X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=blobdiff_plain;f=lib%2FTarget%2FAArch64%2FAArch64ISelLowering.h;h=24fd2384bfcd13a398c7262bed72be5d199d1055;hp=2f5708dd8978f5d660c1a88fb2d6edd3dd3180be;hb=0e496c884c86a50d4f024e6994f5b102118f9821;hpb=2929da99a9dd71f6cb589329d000b7dc66a94abd

diff --git a/lib/Target/AArch64/AArch64ISelLowering.h b/lib/Target/AArch64/AArch64ISelLowering.h
index 2f5708dd897..24fd2384bfc 100644
--- a/lib/Target/AArch64/AArch64ISelLowering.h
+++ b/lib/Target/AArch64/AArch64ISelLowering.h
@@ -18,20 +18,21 @@
 #include "llvm/CodeGen/CallingConvLower.h"
 #include "llvm/CodeGen/SelectionDAG.h"
 #include "llvm/IR/CallingConv.h"
+#include "llvm/IR/Instruction.h"
 #include "llvm/Target/TargetLowering.h"
 
 namespace llvm {
 
 namespace AArch64ISD {
 
-enum {
+enum NodeType : unsigned {
   FIRST_NUMBER = ISD::BUILTIN_OP_END,
   WrapperLarge, // 4-instruction MOVZ/MOVK sequence for 64-bit addresses.
   CALL,         // Function call.
 
-  // Almost the same as a normal call node, except that a TLSDesc relocation is
-  // needed so the linker can relax it correctly if possible.
-  TLSDESC_CALL,
+  // Produces the full sequence of instructions for getting the thread pointer
+  // offset of a variable into X0, using the TLSDesc model.
+  TLSDESC_CALLSEQ,
   ADRP,     // Page address of a TargetGlobalAddress operand.
   ADDlow,   // Add the low 12 bits of a TargetGlobalAddress operand.
   LOADgot,  // Load from automatically generated descriptor (e.g. Global
@@ -140,6 +141,18 @@ enum {
   FCMLEz,
   FCMLTz,
 
+  // Vector across-lanes addition
+  // Only the lower result lane is defined.
+  SADDV,
+  UADDV,
+
+  // Vector across-lanes min/max
+  // Only the lower result lane is defined.
+  SMINV,
+  UMINV,
+  SMAXV,
+  UMAXV,
+
   // Vector bitwise negation
   NOT,
 
@@ -207,7 +220,8 @@ class AArch64TargetLowering : public TargetLowering {
   bool RequireStrictAlign;
 
 public:
-  explicit AArch64TargetLowering(const TargetMachine &TM);
+  explicit AArch64TargetLowering(const TargetMachine &TM,
+                                 const AArch64Subtarget &STI);
 
   /// Selects the correct CCAssignFn for a given CallingConvention value.
   CCAssignFn *CCAssignFnForCall(CallingConv::ID CC, bool IsVarArg) const;
@@ -219,10 +233,10 @@ public:
                                      APInt &KnownOne, const SelectionDAG &DAG,
                                      unsigned Depth = 0) const override;
 
-  MVT getScalarShiftAmountTy(EVT LHSTy) const override;
+  MVT getScalarShiftAmountTy(const DataLayout &DL) const override;
 
   /// allowsMisalignedMemoryAccesses - Returns true if the target allows
-  /// unaligned memory accesses. of the specified type.
+  /// unaligned memory accesses of the specified type.
   bool allowsMisalignedMemoryAccesses(EVT VT, unsigned AddrSpace = 0,
                                       unsigned Align = 1,
                                       bool *Fast = nullptr) const override {
@@ -244,10 +258,6 @@ public:
   /// getFunctionAlignment - Return the Log2 alignment of this function.
   unsigned getFunctionAlignment(const Function *F) const;
 
-  /// getMaximalGlobalOffset - Returns the maximal possible offset which can
-  /// be used for loads / stores from the global.
-  unsigned getMaximalGlobalOffset() const override;
-
   /// Returns true if a cast between SrcAS and DestAS is a noop.
   bool isNoopAddrSpaceCast(unsigned SrcAS, unsigned DestAS) const override {
     // Addrspacecasts are always noops.
@@ -268,7 +278,8 @@ public:
   bool isShuffleMaskLegal(const SmallVectorImpl<int> &M, EVT VT) const override;
 
   /// getSetCCResultType - Return the ISD::SETCC ValueType
-  EVT getSetCCResultType(LLVMContext &Context, EVT VT) const override;
+  EVT getSetCCResultType(const DataLayout &DL, LLVMContext &Context,
+                         EVT VT) const override;
 
   SDValue ReconstructShuffle(SDValue Op, SelectionDAG &DAG) const;
 
@@ -285,6 +296,8 @@ public:
   bool isTruncateFree(Type *Ty1, Type *Ty2) const override;
   bool isTruncateFree(EVT VT1, EVT VT2) const override;
 
+  bool isProfitableToHoist(Instruction *I) const override;
+
   bool isZExtFree(Type *Ty1, Type *Ty2) const override;
   bool isZExtFree(EVT VT1, EVT VT2) const override;
   bool isZExtFree(SDValue Val, EVT VT2) const override;
@@ -293,6 +306,15 @@ public:
                      unsigned &RequiredAligment) const override;
   bool hasPairedLoad(EVT LoadedType, unsigned &RequiredAligment) const override;
 
