[LV] Cache block mask values

[gilr]

Summary

This patch is part of D28975's breakdown.

Add caching for block masks similar to the cache already used for edge masks, replacing generation per user with reusing the first generated value which dominates all uses.

[mkuper]

LGTM.

llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp

protected:
   /// original loop, when scalarized, is represented by UF x VF scalar values
   /// in the new unrolled loop, where UF is the unroll factor and VF is the
   /// vectorization factor.
   typedef SmallVector<SmallVector<Value *, 4>, 2> ScalarParts;
 
   // When we if-convert we need to create edge masks. We have to cache values
   // so that we don't end up with exponential recursion/IR.
   typedef DenseMap<std::pair<BasicBlock *, BasicBlock *>, VectorParts>
-      EdgeMaskCache;
+      EdgeMaskCacheTy;
+  typedef DenseMap<BasicBlock *, VectorParts> BlockMaskCacheTy;
 
   /// Create an empty loop, based on the loop ranges of the old loop.
   void createEmptyLoop();
 
   /// Set up the values of the IVs correctly when exiting the vector loop.
   void fixupIVUsers(PHINode *OrigPhi, const InductionDescriptor &II,
                     Value *CountRoundDown, Value *EndValue,
                     BasicBlock *MiddleBlock);
protected:
   /// vectorized loop. A key value can map to either vector values, scalar
   /// values or both kinds of values, depending on whether the key was
   /// vectorized and scalarized.
   ValueMap VectorLoopValueMap;
 
   /// Store instructions that should be predicated, as a pair
   ///   <StoreInst, Predicate>
   SmallVector<std::pair<Instruction *, Value *>, 4> PredicatedInstructions;
-  EdgeMaskCache MaskCache;
+  EdgeMaskCacheTy EdgeMaskCache;
+  BlockMaskCacheTy BlockMaskCache;
   /// Trip count of the original loop.
   Value *TripCount;
   /// Trip count of the widened loop (TripCount - TripCount % (VF*UF))
   Value *VectorTripCount;
 
   /// The legality analysis.
   LoopVectorizationLegality *Legal;
 

 }
 
 InnerLoopVectorizer::VectorParts
 InnerLoopVectorizer::createEdgeMask(BasicBlock *Src, BasicBlock *Dst) {
   assert(is_contained(predecessors(Dst), Src) && "Invalid edge");
 
   // Look for cached value.
   std::pair<BasicBlock *, BasicBlock *> Edge(Src, Dst);
-  EdgeMaskCache::iterator ECEntryIt = MaskCache.find(Edge);
-  if (ECEntryIt != MaskCache.end())
+  EdgeMaskCacheTy::iterator ECEntryIt = EdgeMaskCache.find(Edge);
+  if (ECEntryIt != EdgeMaskCache.end())
     return ECEntryIt->second;
 
   VectorParts SrcMask = createBlockInMask(Src);
 
   // The terminator has to be a branch inst!
   BranchInst *BI = dyn_cast<BranchInst>(Src->getTerminator());
   assert(BI && "Unexpected terminator found");
 
   if (BI->isConditional()) {
     VectorParts EdgeMask = getVectorValue(BI->getCondition());
 
     if (BI->getSuccessor(0) != Dst)
       for (unsigned part = 0; part < UF; ++part)
         EdgeMask[part] = Builder.CreateNot(EdgeMask[part]);
 
     for (unsigned part = 0; part < UF; ++part)
       EdgeMask[part] = Builder.CreateAnd(EdgeMask[part], SrcMask[part]);
 
-    MaskCache[Edge] = EdgeMask;
+    EdgeMaskCache[Edge] = EdgeMask;
     return EdgeMask;
   }
 
-  MaskCache[Edge] = SrcMask;
+  EdgeMaskCache[Edge] = SrcMask;
   return SrcMask;
 }
 
 InnerLoopVectorizer::VectorParts
 InnerLoopVectorizer::createBlockInMask(BasicBlock *BB) {
   assert(OrigLoop->contains(BB) && "Block is not a part of a loop");
 
+  // Look for cached value.
+  BlockMaskCacheTy::iterator BCEntryIt = BlockMaskCache.find(BB);
+  if (BCEntryIt != BlockMaskCache.end())
+    return BCEntryIt->second;
+
   // Loop incoming mask is all-one.
   if (OrigLoop->getHeader() == BB) {
     Value *C = ConstantInt::get(IntegerType::getInt1Ty(BB->getContext()), 1);
-    return getVectorValue(C);
+    const VectorParts &BlockMask = getVectorValue(C);
+    BlockMaskCache[BB] = BlockMask;
+    return BlockMask;
   }
 
   // This is the block mask. We OR all incoming edges, and with zero.
   Value *Zero = ConstantInt::get(IntegerType::getInt1Ty(BB->getContext()), 0);
   VectorParts BlockMask = getVectorValue(Zero);
 
   // For each pred:
   for (pred_iterator it = pred_begin(BB), e = pred_end(BB); it != e; ++it) {
     VectorParts EM = createEdgeMask(*it, BB);
     for (unsigned part = 0; part < UF; ++part)
       BlockMask[part] = Builder.CreateOr(BlockMask[part], EM[part]);
   }
 
+  BlockMaskCache[BB] = BlockMask;
   return BlockMask;
 }
 
 void InnerLoopVectorizer::widenPHIInstruction(Instruction *PN, unsigned UF,
                                               unsigned VF) {
   PHINode *P = cast<PHINode>(PN);
   // In order to support recurrences we need to be able to vectorize Phi nodes.
   // Phi nodes have cycles, so we need to vectorize them in two stages. This is