileSummaryInfo in inline cost analysis

[eraman]

Summary

Instead of directly using MaxFunctionCount and function entry count to determine callee hotness, use the isHotFunction/isColdFunction methods provided by ProfileSummaryInfo. NFC.

[silvas]

Strictly speaking, I don't think this is NFC (e.g. it required changing the tests). But it seems straightforward enough.

[davidxl]

nice cleanup!

[eraman]

In D21045#450495, @silvas wrote:

Strictly speaking, I don't think this is NFC (e.g. it required changing the tests). But it seems straightforward enough.

Sorry, I meant it in the sense of it doesn't change the functionality of inliner.

David, IIRC patches need an explicit LGTM before submitting and accepting the patch in phabricator is not enough.

[davidxl]

lgtm

llvm/trunk/include/llvm/Analysis/InlineCost.h

 #include <cassert>
 #include <climits>
 
 namespace llvm {
 class AssumptionCacheTracker;
 class CallSite;
 class DataLayout;
 class Function;
+class ProfileSummaryInfo;
 class TargetTransformInfo;
 
 namespace InlineConstants {
   // Various magic constants used to adjust heuristics.
   const int InstrCost = 5;
   const int IndirectCallThreshold = 100;
   const int CallPenalty = 25;
   const int LastCallToStaticBonus = -15000;

 /// new threshold are computed with any accuracy. The new threshold can be
 /// used to bound the computation necessary to determine whether the cost is
 /// sufficiently low to warrant inlining.
 ///
 /// Also note that calling this function *dynamically* computes the cost of
 /// inlining the callsite. It is an expensive, heavyweight call.
 InlineCost getInlineCost(CallSite CS, int DefaultThreshold,
                          TargetTransformInfo &CalleeTTI,
-                         AssumptionCacheTracker *ACT);
+                         AssumptionCacheTracker *ACT, ProfileSummaryInfo *PSI);
 
 /// \brief Get an InlineCost with the callee explicitly specified.
 /// This allows you to calculate the cost of inlining a function via a
 /// pointer. This behaves exactly as the version with no explicit callee
 /// parameter in all other respects.
 //
 InlineCost getInlineCost(CallSite CS, Function *Callee, int DefaultThreshold,
                          TargetTransformInfo &CalleeTTI,
-                         AssumptionCacheTracker *ACT);
+                         AssumptionCacheTracker *ACT, ProfileSummaryInfo *PSI);
 
 int computeThresholdFromOptLevels(unsigned OptLevel, unsigned SizeOptLevel);
 
 /// \brief Return the default value of -inline-threshold.
 int getDefaultInlineThreshold();
 
 /// \brief Minimal filter to detect invalid constructs for inlining.
 bool isInlineViable(Function &Callee);
 }
 
 #endif

llvm/trunk/include/llvm/Transforms/IPO/InlinerPass.h

 
 #include "llvm/Analysis/CallGraphSCCPass.h"
 
 namespace llvm {
 class AssumptionCacheTracker;
 class CallSite;
 class DataLayout;
 class InlineCost;
+class ProfileSummaryInfo;
 template <class PtrType, unsigned SmallSize> class SmallPtrSet;
 
 /// Inliner - This class contains all of the helper code which is used to
 /// perform the inlining operations that do not depend on the policy.
 ///
 struct Inliner : public CallGraphSCCPass {
   explicit Inliner(char &ID);
   explicit Inliner(char &ID, bool InsertLifetime);
private:
   /// estimated inline cost associated with callsite \p CS.
   /// \p TotalAltCost will be set to the estimated cost of inlining the caller
   /// if \p CS is suppressed for inlining.
   bool shouldBeDeferred(Function *Caller, CallSite CS, InlineCost IC,
                         int &TotalAltCost);
 
 protected:
   AssumptionCacheTracker *ACT;
+  ProfileSummaryInfo *PSI;
 };
 