+  unsigned getMaxSupportedInterleaveFactor() const override { return 4; }
+
+  bool lowerInterleavedLoad(LoadInst *LI,
+                            ArrayRef<ShuffleVectorInst *> Shuffles,
+                            ArrayRef<unsigned> Indices,
+                            unsigned Factor) const override;
+  bool lowerInterleavedStore(StoreInst *SI, ShuffleVectorInst *SVI,
+                             unsigned Factor) const override;
+
   bool isLegalAddImmediate(int64_t) const override;
   bool isLegalICmpImmediate(int64_t) const override;
 
@@ -302,14 +324,16 @@ public:
 
   /// isLegalAddressingMode - Return true if the addressing mode represented
   /// by AM is legal for this target, for a load/store of the specified type.
-  bool isLegalAddressingMode(const AddrMode &AM, Type *Ty) const override;
+  bool isLegalAddressingMode(const DataLayout &DL, const AddrMode &AM, Type *Ty,
+                             unsigned AS) const override;
 
   /// \brief Return the cost of the scaling factor used in the addressing
   /// mode represented by AM for this target, for a load/store
   /// of the specified type.
   /// If the AM is supported, the return value must be >= 0.
   /// If the AM is not supported, it returns a negative value.
-  int getScalingFactorCost(const AddrMode &AM, Type *Ty) const override;
+  int getScalingFactorCost(const DataLayout &DL, const AddrMode &AM, Type *Ty,
+                           unsigned AS) const override;
 
   /// isFMAFasterThanFMulAndFAdd - Return true if an FMA operation is faster
   /// than a pair of fmul and fadd instructions. fmuladd intrinsics will be
@@ -335,13 +359,16 @@ public:
 
   bool shouldExpandAtomicLoadInIR(LoadInst *LI) const override;
   bool shouldExpandAtomicStoreInIR(StoreInst *SI) const override;
-  bool shouldExpandAtomicRMWInIR(AtomicRMWInst *AI) const override;
+  TargetLoweringBase::AtomicRMWExpansionKind
+  shouldExpandAtomicRMWInIR(AtomicRMWInst *AI) const override;
 
   bool useLoadStackGuardNode() const override;
   TargetLoweringBase::LegalizeTypeAction
   getPreferredVectorAction(EVT VT) const override;
 
 private:
+  bool isExtFreeImpl(const Instruction *Ext) const override;
+
   /// Subtarget - Keep a pointer to the AArch64Subtarget around so that we can
   /// make the right decision when generating code for different targets.
   const AArch64Subtarget *Subtarget;
@@ -399,12 +426,15 @@ private:
   SDValue LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerDarwinGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerELFGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
-  SDValue LowerELFTLSDescCall(SDValue SymAddr, SDValue DescAddr, SDLoc DL,
-                              SelectionDAG &DAG) const;
+  SDValue LowerELFTLSDescCallSeq(SDValue SymAddr, SDLoc DL,
+                                 SelectionDAG &DAG) const;
   SDValue LowerSETCC(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerBR_CC(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerSELECT(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
+  SDValue LowerSELECT_CC(ISD::CondCode CC, SDValue LHS, SDValue RHS,
+                         SDValue TVal, SDValue FVal, SDLoc dl,
+                         SelectionDAG &DAG) const;
   SDValue LowerJumpTable(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerConstantPool(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerBlockAddress(SDValue Op, SelectionDAG &DAG) const;
@@ -440,9 +470,9 @@ private:
 
   SDValue BuildSDIVPow2(SDNode *N, const APInt &Divisor, SelectionDAG &DAG,
                         std::vector<SDNode *> *Created) const override;
+  bool combineRepeatedFPDivisors(unsigned NumUsers) const override;
 
-  ConstraintType
-  getConstraintType(const std::string &Constraint) const override;
+  ConstraintType getConstraintType(StringRef Constraint) const override;
   unsigned getRegisterByName(const char* RegName, EVT VT) const override;
 
   /// Examine constraint string and operand type and determine a weight value.
@@ -452,12 +482,21 @@ private:
                                  const char *constraint) const override;
 
   std::pair<unsigned, const TargetRegisterClass *>
-  getRegForInlineAsmConstraint(const std::string &Constraint,
-                               MVT VT) const override;
+  getRegForInlineAsmConstraint(const TargetRegisterInfo *TRI,
+                               StringRef Constraint, MVT VT) const override;
   void LowerAsmOperandForConstraint(SDValue Op, std::string &Constraint,
                                     std::vector<SDValue> &Ops,
                                     SelectionDAG &DAG) const override;
 
+  unsigned getInlineAsmMemConstraint(StringRef ConstraintCode) const override {
+    if (ConstraintCode == "Q")
+      return InlineAsm::Constraint_Q;
+    // FIXME: clang has code for 'Ump', 'Utf', 'Usa', and 'Ush' but these are
+    //        followed by llvm_unreachable so we'll leave them unimplemented in
+    //        the backend for now.
+    return TargetLowering::getInlineAsmMemConstraint(ConstraintCode);
+  }
+
   bool isUsedByReturnOnly(SDNode *N, SDValue &Chain) const override;
   bool mayBeEmittedAsTailCall(CallInst *CI) const override;
   bool getIndexedAddressParts(SDNode *Op, SDValue &Base, SDValue &Offset,
@@ -472,6 +511,10 @@ private:
 
   void ReplaceNodeResults(SDNode *N, SmallVectorImpl<SDValue> &Results,
                           SelectionDAG &DAG) const override;
+
+  bool functionArgumentNeedsConsecutiveRegisters(Type *Ty,
+                                                 CallingConv::ID CallConv,
+                                                 bool isVarArg) const override;
 };
 
 namespace AArch64 {