SimplifyCFG: Use parallel-and and parallel-or mode to consolidate branch conditions

Merge consecutive if-regions if they contain identical statements.
Both transformations reduce number of branches.  The transformation
is guarded by a target-hook, and is currently enabled only for +R600,
but the correctness has been tested on X86 target using a variety of
CPU benchmarks.

Patch by: Mei Ye

llvm-svn: 187278

4 files changed, 11 insertions, 3 deletions

diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
index b8a44b5b665..21a3a12ebb8 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -171,6 +171,12 @@ public:
   /// comments for a detailed explanation of the cost values.
   virtual unsigned getUserCost(const User *U) const;
 
+  /// \brief hasBranchDivergence - Return true if branch divergence exists.
+  /// Branch divergence has a significantly negative impact on GPU performance
+  /// when threads in the same wavefront take different paths due to conditional
+  /// branches.
+  virtual bool hasBranchDivergence() const;
+
   /// \brief Test whether calls to a function lower to actual program function
   /// calls.
   ///
diff --git a/llvm/include/llvm/InitializePasses.h b/llvm/include/llvm/InitializePasses.h
index 86fd85108a2..d49636dde3a 100644
--- a/llvm/include/llvm/InitializePasses.h
+++ b/llvm/include/llvm/InitializePasses.h
@@ -86,7 +86,8 @@ void initializeCallGraphViewerPass(PassRegistry&);
 void initializeCFGOnlyPrinterPass(PassRegistry&);
 void initializeCFGOnlyViewerPass(PassRegistry&);
 void initializeCFGPrinterPass(PassRegistry&);
-void initializeCFGSimplifyPassPass(PassRegistry&);
+void initializeCFGOptimizePass(PassRegistry&);
+void initializeCFGCanonicalizePass(PassRegistry&);
 void initializeStructurizeCFGPass(PassRegistry&);
 void initializeCFGViewerPass(PassRegistry&);
 void initializeCalculateSpillWeightsPass(PassRegistry&);
diff --git a/llvm/include/llvm/Transforms/Scalar.h b/llvm/include/llvm/Transforms/Scalar.h
index a327dfff3ec..b52c327e4e0 100644
--- a/llvm/include/llvm/Transforms/Scalar.h
+++ b/llvm/include/llvm/Transforms/Scalar.h
@@ -196,7 +196,7 @@ FunctionPass *createJumpThreadingPass();
 // CFGSimplification - Merge basic blocks, eliminate unreachable blocks,
 // simplify terminator instructions, etc...
 //
-FunctionPass *createCFGSimplificationPass();
+FunctionPass *createCFGSimplificationPass(bool IsTargetAware = false);
 
 //===----------------------------------------------------------------------===//
 //
diff --git a/llvm/include/llvm/Transforms/Utils/Local.h b/llvm/include/llvm/Transforms/Utils/Local.h
index 267825079e1..ec2ab2a75b8 100644
--- a/llvm/include/llvm/Transforms/Utils/Local.h
+++ b/llvm/include/llvm/Transforms/Utils/Local.h
@@ -39,6 +39,7 @@ class DataLayout;
 class TargetLibraryInfo;
 class TargetTransformInfo;
 class DIBuilder;
+class AliasAnalysis;
 
 template<typename T> class SmallVectorImpl;
   
@@ -136,7 +137,7 @@ bool EliminateDuplicatePHINodes(BasicBlock *BB);
 /// the basic block that was pointed to.
 ///
 bool SimplifyCFG(BasicBlock *BB, const TargetTransformInfo &TTI,
-                 const DataLayout *TD = 0);
+                 const DataLayout *TD = 0, AliasAnalysis *AA = 0);
 
 /// FoldBranchToCommonDest - If this basic block is ONLY a setcc and a branch,
 /// and if a predecessor branches to us and one of our successors, fold the