 } // End llvm namespace
 
 #endif

llvm/trunk/lib/Analysis/InlineCost.cpp

 #include "llvm/ADT/SetVector.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/AssumptionCache.h"
 #include "llvm/Analysis/CodeMetrics.h"
 #include "llvm/Analysis/ConstantFolding.h"
 #include "llvm/Analysis/InstructionSimplify.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/CallingConv.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/GetElementPtrTypeIterator.h"
 #include "llvm/IR/GlobalAlias.h"
 #include "llvm/IR/InstVisitor.h"
 #include "llvm/IR/IntrinsicInst.h"
class CallAnalyzer : public InstVisitor<CallAnalyzer, bool> {
   friend class InstVisitor<CallAnalyzer, bool>;
 
   /// The TargetTransformInfo available for this compilation.
   const TargetTransformInfo &TTI;
 
   /// The cache of @llvm.assume intrinsics.
   AssumptionCacheTracker *ACT;
 
+  /// Profile summary information.
+  ProfileSummaryInfo *PSI;
+
   // The called function.
   Function &F;
 
   // The candidate callsite being analyzed. Please do not use this to do
   // analysis in the caller function; we want the inline cost query to be
   // easily cacheable. Instead, use the cover function paramHasAttr.
   CallSite CandidateCS;
 
class CallAnalyzer : public InstVisitor<CallAnalyzer, bool> {
   bool visitIndirectBrInst(IndirectBrInst &IBI);
   bool visitResumeInst(ResumeInst &RI);
   bool visitCleanupReturnInst(CleanupReturnInst &RI);
   bool visitCatchReturnInst(CatchReturnInst &RI);
   bool visitUnreachableInst(UnreachableInst &I);
 
 public:
   CallAnalyzer(const TargetTransformInfo &TTI, AssumptionCacheTracker *ACT,
-               Function &Callee, int Threshold, CallSite CSArg)
-      : TTI(TTI), ACT(ACT), F(Callee), CandidateCS(CSArg), Threshold(Threshold),
-        Cost(0), IsCallerRecursive(false), IsRecursiveCall(false),
-        ExposesReturnsTwice(false), HasDynamicAlloca(false),
-        ContainsNoDuplicateCall(false), HasReturn(false), HasIndirectBr(false),
-        HasFrameEscape(false), AllocatedSize(0), NumInstructions(0),
-        NumVectorInstructions(0), FiftyPercentVectorBonus(0),
-        TenPercentVectorBonus(0), VectorBonus(0), NumConstantArgs(0),
-        NumConstantOffsetPtrArgs(0), NumAllocaArgs(0), NumConstantPtrCmps(0),
-        NumConstantPtrDiffs(0), NumInstructionsSimplified(0),
-        SROACostSavings(0), SROACostSavingsLost(0) {}
+               ProfileSummaryInfo *PSI, Function &Callee, int Threshold,
+               CallSite CSArg)
+      : TTI(TTI), ACT(ACT), PSI(PSI), F(Callee), CandidateCS(CSArg),
+        Threshold(Threshold), Cost(0), IsCallerRecursive(false),
+        IsRecursiveCall(false), ExposesReturnsTwice(false),
+        HasDynamicAlloca(false), ContainsNoDuplicateCall(false),
+        HasReturn(false), HasIndirectBr(false), HasFrameEscape(false),
+        AllocatedSize(0), NumInstructions(0), NumVectorInstructions(0),
+        FiftyPercentVectorBonus(0), TenPercentVectorBonus(0), VectorBonus(0),
+        NumConstantArgs(0), NumConstantOffsetPtrArgs(0), NumAllocaArgs(0),
+        NumConstantPtrCmps(0), NumConstantPtrDiffs(0),
+        NumInstructionsSimplified(0), SROACostSavings(0),
+        SROACostSavingsLost(0) {}
 
   bool analyzeCall(CallSite CS);
 
   int getThreshold() { return Threshold; }
   int getCost() { return Cost; }
 
   // Keep a bunch of stats about the cost savings found so we can print them
   // out when debugging.
if (DefaultInlineThreshold.getNumOccurrences() > 0) {
     // If -inline-threshold is not given, listen to the optsize and minsize
     // attributes when they would decrease the threshold.
     if (Caller->optForMinSize() && OptMinSizeThreshold < Threshold)
       Threshold = OptMinSizeThreshold;
     else if (Caller->optForSize() && OptSizeThreshold < Threshold)
       Threshold = OptSizeThreshold;
   }
 
