[PGO] early exit if all count values are zero

[xur]

Summary

If all the edge counts for a function are zero, skip count population and annotation, as nothing will happen. This can save some compile time.

[davidxl]

lib/Transforms/Instrumentation/PGOInstrumentation.cpp

1485

Is function entry annotated ?

[xur]

set entry count

[davidxl]

Can you add a simple test case making sure the func entry is properly annotated?

[xur]

Add a testcase.

[davidxl]

lgtm

lib/Transforms/Instrumentation/PGOInstrumentation.cpp

PGOUseFunc(Function &Func, Module *Modu,
              std::unordered_multimap<Comdat *, GlobalValue *> &ComdatMembers,
              BranchProbabilityInfo *BPI = nullptr,
              BlockFrequencyInfo *BFIin = nullptr)
       : F(Func), M(Modu), BFI(BFIin),
         FuncInfo(Func, ComdatMembers, false, BPI, BFIin),
         FreqAttr(FFA_Normal) {}
 
   // Read counts for the instrumented BB from profile.
-  bool readCounters(IndexedInstrProfReader *PGOReader);
+  bool readCounters(IndexedInstrProfReader *PGOReader, bool &AllZeros);
 
   // Populate the counts for all BBs.
   void populateCounters();
 
   // Set the branch weights based on the count values.
   void setBranchWeights();
 
   // Annotate the value profile call sites for all value kind.
public:
   }
 
   Function &getFunc() const { return F; }
 
   void dumpInfo(std::string Str = "") const {
     FuncInfo.dumpInfo(Str);
   }
 
+  uint64_t getProgramMaxCount() const { return ProgramMaxCount; }
 private:
   Function &F;
   Module *M;
   BlockFrequencyInfo *BFI;
 
   // This member stores the shared information with class PGOGenFunc.
   FuncPGOInstrumentation<PGOUseEdge, UseBBInfo> FuncInfo;
 
for (auto &E : Edges) {
     return;
   }
   llvm_unreachable("Cannot find the unknown count edge");
 }
 
 // Read the profile from ProfileFileName and assign the value to the
 // instrumented BB and the edges. This function also updates ProgramMaxCount.
 // Return true if the profile are successfully read, and false on errors.
-bool PGOUseFunc::readCounters(IndexedInstrProfReader *PGOReader) {
+bool PGOUseFunc::readCounters(IndexedInstrProfReader *PGOReader, bool &AllZeros) {
   auto &Ctx = M->getContext();
   Expected<InstrProfRecord> Result =
       PGOReader->getInstrProfRecord(FuncInfo.FuncName, FuncInfo.FunctionHash);
   if (Error E = Result.takeError()) {
     handleAllErrors(std::move(E), [&](const InstrProfError &IPE) {
       auto Err = IPE.get();
       bool SkipWarning = false;
       if (Err == instrprof_error::unknown_function) {
bool PGOUseFunc::readCounters(IndexedInstrProfReader *PGOReader, bool &AllZeros) {
 
   NumOfPGOFunc++;
   LLVM_DEBUG(dbgs() << CountFromProfile.size() << " counts\n");
   uint64_t ValueSum = 0;
   for (unsigned I = 0, S = CountFromProfile.size(); I < S; I++) {
     LLVM_DEBUG(dbgs() << "  " << I << ": " << CountFromProfile[I] << "\n");
     ValueSum += CountFromProfile[I];
   }
+  AllZeros = (ValueSum == 0);
 
   LLVM_DEBUG(dbgs() << "SUM =  " << ValueSum << "\n");
 
   getBBInfo(nullptr).UnknownCountOutEdge = 2;
   getBBInfo(nullptr).UnknownCountInEdge = 2;
 
   setInstrumentedCounts(CountFromProfile);
   ProgramMaxCount = PGOReader->getMaximumFunctionCount();
for (auto &F : M) {
     if (F.isDeclaration())
       continue;
     auto *BPI = LookupBPI(F);
     auto *BFI = LookupBFI(F);
     // Split indirectbr critical edges here before computing the MST rather than
     // later in getInstrBB() to avoid invalidating it.
     SplitIndirectBrCriticalEdges(F, BPI, BFI);
     PGOUseFunc Func(F, &M, ComdatMembers, BPI, BFI);
-    if (!Func.readCounters(PGOReader.get()))
+    bool AllZeros = false;
+    if (!Func.readCounters(PGOReader.get(), AllZeros))
       continue;
+    if (AllZeros) {
+      F.setEntryCount(ProfileCount(0, Function::PCT_Real));
+      if (Func.getProgramMaxCount() != 0)
+        ColdFunctions.push_back(&F);
+      continue;
+    }
     Func.populateCounters();
     Func.setBranchWeights();
     Func.annotateValueSites();
     Func.annotateIrrLoopHeaderWeights();
     PGOUseFunc::FuncFreqAttr FreqAttr = Func.getFuncFreqAttr();
     if (FreqAttr == PGOUseFunc::FFA_Cold)
       ColdFunctions.push_back(&F);
     else if (FreqAttr == PGOUseFunc::FFA_Hot)

test/Transforms/PGOProfile/Inputs/func_entry.proftext

+# IR level Instrumentation Flag
+:ir
+foo
+# Func Hash:
[phone]
+# Num Counters:
+1
+# Counter Values:
+9999
+
+bar
+# Func Hash:
[phone]
+# Num Counters:
+1
+# Counter Values:
+0

test/Transforms/PGOProfile/func_entry.ll

+; RUN: llvm-profdata merge %S/Inputs/func_entry.proftext -o %t.profdata
+; RUN: opt < %s -passes=pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@s = common dso_local local_unnamed_addr global i32 0, align 4
+
+define void @bar() {
+; CHECK-LABEL: @bar
+; CHECK-SAME: !prof ![[FUNC_ENTRY_COUNT_ZERO:[0-9]+]]
+
+entry:
+  store i32 1, i32* @s, align 4
+  ret void
+}
+
+define void @foo() {
+; CHECK-LABEL: @foo
+; CHECK-SAME: !prof ![[FUNC_ENTRY_COUNT_NON_ZERO:[0-9]+]]
+entry:
+  %0 = load i32, i32* @s, align 4
+  %add = add nsw i32 %0, 4
+  store i32 %add, i32* @s, align 4
+  ret void
+}
+
+; USE-DAG: ![[FUNC_ENTRY_COUNT_ZERO]] = !{!"function_entry_count", i64 0}
+; USE-DAG: ![[FUNC_ENTRY_COUNT_NON_ZERO]] = !{!"function_entry_count", i64 9999}