Add function importing info from samplepgo profile to the module summary.

Summary: For SamplePGO, the profile may contain cross-module inline stacks. As we need to make sure the profile annotation happens when all the hot inline stacks are expanded, we need to pass this info to the module importer so that it can import proper functions if necessary. This patch implemented this feature by emitting cross-module targets as part of function entry metadata. In the module-summary phase, the metadata is used to build call edges that points to functions need to be imported.

Reviewers: mehdi_amini, tejohnson

Reviewed By: tejohnson

Subscribers: davidxl, llvm-commits

Differential Revision: https://reviews.llvm.org/D30053

llvm-svn: 296498

1 files changed, 19 insertions, 8 deletions

diff --git a/llvm/lib/Transforms/IPO/SampleProfile.cpp b/llvm/lib/Transforms/IPO/SampleProfile.cpp
index ad057d50cc3..a9f5b0333c5 100644
--- a/llvm/lib/Transforms/IPO/SampleProfile.cpp
+++ b/llvm/lib/Transforms/IPO/SampleProfile.cpp
@@ -163,7 +163,8 @@ protected:
   ErrorOr<uint64_t> getBlockWeight(const BasicBlock *BB);
   const FunctionSamples *findCalleeFunctionSamples(const Instruction &I) const;
   const FunctionSamples *findFunctionSamples(const Instruction &I) const;
-  bool inlineHotFunctions(Function &F);
+  bool inlineHotFunctions(Function &F,
+                          DenseSet<GlobalValue::GUID> &ImportGUIDs);
   void printEdgeWeight(raw_ostream &OS, Edge E);
   void printBlockWeight(raw_ostream &OS, const BasicBlock *BB) const;
   void printBlockEquivalence(raw_ostream &OS, const BasicBlock *BB);
@@ -604,9 +605,12 @@ SampleProfileLoader::findFunctionSamples(const Instruction &Inst) const {
 /// it to direct call. Each indirect call is limited with a single target.
 ///
 /// \param F function to perform iterative inlining.
+/// \param ImportGUIDs a set to be updated to include all GUIDs that come
+///     from a different module but inlined in the profiled binary.
 ///
 /// \returns True if there is any inline happened.
-bool SampleProfileLoader::inlineHotFunctions(Function &F) {
+bool SampleProfileLoader::inlineHotFunctions(
+    Function &F, DenseSet<GlobalValue::GUID> &ImportGUIDs) {
   DenseSet<Instruction *> PromotedInsns;
   bool Changed = false;
   LLVMContext &Ctx = F.getContext();
@@ -655,8 +659,12 @@ bool SampleProfileLoader::inlineHotFunctions(Function &F) {
           continue;
         }
       }
-      if (!CalledFunction || !CalledFunction->getSubprogram())
+      if (!CalledFunction || !CalledFunction->getSubprogram()) {
+        findCalleeFunctionSamples(*I)->findImportedFunctions(
+            ImportGUIDs, F.getParent(),
+            Samples->getTotalSamples() * SampleProfileHotThreshold / 100);
         continue;
+      }
       DebugLoc DLoc = I->getDebugLoc();
       uint64_t NumSamples = findCalleeFunctionSamples(*I)->getTotalSamples();
       if (InlineFunction(CallSite(DI), IFI)) {
@@ -1041,10 +1049,6 @@ void SampleProfileLoader::propagateWeights(Function &F) {
   bool Changed = true;
   unsigned I = 0;
 
-  // Add an entry count to the function using the samples gathered
-  // at the function entry.
-  F.setEntryCount(Samples->getHeadSamples() + 1);
-
   // If BB weight is larger than its corresponding loop's header BB weight,
   // use the BB weight to replace the loop header BB weight.
   for (auto &BI : F) {
@@ -1273,12 +1277,19 @@ bool SampleProfileLoader::emitAnnotations(Function &F) {
   DEBUG(dbgs() << "Line number for the first instruction in " << F.getName()
                << ": " << getFunctionLoc(F) << "\n");
 
-  Changed |= inlineHotFunctions(F);
+  DenseSet<GlobalValue::GUID> ImportGUIDs;
+  Changed |= inlineHotFunctions(F, ImportGUIDs);
 
   // Compute basic block weights.
   Changed |= computeBlockWeights(F);
 
   if (Changed) {
+    // Add an entry count to the function using the samples gathered at the
+    // function entry. Also sets the GUIDs that comes from a different
+    // module but inlined in the profiled binary. This is aiming at making
+    // the IR match the profiled binary before annotation.
+    F.setEntryCount(Samples->getHeadSamples() + 1, &ImportGUIDs);
+
     // Compute dominance and loop info needed for propagation.
     computeDominanceAndLoopInfo(F);