Allow vectorization of division by uniform power of 2.

This patch adds support to recognize division by uniform power of 2 and modifies the cost table to vectorize division by uniform power of 2 whenever possible.
Updates Cost model for Loop and SLP Vectorizer.The cost table is currently only updated for X86 backend.
Thanks to Hal, Andrea, Sanjay for the review. (http://reviews.llvm.org/D4971)

llvm-svn: 216371

2 files changed, 31 insertions, 8 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 0c2b3d200cc..42fb1242f67 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -5837,18 +5837,31 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, unsigned VF) {
       TargetTransformInfo::OK_AnyValue;
     TargetTransformInfo::OperandValueKind Op2VK =
       TargetTransformInfo::OK_AnyValue;
+    TargetTransformInfo::OperandValueProperties Op1VP =
+        TargetTransformInfo::OP_None;
+    TargetTransformInfo::OperandValueProperties Op2VP =
+        TargetTransformInfo::OP_None;
     Value *Op2 = I->getOperand(1);
 
     // Check for a splat of a constant or for a non uniform vector of constants.
-    if (isa<ConstantInt>(Op2))
+    if (isa<ConstantInt>(Op2)) {
+      ConstantInt *CInt = cast<ConstantInt>(Op2);
+      if (CInt && CInt->getValue().isPowerOf2())
+        Op2VP = TargetTransformInfo::OP_PowerOf2;
       Op2VK = TargetTransformInfo::OK_UniformConstantValue;
-    else if (isa<ConstantVector>(Op2) || isa<ConstantDataVector>(Op2)) {
+    } else if (isa<ConstantVector>(Op2) || isa<ConstantDataVector>(Op2)) {
       Op2VK = TargetTransformInfo::OK_NonUniformConstantValue;
-      if (cast<Constant>(Op2)->getSplatValue() != nullptr)
+      Constant *SplatValue = cast<Constant>(Op2)->getSplatValue();
+      if (SplatValue) {
+        ConstantInt *CInt = dyn_cast<ConstantInt>(SplatValue);
+        if (CInt && CInt->getValue().isPowerOf2())
+          Op2VP = TargetTransformInfo::OP_PowerOf2;
         Op2VK = TargetTransformInfo::OK_UniformConstantValue;
+      }
     }
 
-    return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK, Op2VK);
+    return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK, Op2VK,
+                                      Op1VP, Op2VP);
   }
   case Instruction::Select: {
     SelectInst *SI = cast<SelectInst>(I);
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 3aced0b4c40..2602feb2f2c 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -1425,6 +1425,10 @@ int BoUpSLP::getEntryCost(TreeEntry *E) {
             TargetTransformInfo::OK_AnyValue;
         TargetTransformInfo::OperandValueKind Op2VK =
             TargetTransformInfo::OK_UniformConstantValue;
+        TargetTransformInfo::OperandValueProperties Op1VP =
+            TargetTransformInfo::OP_None;
+        TargetTransformInfo::OperandValueProperties Op2VP =
+            TargetTransformInfo::OP_None;
 
         // If all operands are exactly the same ConstantInt then set the
         // operand kind to OK_UniformConstantValue.
@@ -1446,11 +1450,17 @@ int BoUpSLP::getEntryCost(TreeEntry *E) {
               CInt != cast<ConstantInt>(I->getOperand(1)))
             Op2VK = TargetTransformInfo::OK_NonUniformConstantValue;
         }
+        // FIXME: Currently cost of model modification for division by
+        // power of 2 is handled only for X86. Add support for other targets.
+        if (Op2VK == TargetTransformInfo::OK_UniformConstantValue && CInt &&
+            CInt->getValue().isPowerOf2())
+          Op2VP = TargetTransformInfo::OP_PowerOf2;
 
-        ScalarCost =
-            VecTy->getNumElements() *
-            TTI->getArithmeticInstrCost(Opcode, ScalarTy, Op1VK, Op2VK);
-        VecCost = TTI->getArithmeticInstrCost(Opcode, VecTy, Op1VK, Op2VK);
+        ScalarCost = VecTy->getNumElements() *
+                     TTI->getArithmeticInstrCost(Opcode, ScalarTy, Op1VK, Op2VK,
+                                                 Op1VP, Op2VP);
+        VecCost = TTI->getArithmeticInstrCost(Opcode, VecTy, Op1VK, Op2VK,
+                                              Op1VP, Op2VP);
       }
       return VecCost - ScalarCost;
     }