[AutoFDO] Statistic for context sensitive profile guided inlining

Summary: AutoFDO compilation has two places that do inlining - the sample profile loader that does inlining with context sensitive profile, and the regular inliner as CGSCC pass. Ideally we want most inlining to come from sample profile loader as that is driven by context sensitive profile and also retains context sensitivity after inlining. However the reality is most of the inlining actually happens during regular inliner. To track the number of inline instances from sample profile loader and help move more inlining to sample profile loader, I'm adding statistics and optimization remarks for sample profile loader's inlining.

Reviewers: wmi, davidxl

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D70584

1 files changed, 40 insertions, 3 deletions

diff --git a/llvm/lib/Transforms/IPO/SampleProfile.cpp b/llvm/lib/Transforms/IPO/SampleProfile.cpp
index 40bcf43cab2..2b169638d40 100644
--- a/llvm/lib/Transforms/IPO/SampleProfile.cpp
+++ b/llvm/lib/Transforms/IPO/SampleProfile.cpp
@@ -30,6 +30,7 @@
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Twine.h"
@@ -94,6 +95,12 @@ using namespace llvm;
 using namespace sampleprof;
 using ProfileCount = Function::ProfileCount;
 #define DEBUG_TYPE "sample-profile"
+#define CSINLINE_DEBUG DEBUG_TYPE "-inline"
+
+STATISTIC(NumCSInlined,
+          "Number of functions inlined with context sensitive profile");
+STATISTIC(NumCSNotInlined,
+          "Number of functions not inlined with context sensitive profile");
 
 // Command line option to specify the file to read samples from. This is
 // mainly used for debugging.
@@ -330,6 +337,8 @@ protected:
                           DenseSet<GlobalValue::GUID> &InlinedGUIDs);
   // Inline cold/small functions in addition to hot ones
   bool shouldInlineColdCallee(Instruction &CallInst);
+  void emitOptimizationRemarksForInlineCandidates(
+    const SmallVector<Instruction *, 10> &Candidates, const Function &F, bool Hot);
   void printEdgeWeight(raw_ostream &OS, Edge E);
   void printBlockWeight(raw_ostream &OS, const BasicBlock *BB) const;
   void printBlockEquivalence(raw_ostream &OS, const BasicBlock *BB);
@@ -895,15 +904,15 @@ bool SampleProfileLoader::inlineCallInstruction(Instruction *I) {
       getInlineCost(cast<CallBase>(*I), Params, GetTTI(*CalledFunction), GetAC,
                     None, nullptr, nullptr);
   if (Cost.isNever()) {
-    ORE->emit(OptimizationRemark(DEBUG_TYPE, "Not inline", DLoc, BB)
+    ORE->emit(OptimizationRemarkAnalysis(CSINLINE_DEBUG, "InlineFail", DLoc, BB)
               << "incompatible inlining");
     return false;
   }
   InlineFunctionInfo IFI(nullptr, &GetAC);
   if (InlineFunction(CS, IFI)) {
     // The call to InlineFunction erases I, so we can't pass it here.
-    ORE->emit(OptimizationRemark(DEBUG_TYPE, "HotInline", DLoc, BB)
-              << "inlined hot callee '" << ore::NV("Callee", CalledFunction)
+    ORE->emit(OptimizationRemark(CSINLINE_DEBUG, "InlineSuccess", DLoc, BB)
+              << "inlined callee '" << ore::NV("Callee", CalledFunction)
               << "' into '" << ore::NV("Caller", BB->getParent()) << "'");
     return true;
   }
@@ -925,6 +934,22 @@ bool SampleProfileLoader::shouldInlineColdCallee(Instruction &CallInst) {
   return Cost.getCost() <= SampleColdCallSiteThreshold;
 }
 
+void SampleProfileLoader::emitOptimizationRemarksForInlineCandidates(
+    const SmallVector<Instruction *, 10> &Candidates, const Function &F,
+    bool Hot) {
+  for (auto I : Candidates) {
+    Function *CalledFunction = CallSite(I).getCalledFunction();
+    if (CalledFunction) {
+      ORE->emit(OptimizationRemarkAnalysis(CSINLINE_DEBUG, "InlineAttempt", 
+                                           I->getDebugLoc(), I->getParent())
+                << "previous inlining reattempted for "
+                << (Hot ? "hotness: '" : "size: '")
+                << ore::NV("Callee", CalledFunction) << "' into '"
+                << ore::NV("Caller", &F) << "'");
+    }
+  }
+}
+
 /// Iteratively inline hot callsites of a function.
 ///
 /// Iteratively traverse all callsites of the function \p F, and find if
@@ -974,9 +999,11 @@ bool SampleProfileLoader::inlineHotFunctions(
       }
       if (Hot) {
         CIS.insert(CIS.begin(), AllCandidates.begin(), AllCandidates.end());
+        emitOptimizationRemarksForInlineCandidates(AllCandidates, F, true);
       }
       else {
         CIS.insert(CIS.begin(), ColdCandidates.begin(), ColdCandidates.end());
+        emitOptimizationRemarksForInlineCandidates(ColdCandidates, F, false);
       }
     }
     for (auto I : CIS) {
@@ -1022,6 +1049,7 @@ bool SampleProfileLoader::inlineHotFunctions(
                 inlineCallInstruction(DI)) {
               localNotInlinedCallSites.erase(I);
               LocalChanged = true;
+              ++NumCSInlined;
             }
           } else {
             LLVM_DEBUG(dbgs()
@@ -1034,6 +1062,7 @@ bool SampleProfileLoader::inlineHotFunctions(
         if (inlineCallInstruction(I)) {
           localNotInlinedCallSites.erase(I);
           LocalChanged = true;
+          ++NumCSInlined;
         }
       } else if (IsThinLTOPreLink) {
         findCalleeFunctionSamples(*I)->findInlinedFunctions(
@@ -1053,6 +1082,14 @@ bool SampleProfileLoader::inlineHotFunctions(
     Function *Callee = CallSite(I).getCalledFunction();
     if (!Callee || Callee->isDeclaration())
       continue;
+
+    ORE->emit(OptimizationRemarkAnalysis(CSINLINE_DEBUG, "NotInline",
+                                         I->getDebugLoc(), I->getParent())
+              << "previous inlining not repeated: '"
+              << ore::NV("Callee", Callee) << "' into '"
+              << ore::NV("Caller", &F) << "'");
+
+    ++NumCSNotInlined;
     const FunctionSamples *FS = Pair.getSecond();
     if (FS->getTotalSamples() == 0 && FS->getEntrySamples() == 0) {
       continue;