-  // If profile information is available, use that to adjust threshold of hot
-  // and cold functions.
-  // FIXME: The heuristic used below for determining hotness and coldness are
-  // based on preliminary SPEC tuning and may not be optimal. Replace this with
-  // 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()) {
-    HasPGOCounts = true;
-    FunctionCount = Callee.getEntryCount().getValue();
-    MaxFunctionCount = Callee.getParent()->getMaximumFunctionCount().getValue();
-  }
-
   // Listen to the inlinehint attribute or profile based hotness information
   // when it would increase the threshold and the caller does not need to
   // minimize its size.
-  bool InlineHint =
-      Callee.hasFnAttribute(Attribute::InlineHint) ||
-      (HasPGOCounts &&
-       FunctionCount >= (uint64_t)(0.3 * (double)MaxFunctionCount));
+  bool InlineHint = Callee.hasFnAttribute(Attribute::InlineHint) ||
+                    PSI->isHotFunction(&Callee);
   if (InlineHint && HintThreshold > Threshold && !Caller->optForMinSize())
     Threshold = HintThreshold;
 
-  // Listen to the cold attribute or profile based coldness information
-  // when it would decrease the threshold.
-  bool ColdCallee =
-      Callee.hasFnAttribute(Attribute::Cold) ||
-      (HasPGOCounts &&
-       FunctionCount <= (uint64_t)(0.01 * (double)MaxFunctionCount));
+  bool ColdCallee = PSI->isColdFunction(&Callee);
   // Command line argument for DefaultInlineThreshold will override the default
   // ColdThreshold. If we have -inline-threshold but no -inlinecold-threshold,
   // do not use the default cold threshold even if it is smaller.
   if ((DefaultInlineThreshold.getNumOccurrences() == 0 ||
        ColdThreshold.getNumOccurrences() > 0) &&
       ColdCallee && ColdThreshold < Threshold)
     Threshold = ColdThreshold;
 
bool CallAnalyzer::visitCallSite(CallSite CS) {
   if (!F)
     return Base::visitCallSite(CS);
 
   // If we have a constant that we are calling as a function, we can peer
   // through it and see the function target. This happens not infrequently
   // during devirtualization and so we want to give it a hefty bonus for
   // inlining, but cap that bonus in the event that inlining wouldn't pan
   // out. Pretend to inline the function, with a custom threshold.
-  CallAnalyzer CA(TTI, ACT, *F, InlineConstants::IndirectCallThreshold, CS);
+  CallAnalyzer CA(TTI, ACT, PSI, *F, InlineConstants::IndirectCallThreshold,
+                  CS);
   if (CA.analyzeCall(CS)) {
     // We were able to inline the indirect call! Subtract the cost from the
     // threshold to get the bonus we want to apply, but don't go below zero.
     Cost -= std::max(0, CA.getThreshold() - CA.getCost());
   }
 
   return Base::visitCallSite(CS);
 }
static bool functionsHaveCompatibleAttributes(Function *Caller,
                                               Function *Callee,
                                               TargetTransformInfo &TTI) {
   return TTI.areInlineCompatible(Caller, Callee) &&
          AttributeFuncs::areInlineCompatible(*Caller, *Callee);
 }
 
 InlineCost llvm::getInlineCost(CallSite CS, int DefaultThreshold,
                                TargetTransformInfo &CalleeTTI,
-                               AssumptionCacheTracker *ACT) {
+                               AssumptionCacheTracker *ACT,
+                               ProfileSummaryInfo *PSI) {
   return getInlineCost(CS, CS.getCalledFunction(), DefaultThreshold, CalleeTTI,
-                       ACT);
+                       ACT, PSI);
 }
 
