We can improve the performance (generally) by memo-izing the action to map a debug location to its function summary.

Summary:
Here are timings (as reported by "opt -time-passes") for
sample-profile pass for some files holding hot functions from a major
service©r. Average 17% reduction. Delta column is 100*(old-new)/old.

```
Old    New    Delta
0.0537 0.0538 -0.2%
0.8155 0.6522 20.0%
0.0779 0.0751  3.6%
0.0727 0.0913 -25.6%
0.1622 0.1302 19.7%
0.0627 0.0594  5.3%
0.0766 0.0744  2.9%
0.6426 0.4387 31.7%
0.3521 0.2776 21.2%
0.3549 0.2721 23.3%
0.0912 0.0904  0.9%
0.1236 0.1059 14.3%
0.0854 0.0866 -1.4%
0.0757 0.0722  4.6%
0.1293 0.1147 11.3%
0.1354 0.1122 17.1%
0.0767 0.0770 -0.4%
0.1135 0.0968 14.7%
0.0524 0.0608 -16.0%
0.1279 0.1106 13.5%
==========
3.6820 3.0520 17.1% Total
```

Reviewers: twoh, Kader, danielcdh, wmi

Reviewed By: wmi

Subscribers: dblaikie, llvm-commits

Differential Revision: https://reviews.llvm.org/D56435

1 files changed, 7 insertions, 2 deletions

diff --git a/llvm/lib/Transforms/IPO/SampleProfile.cpp b/llvm/lib/Transforms/IPO/SampleProfile.cpp
index 1e86e04a79d..9f123c2b875 100644
--- a/llvm/lib/Transforms/IPO/SampleProfile.cpp
+++ b/llvm/lib/Transforms/IPO/SampleProfile.cpp
@@ -218,6 +218,7 @@ protected:
   const FunctionSamples *findCalleeFunctionSamples(const Instruction &I) const;
   std::vector<const FunctionSamples *>
   findIndirectCallFunctionSamples(const Instruction &I, uint64_t &Sum) const;
+  mutable DenseMap<const DILocation *, const FunctionSamples *> DILocation2SampleMap;
   const FunctionSamples *findFunctionSamples(const Instruction &I) const;
   bool inlineCallInstruction(Instruction *I);
   bool inlineHotFunctions(Function &F,
@@ -719,12 +720,14 @@ SampleProfileLoader::findIndirectCallFunctionSamples(
 /// \returns the FunctionSamples pointer to the inlined instance.
 const FunctionSamples *
 SampleProfileLoader::findFunctionSamples(const Instruction &Inst) const {
-  SmallVector<std::pair<LineLocation, StringRef>, 10> S;
   const DILocation *DIL = Inst.getDebugLoc();
   if (!DIL)
     return Samples;
 
-  return Samples->findFunctionSamples(DIL);
+  auto it = DILocation2SampleMap.try_emplace(DIL,nullptr);
+  if (it.second)
+    it.first->second = Samples->findFunctionSamples(DIL);
+  return it.first->second;
 }
 
 bool SampleProfileLoader::inlineCallInstruction(Instruction *I) {
@@ -1610,6 +1613,8 @@ bool SampleProfileLoaderLegacyPass::runOnModule(Module &M) {
 }
 
 bool SampleProfileLoader::runOnFunction(Function &F, ModuleAnalysisManager *AM) {
+  
+  DILocation2SampleMap.clear();
   // By default the entry count is initialized to -1, which will be treated
   // conservatively by getEntryCount as the same as unknown (None). This is
   // to avoid newly added code to be treated as cold. If we have samples