AMDGPU/SI: Test commit

[oota-llvm.git] / lib / Target / AArch64 / AArch64TargetTransformInfo.h

diff --git a/lib/Target/AArch64/AArch64TargetTransformInfo.h b/lib/Target/AArch64/AArch64TargetTransformInfo.h
index 5d4b9a39f67aed70a360bc742198674b4797da32..ec58c4fe309f3e77ac6a82a22dd293909c2cb00d 100644 (file)
--- a/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ b/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -29,6 +29,7 @@ namespace llvm {
 class AArch64TTIImpl : public BasicTTIImplBase<AArch64TTIImpl> {
   typedef BasicTTIImplBase<AArch64TTIImpl> BaseT;
   typedef TargetTransformInfo TTI;
+  friend BaseT;
 
   const AArch64Subtarget *ST;
   const AArch64TargetLowering *TLI;
@@ -37,6 +38,9 @@ class AArch64TTIImpl : public BasicTTIImplBase<AArch64TTIImpl> {
   /// are set if the result needs to be inserted and/or extracted from vectors.
   unsigned getScalarizationOverhead(Type *Ty, bool Insert, bool Extract);
 
+  const AArch64Subtarget *getST() const { return ST; }
+  const AArch64TargetLowering *getTLI() const { return TLI; }
+
   enum MemIntrinsicType {
     VECTOR_LDST_TWO_ELEMENTS,
     VECTOR_LDST_THREE_ELEMENTS,
@@ -44,8 +48,9 @@ class AArch64TTIImpl : public BasicTTIImplBase<AArch64TTIImpl> {
   };
 
 public:
-  explicit AArch64TTIImpl(const AArch64TargetMachine *TM)
-      : BaseT(TM), ST(TM->getSubtargetImpl()), TLI(ST->getTargetLowering()) {}
+  explicit AArch64TTIImpl(const AArch64TargetMachine *TM, const Function &F)
+      : BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),
+        TLI(ST->getTargetLowering()) {}
 
   // Provide value semantics. MSVC requires that we spell all of these out.
   AArch64TTIImpl(const AArch64TTIImpl &Arg)
@@ -53,29 +58,16 @@ public:
   AArch64TTIImpl(AArch64TTIImpl &&Arg)
       : BaseT(std::move(static_cast<BaseT &>(Arg))), ST(std::move(Arg.ST)),
         TLI(std::move(Arg.TLI)) {}
-  AArch64TTIImpl &operator=(const AArch64TTIImpl &RHS) {
-    BaseT::operator=(static_cast<const BaseT &>(RHS));
-    ST = RHS.ST;
-    TLI = RHS.TLI;
-    return *this;
-  }
-  AArch64TTIImpl &operator=(AArch64TTIImpl &&RHS) {
-    BaseT::operator=(std::move(static_cast<BaseT &>(RHS)));
-    ST = std::move(RHS.ST);
-    TLI = std::move(RHS.TLI);
-    return *this;
-  }
 
   /// \name Scalar TTI Implementations
   /// @{
 
   using BaseT::getIntImmCost;
-  unsigned getIntImmCost(int64_t Val);
-  unsigned getIntImmCost(const APInt &Imm, Type *Ty);
-  unsigned getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm,
-                         Type *Ty);
-  unsigned getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
-                         Type *Ty);
+  int getIntImmCost(int64_t Val);
+  int getIntImmCost(const APInt &Imm, Type *Ty);
+  int getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty);
+  int getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
+                    Type *Ty);
   TTI::PopcntSupportKind getPopcntSupport(unsigned TyWidth);
 
   /// @}
@@ -83,6 +75,8 @@ public:
   /// \name Vector TTI Implementations
   /// @{
 
+  bool enableInterleavedAccessVectorization() { return true; }
+
   unsigned getNumberOfRegisters(bool Vector) {
     if (Vector) {
       if (ST->hasNEON())
@@ -101,36 +95,38 @@ public:
     return 64;
   }
 
-  unsigned getMaxInterleaveFactor();
+  unsigned getMaxInterleaveFactor(unsigned VF);
 
-  unsigned getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src);
+  int getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src);
 
-  unsigned getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
+  int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
 
-  unsigned getArithmeticInstrCost(
+  int getArithmeticInstrCost(
       unsigned Opcode, Type *Ty,
       TTI::OperandValueKind Opd1Info = TTI::OK_AnyValue,
       TTI::OperandValueKind Opd2Info = TTI::OK_AnyValue,
       TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
       TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None);
 
-  unsigned getAddressComputationCost(Type *Ty, bool IsComplex);
+  int getAddressComputationCost(Type *Ty, bool IsComplex);
 
-  unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy);
+  int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy);
 
-  unsigned getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
-                           unsigned AddressSpace);
+  int getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
+                      unsigned AddressSpace);
 
-  unsigned getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys);
+  int getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys);
 
-  void getUnrollingPreferences(const Function *F, Loop *L,
-                               TTI::UnrollingPreferences &UP);
+  void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP);
 
   Value *getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst,
                                            Type *ExpectedType);
 
   bool getTgtMemIntrinsic(IntrinsicInst *Inst, MemIntrinsicInfo &Info);
 
+  int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor,
+                                 ArrayRef<unsigned> Indices, unsigned Alignment,
+                                 unsigned AddressSpace);
   /// @}
 };