 int llvm::computeThresholdFromOptLevels(unsigned OptLevel,
                                         unsigned SizeOptLevel) {
   if (OptLevel > 2)
     return OptAggressiveThreshold;
   if (SizeOptLevel == 1) // -Os
     return OptSizeThreshold;
   if (SizeOptLevel == 2) // -Oz
     return OptMinSizeThreshold;
   return DefaultInlineThreshold;
 }
 
 int llvm::getDefaultInlineThreshold() { return DefaultInlineThreshold; }
 
 InlineCost llvm::getInlineCost(CallSite CS, Function *Callee,
                                int DefaultThreshold,
                                TargetTransformInfo &CalleeTTI,
-                               AssumptionCacheTracker *ACT) {
+                               AssumptionCacheTracker *ACT,
+                               ProfileSummaryInfo *PSI) {
 
   // Cannot inline indirect calls.
   if (!Callee)
     return llvm::InlineCost::getNever();
 
   // Calls to functions with always-inline attributes should be inlined
   // whenever possible.
   if (CS.hasFnAttr(Attribute::AlwaysInline)) {
InlineCost llvm::getInlineCost(CallSite CS, Function *Callee,
   // we have *a* correct implementation of the source level function.
   if (Callee->isInterposable() || Callee->hasFnAttribute(Attribute::NoInline) ||
       CS.isNoInline())
     return llvm::InlineCost::getNever();
 
   DEBUG(llvm::dbgs() << "      Analyzing call of " << Callee->getName()
                      << "...\n");
 
-  CallAnalyzer CA(CalleeTTI, ACT, *Callee, DefaultThreshold, CS);
+  CallAnalyzer CA(CalleeTTI, ACT, PSI, *Callee, DefaultThreshold, CS);
   bool ShouldInline = CA.analyzeCall(CS);
 
   DEBUG(CA.dump());
 
   // Check if there was a reason to force inlining or no inlining.
   if (!ShouldInline && CA.getCost() < CA.getThreshold())
     return InlineCost::getNever();
   if (ShouldInline && CA.getCost() >= CA.getThreshold())

llvm/trunk/lib/Transforms/IPO/InlineAlways.cpp

 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Transforms/IPO.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/Analysis/AssumptionCache.h"
 #include "llvm/Analysis/CallGraph.h"
 #include "llvm/Analysis/InlineCost.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/CallingConv.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/Type.h"

 
 }
 
 char AlwaysInliner::ID = 0;
 INITIALIZE_PASS_BEGIN(AlwaysInliner, "always-inline",
                 "Inliner for always_inline functions", false, false)
 INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
 INITIALIZE_PASS_DEPENDENCY(CallGraphWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
 INITIALIZE_PASS_END(AlwaysInliner, "always-inline",
                 "Inliner for always_inline functions", false, false)
 
 Pass *llvm::createAlwaysInlinerPass() { return new AlwaysInliner(); }
 
 Pass *llvm::createAlwaysInlinerPass(bool InsertLifetime) {
   return new AlwaysInliner(InsertLifetime);

llvm/trunk/lib/Transforms/IPO/InlineSimple.cpp

 //===- InlineSimple.cpp - Code to perform simple function inlining --------===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
 // This file implements bottom-up inlining of functions into callees.
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Analysis/AssumptionCache.h"
 #include "llvm/Analysis/CallGraph.h"
 #include "llvm/Analysis/InlineCost.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/CallingConv.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Module.h"
explicit SimpleInliner(int Threshold)
     initializeSimpleInlinerPass(*PassRegistry::getPassRegistry());
   }
 
   static char ID; // Pass identification, replacement for typeid
 
   InlineCost getInlineCost(CallSite CS) override {
     Function *Callee = CS.getCalledFunction();
     TargetTransformInfo &TTI = TTIWP->getTTI(*Callee);
-    return llvm::getInlineCost(CS, DefaultThreshold, TTI, ACT);
+    return llvm::getInlineCost(CS, DefaultThreshold, TTI, ACT, PSI);
   }
 
   bool runOnSCC(CallGraphSCC &SCC) override;
   void getAnalysisUsage(AnalysisUsage &AU) const override;
 
 private:
   TargetTransformInfoWrapperPass *TTIWP;
 };
 
