X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FCodeGen%2FBasicTargetTransformInfo.cpp;h=24bc570f44a1fcb25010a4b126c486ce350aa292;hb=2a2fcc1a0ec4a115bbe76c185f7cd64e77b61e7c;hp=763a4c0b3cfc487f0a0beda0030a033139e62b3b;hpb=f35ce2376ca361e059ad9390ce1f8467f8756bcd;p=oota-llvm.git

diff --git a/lib/CodeGen/BasicTargetTransformInfo.cpp b/lib/CodeGen/BasicTargetTransformInfo.cpp
index 763a4c0b3cf..24bc570f44a 100644
--- a/lib/CodeGen/BasicTargetTransformInfo.cpp
+++ b/lib/CodeGen/BasicTargetTransformInfo.cpp
@@ -39,7 +39,12 @@ class BasicTTI final : public ImmutablePass, public TargetTransformInfo {
   /// are set if the result needs to be inserted and/or extracted from vectors.
   unsigned getScalarizationOverhead(Type *Ty, bool Insert, bool Extract) const;
 
-  const TargetLoweringBase *getTLI() const { return TM->getTargetLowering(); }
+  /// Estimate the cost overhead of SK_Alternate shuffle.
+  unsigned getAltShuffleOverhead(Type *Ty) const;
+
+  const TargetLoweringBase *getTLI() const {
+    return TM->getSubtargetImpl()->getTargetLowering();
+  }
 
 public:
   BasicTTI() : ImmutablePass(ID), TM(nullptr) {
@@ -197,7 +202,7 @@ bool BasicTTI::haveFastSqrt(Type *Ty) const {
 void BasicTTI::getUnrollingPreferences(Loop *L,
                                        UnrollingPreferences &UP) const {
   // This unrolling functionality is target independent, but to provide some
-  // motivation for its indended use, for x86:
+  // motivation for its intended use, for x86:
 
   // According to the Intel 64 and IA-32 Architectures Optimization Reference
   // Manual, Intel Core models and later have a loop stream detector
@@ -327,8 +332,28 @@ unsigned BasicTTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty,
   return OpCost;
 }
 
+unsigned BasicTTI::getAltShuffleOverhead(Type *Ty) const {
+  assert(Ty->isVectorTy() && "Can only shuffle vectors");
+  unsigned Cost = 0;
+  // Shuffle cost is equal to the cost of extracting element from its argument
+  // plus the cost of inserting them onto the result vector.
+
+  // e.g. <4 x float> has a mask of <0,5,2,7> i.e we need to extract from index
+  // 0 of first vector, index 1 of second vector,index 2 of first vector and
+  // finally index 3 of second vector and insert them at index <0,1,2,3> of
+  // result vector.
+  for (int i = 0, e = Ty->getVectorNumElements(); i < e; ++i) {
+    Cost += TopTTI->getVectorInstrCost(Instruction::InsertElement, Ty, i);
+    Cost += TopTTI->getVectorInstrCost(Instruction::ExtractElement, Ty, i);
+  }
+  return Cost;
+}
+
 unsigned BasicTTI::getShuffleCost(ShuffleKind Kind, Type *Tp, int Index,
                                   Type *SubTp) const {
+  if (Kind == SK_Alternate) {
+    return getAltShuffleOverhead(Tp);
+  }
   return 1;
 }
 
@@ -549,6 +574,7 @@ unsigned BasicTTI::getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
   case Intrinsic::pow:     ISD = ISD::FPOW;   break;
   case Intrinsic::fma:     ISD = ISD::FMA;    break;
   case Intrinsic::fmuladd: ISD = ISD::FMA;    break;
+  // FIXME: We should return 0 whenever getIntrinsicCost == TCC_Free.
   case Intrinsic::lifetime_start:
   case Intrinsic::lifetime_end:
     return 0;