Merging r258616:

[oota-llvm.git] / lib / Transforms / IPO / Inliner.cpp

diff --git a/lib/Transforms/IPO/Inliner.cpp b/lib/Transforms/IPO/Inliner.cpp
index 20b385ae8201302a43bbaace073ce507eebb5590..bbe5f8761d5f1d3179af864ee995d1de8e9b3dde 100644 (file)
--- a/lib/Transforms/IPO/Inliner.cpp
+++ b/lib/Transforms/IPO/Inliner.cpp
@@ -65,13 +65,15 @@ ColdThreshold("inlinecold-threshold", cl::Hidden, cl::init(225),
 // Threshold to use when optsize is specified (and there is no -inline-limit).
 const int OptSizeThreshold = 75;
 
-Inliner::Inliner(char &ID) 
-  : CallGraphSCCPass(ID), InlineThreshold(InlineLimit), InsertLifetime(true) {}
+Inliner::Inliner(char &ID)
+    : CallGraphSCCPass(ID), InlineThreshold(InlineLimit), InsertLifetime(true) {
+}
 
 Inliner::Inliner(char &ID, int Threshold, bool InsertLifetime)
-  : CallGraphSCCPass(ID), InlineThreshold(InlineLimit.getNumOccurrences() > 0 ?
-                                          InlineLimit : Threshold),
-    InsertLifetime(InsertLifetime) {}
+    : CallGraphSCCPass(ID),
+      InlineThreshold(InlineLimit.getNumOccurrences() > 0 ? InlineLimit
+                                                          : Threshold),
+      InsertLifetime(InsertLifetime) {}
 
 /// For this class, we declare that we require and preserve the call graph.
 /// If the derived class implements this method, it should
@@ -255,18 +257,42 @@ unsigned Inliner::getInlineThreshold(CallSite CS) const {
       OptSizeThreshold < Threshold)
     Threshold = OptSizeThreshold;
 
-  // Listen to the inlinehint attribute when it would increase the threshold
-  // and the caller does not need to minimize its size.
   Function *Callee = CS.getCalledFunction();
-  bool InlineHint = Callee && !Callee->isDeclaration() &&
-                    Callee->hasFnAttribute(Attribute::InlineHint);
+  if (!Callee || Callee->isDeclaration())
+    return Threshold;
+
+  // 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));
   if (InlineHint && HintThreshold > Threshold &&
       !Caller->hasFnAttribute(Attribute::MinSize))
     Threshold = HintThreshold;
 
-  // Listen to the cold attribute when it would decrease the threshold.
-  bool ColdCallee = Callee && !Callee->isDeclaration() &&
-                    Callee->hasFnAttribute(Attribute::Cold);
+  // 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));
   // Command line argument for InlineLimit 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.
@@ -415,7 +441,7 @@ static bool InlineHistoryIncludes(Function *F, int InlineHistoryID,
 
 bool Inliner::runOnSCC(CallGraphSCC &SCC) {
   CallGraph &CG = getAnalysis<CallGraphWrapperPass>().getCallGraph();
-  AssumptionCacheTracker *ACT = &getAnalysis<AssumptionCacheTracker>();
+  ACT = &getAnalysis<AssumptionCacheTracker>();
   auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
 
   SmallPtrSet<Function*, 8> SCCFunctions;