[llvm] 351d234 - [OpenMPOpt] Most SCC's are uninteresting, don't waste time on them (up to 16x faster)

[Roman Lebedev via llvm-commits]

Author: Roman Lebedev
Date: 2020-07-27T23:36:34+03:00
New Revision: 351d234d866ea441d8f8ad1e9b483a98fd51da19

URL: https://github.com/llvm/llvm-project/commit/351d234d866ea441d8f8ad1e9b483a98fd51da19
DIFF: https://github.com/llvm/llvm-project/commit/351d234d866ea441d8f8ad1e9b483a98fd51da19.diff

LOG: [OpenMPOpt] Most SCC's are uninteresting, don't waste time on them (up to 16x faster)

Summary:
This seems obvious in hindsight, but the result is surprising.
I've measured compile-time of `-openmpopt` pass standalone
on RawSpeed unity build, and while there is some OpenMP stuff,
most is not OpenMP. But nonetheless the pass does a lot of costly
preparations before ever trying to look for OpenMP stuff in SCC.

Numbers (n=25): 0.094624s  ->  0.005976s, an -93.68% improvement, or ~16x

Reviewers: jdoerfert

Reviewed By: jdoerfert

Subscribers: yaxunl, hiraditya, guansong, llvm-commits, sstefan1

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D84689

Added: 
    

Modified: 
    llvm/include/llvm/Transforms/IPO/OpenMPOpt.h
    llvm/lib/Transforms/IPO/OpenMPOpt.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/include/llvm/Transforms/IPO/OpenMPOpt.h b/llvm/include/llvm/Transforms/IPO/OpenMPOpt.h
index d96187b73f9b..9b72ee0afd28 100644
--- a/llvm/include/llvm/Transforms/IPO/OpenMPOpt.h
+++ b/llvm/include/llvm/Transforms/IPO/OpenMPOpt.h
@@ -33,6 +33,11 @@ struct OpenMPInModule {
   bool isKnown() { return Value != OpenMP::UNKNOWN; }
   operator bool() { return Value != OpenMP::NOT_FOUND; }
 
+  /// Does this function \p F contain any OpenMP runtime calls?
+  bool containsOMPRuntimeCalls(Function *F) const {
+    return FuncsWithOMPRuntimeCalls.contains(F);
+  }
+
   /// Return the known kernels (=GPU entry points) in the module.
   SmallPtrSetImpl<Kernel> &getKernels() { return Kernels; }
 
@@ -42,6 +47,11 @@ struct OpenMPInModule {
 private:
   enum class OpenMP { FOUND, NOT_FOUND, UNKNOWN } Value = OpenMP::UNKNOWN;
 
+  friend bool containsOpenMP(Module &M, OpenMPInModule &OMPInModule);
+
+  /// In which functions are OpenMP runtime calls present?
+  SmallPtrSet<Function *, 32> FuncsWithOMPRuntimeCalls;
+
   /// Collection of known kernels (=GPU entry points) in the module.
   SmallPtrSet<Kernel, 8> Kernels;
 };

diff  --git a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
index f664a2417374..93f1e5392eb2 100644
--- a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
+++ b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
@@ -1339,10 +1339,21 @@ PreservedAnalyses OpenMPOptPass::run(LazyCallGraph::SCC &C,
     return PreservedAnalyses::all();
 
   SmallVector<Function *, 16> SCC;
-  for (LazyCallGraph::Node &N : C)
-    SCC.push_back(&N.getFunction());
+  // If there are kernels in the module, we have to run on all SCC's.
+  bool SCCIsInteresting = !OMPInModule.getKernels().empty();
+  for (LazyCallGraph::Node &N : C) {
+    Function *Fn = &N.getFunction();
+    SCC.push_back(Fn);
+
+    // Do we already know that the SCC contains kernels,
+    // or that OpenMP functions are called from this SCC?
+    if (SCCIsInteresting)
+      continue;
+    // If not, let's check that.
+    SCCIsInteresting |= OMPInModule.containsOMPRuntimeCalls(Fn);
+  }
 
-  if (SCC.empty())
+  if (!SCCIsInteresting || SCC.empty())
     return PreservedAnalyses::all();
 
   FunctionAnalysisManager &FAM =
@@ -1401,12 +1412,23 @@ struct OpenMPOptLegacyPass : public CallGraphSCCPass {
       return false;
 
     SmallVector<Function *, 16> SCC;
-    for (CallGraphNode *CGN : CGSCC)
-      if (Function *Fn = CGN->getFunction())
-        if (!Fn->isDeclaration())
-          SCC.push_back(Fn);
+    // If there are kernels in the module, we have to run on all SCC's.
+    bool SCCIsInteresting = !OMPInModule.getKernels().empty();
+    for (CallGraphNode *CGN : CGSCC) {
+      Function *Fn = CGN->getFunction();
+      if (!Fn || Fn->isDeclaration())
+        continue;
+      SCC.push_back(Fn);
 
-    if (SCC.empty())
+      // Do we already know that the SCC contains kernels,
+      // or that OpenMP functions are called from this SCC?
+      if (SCCIsInteresting)
+        continue;
+      // If not, let's check that.
+      SCCIsInteresting |= OMPInModule.containsOMPRuntimeCalls(Fn);
+    }
+
+    if (!SCCIsInteresting || SCC.empty())
       return false;
 
     CallGraph &CG = getAnalysis<CallGraphWrapperPass>().getCallGraph();
@@ -1468,13 +1490,19 @@ bool llvm::omp::containsOpenMP(Module &M, OpenMPInModule &OMPInModule) {
   if (OMPInModule.isKnown())
     return OMPInModule;
 
+  auto RecordFunctionsContainingUsesOf = [&](Function *F) {
+    for (User *U : F->users())
+      if (auto *I = dyn_cast<Instruction>(U))
+        OMPInModule.FuncsWithOMPRuntimeCalls.insert(I->getFunction());
+  };
+
   // MSVC doesn't like long if-else chains for some reason and instead just
   // issues an error. Work around it..
   do {
 #define OMP_RTL(_Enum, _Name, ...)                                             \
-  if (M.getFunction(_Name)) {                                                  \
+  if (Function *F = M.getFunction(_Name)) {                                    \
+    RecordFunctionsContainingUsesOf(F);                                        \
     OMPInModule = true;                                                        \
-    break;                                                                     \
   }
 #include "llvm/Frontend/OpenMP/OMPKinds.def"
   } while (false);