[ProfileData] Add a variant of getValueProfDataFromInst (#95993)

This patch adds a variant of getValueProfDataFromInst that returns
std::vector<InstrProfValueData> instead of
std::unique<InstrProfValueData[]>.  The new return type carries the
length with it, so we can drop out parameter ActualNumValueData.
Also, the caller can directly feed the return value into a range-based
for loop as shown in the patch.

I'm planning to migrate other callers of getValueProfDataFromInst to
the new variant in follow-up patches.

3 files changed, 52 insertions, 11 deletions

diff --git a/llvm/include/llvm/ProfileData/InstrProf.h b/llvm/include/llvm/ProfileData/InstrProf.h
index d5ddf169..9bb1d8c 100644
--- a/llvm/include/llvm/ProfileData/InstrProf.h
+++ b/llvm/include/llvm/ProfileData/InstrProf.h
@@ -294,6 +294,13 @@ getValueProfDataFromInst(const Instruction &Inst, InstrProfValueKind ValueKind,
                          uint32_t MaxNumValueData, uint32_t &ActualNumValueData,
                          uint64_t &TotalC, bool GetNoICPValue = false);
 
+/// Extract the value profile data from \p Inst and returns them if \p Inst is
+/// annotated with value profile data. Returns an empty vector otherwise.
+SmallVector<InstrProfValueData, 4>
+getValueProfDataFromInst(const Instruction &Inst, InstrProfValueKind ValueKind,
+                         uint32_t MaxNumValueData, uint64_t &TotalC,
+                         bool GetNoICPValue = false);
+
 inline StringRef getPGOFuncNameMetadataName() { return "PGOFuncName"; }
 
 /// Return the PGOFuncName meta data associated with a function.
diff --git a/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp b/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp
index c6934f5..94ac048 100644
--- a/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp
+++ b/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp
@@ -143,20 +143,15 @@ static bool findRefEdges(ModuleSummaryIndex &Index, const User *CurUser,
 
   const Instruction *I = dyn_cast<Instruction>(CurUser);
   if (I) {
-    uint32_t ActualNumValueData = 0;
     uint64_t TotalCount = 0;
     // MaxNumVTableAnnotations is the maximum number of vtables annotated on
     // the instruction.
-    auto ValueDataArray =
-        getValueProfDataFromInst(*I, IPVK_VTableTarget, MaxNumVTableAnnotations,
-                                 ActualNumValueData, TotalCount);
-
-    if (ValueDataArray.get()) {
-      for (uint32_t j = 0; j < ActualNumValueData; j++) {
-        RefEdges.insert(Index.getOrInsertValueInfo(/* VTableGUID = */
-                                                   ValueDataArray[j].Value));
-      }
-    }
+    auto ValueDataArray = getValueProfDataFromInst(
+        *I, IPVK_VTableTarget, MaxNumVTableAnnotations, TotalCount);
+
+    for (const auto &V : ValueDataArray)
+      RefEdges.insert(Index.getOrInsertValueInfo(/* VTableGUID = */
+                                                 V.Value));
   }
   return HasBlockAddress;
 }
diff --git a/llvm/lib/ProfileData/InstrProf.cpp b/llvm/lib/ProfileData/InstrProf.cpp
index 3e0e2b2..c7749f3 100644
--- a/llvm/lib/ProfileData/InstrProf.cpp
+++ b/llvm/lib/ProfileData/InstrProf.cpp
@@ -1382,6 +1382,45 @@ getValueProfDataFromInst(const Instruction &Inst, InstrProfValueKind ValueKind,
   return ValueDataArray;
 }
 
+SmallVector<InstrProfValueData, 4>
+getValueProfDataFromInst(const Instruction &Inst, InstrProfValueKind ValueKind,
+                         uint32_t MaxNumValueData, uint64_t &TotalC,
+                         bool GetNoICPValue) {
+  // Four inline elements seem to work well in practice.  With MaxNumValueData,
+  // this array won't grow very big anyway.
+  SmallVector<InstrProfValueData, 4> ValueData;
+  MDNode *MD = mayHaveValueProfileOfKind(Inst, ValueKind);
+  if (!MD)
+    return ValueData;
+  const unsigned NOps = MD->getNumOperands();
+  // Get total count
+  ConstantInt *TotalCInt = mdconst::dyn_extract<ConstantInt>(MD->getOperand(2));
+  if (!TotalCInt)
+    return ValueData;
+  TotalC = TotalCInt->getZExtValue();
+
+  ValueData.reserve((NOps - 3) / 2);
+  for (unsigned I = 3; I < NOps; I += 2) {
+    if (ValueData.size() >= MaxNumValueData)
+      break;
+    ConstantInt *Value = mdconst::dyn_extract<ConstantInt>(MD->getOperand(I));
+    ConstantInt *Count =
+        mdconst::dyn_extract<ConstantInt>(MD->getOperand(I + 1));
+    if (!Value || !Count) {
+      ValueData.clear();
+      return ValueData;
+    }
+    uint64_t CntValue = Count->getZExtValue();
+    if (!GetNoICPValue && (CntValue == NOMORE_ICP_MAGICNUM))
+      continue;
+    InstrProfValueData V;
+    V.Value = Value->getZExtValue();
+    V.Count = CntValue;
+    ValueData.push_back(V);
+  }
+  return ValueData;
+}
+
 MDNode *getPGOFuncNameMetadata(const Function &F) {
   return F.getMetadata(getPGOFuncNameMetadataName());
 }