 } // end anonymous namespace
 
 char SimpleInliner::ID = 0;
 INITIALIZE_PASS_BEGIN(SimpleInliner, "inline",
                 "Function Integration/Inlining", false, false)
 INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
 INITIALIZE_PASS_DEPENDENCY(CallGraphWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
 INITIALIZE_PASS_END(SimpleInliner, "inline",
                 "Function Integration/Inlining", false, false)
 
 Pass *llvm::createFunctionInliningPass() { return new SimpleInliner(); }
 
 Pass *llvm::createFunctionInliningPass(int Threshold) {

llvm/trunk/lib/Transforms/IPO/Inliner.cpp

 
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/AliasAnalysis.h"
 #include "llvm/Analysis/AssumptionCache.h"
 #include "llvm/Analysis/BasicAliasAnalysis.h"
 #include "llvm/Analysis/CallGraph.h"
 #include "llvm/Analysis/InlineCost.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/Debug.h"

 Inliner::Inliner(char &ID, bool InsertLifetime)
     : CallGraphSCCPass(ID), InsertLifetime(InsertLifetime) {}
 
 /// For this class, we declare that we require and preserve the call graph.
 /// If the derived class implements this method, it should
 /// always explicitly call the implementation here.
 void Inliner::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.addRequired<AssumptionCacheTracker>();
+  AU.addRequired<ProfileSummaryInfoWrapperPass>();
   AU.addRequired<TargetLibraryInfoWrapperPass>();
   getAAResultsAnalysisUsage(AU);
   CallGraphSCCPass::getAnalysisUsage(AU);
 }
 
 
 typedef DenseMap<ArrayType*, std::vector<AllocaInst*> >
 InlinedArrayAllocasTy;
bool Inliner::runOnSCC(CallGraphSCC &SCC) {
   if (skipSCC(SCC))
     return false;
   return inlineCalls(SCC);
 }
 
 bool Inliner::inlineCalls(CallGraphSCC &SCC) {
   CallGraph &CG = getAnalysis<CallGraphWrapperPass>().getCallGraph();
   ACT = &getAnalysis<AssumptionCacheTracker>();
+  PSI = getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI(CG.getModule());
   auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
 
   SmallPtrSet<Function*, 8> SCCFunctions;
   DEBUG(dbgs() << "Inliner visiting SCC:");
   for (CallGraphNode *Node : SCC) {
     Function *F = Node->getFunction();
     if (F) SCCFunctions.insert(F);
     DEBUG(dbgs() << " " << (F ? F->getName() : "INDIRECTNODE"));

llvm/trunk/test/Transforms/Inline/inline-cold-callee.ll

 ; RUN: opt < %s -inline  -inlinecold-threshold=0 -S | FileCheck %s
 
 ; This tests that a cold callee gets the (lower) inlinecold-threshold even without
 ; Cold hint and does not get inlined because the cost exceeds the inlinecold-threshold.
 ; 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
 
   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
   %x3 = add i32 %x2, 1
 
   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
 ; CHECK: ret i32 %x3.i
   %y2 = call i32 @callee2(i32 %y1)
   %y3 = call i32 @callee1(i32 %y2)
   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 = !{!"MaxCount", i64 1000}
+!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}

llvm/trunk/test/Transforms/Inline/inline-hot-callee.ll

 ; RUN: opt < %s -inline -inline-threshold=0 -inlinehint-threshold=100 -S | FileCheck %s
 
 ; This tests that a hot callee gets the (higher) inlinehint-threshold even without
 ; inline hints and gets inlined because the cost is less than inlinehint-threshold.
 ; 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 !21 {
   %x1 = add i32 %x, 1
   %x2 = add i32 %x1, 1
   %x3 = add i32 %x2, 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
   %x3 = add i32 %x2, 1
 
   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
 ; CHECK: ret i32 %x3.i
   %y2 = call i32 @callee2(i32 %y1)
   %y3 = call i32 @callee1(i32 %y2)
   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}
+!21 = !{!"function_entry_count", i64 300}
+!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 = !{!"MaxCount", i64 1000}
+!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}