// mask (ex: x86 blends).
};
- /// Enum that specifies what a AtomicRMWInst is expanded to, if at all. Exists
- /// because different targets have different levels of support for these
- /// atomic RMW instructions, and also have different options w.r.t. what they
- /// should expand to.
- enum class AtomicRMWExpansionKind {
+ /// Enum that specifies what an atomic load/AtomicRMWInst is expanded
+ /// to, if at all. Exists because different targets have different levels of
+ /// support for these atomic instructions, and also have different options
+ /// w.r.t. what they should expand to.
+ enum class AtomicExpansionKind {
None, // Don't expand the instruction.
LLSC, // Expand the instruction into loadlinked/storeconditional; used
- // by ARM/AArch64. Implies `hasLoadLinkedStoreConditional`
- // returns true.
+ // by ARM/AArch64.
CmpXChg, // Expand the instruction into cmpxchg; used by at least X86.
};
/// Return true if integer divide is usually cheaper than a sequence of
/// several shifts, adds, and multiplies for this target.
- bool isIntDivCheap() const { return IntDivIsCheap; }
+ /// The definition of "cheaper" may depend on whether we're optimizing
+ /// for speed or for size.
+ virtual bool isIntDivCheap(EVT VT, AttributeSet Attr) const {
+ return false;
+ }
/// Return true if sqrt(x) is as cheap or cheaper than 1 / rsqrt(x)
bool isFsqrtCheap() const {
return BypassSlowDivWidths;
}
- /// Return true if pow2 sdiv is cheaper than a chain of sra/srl/add/sra.
- bool isPow2SDivCheap() const { return Pow2SDivIsCheap; }
-
/// Return true if Flow Control is an expensive operation that should be
/// avoided.
bool isJumpExpensive() const { return JumpIsExpensive; }
return false;
}
+ /// Return true if the target supports a memory access of this type for the
+ /// given address space and alignment. If the access is allowed, the optional
+ /// final parameter returns if the access is also fast (as defined by the
+ /// target).
+ bool allowsMemoryAccess(LLVMContext &Context, const DataLayout &DL, EVT VT,
+ unsigned AddrSpace = 0, unsigned Alignment = 1,
+ bool *Fast = nullptr) const;
+
/// Returns the target specific optimal type for load and store operations as
/// a result of memset, memcpy, and memmove lowering.
///
return false;
}
+ /// Return true if the target stores SafeStack pointer at a fixed offset in
+ /// some non-standard address space, and populates the address space and
+ /// offset as appropriate.
+ virtual bool getSafeStackPointerLocation(unsigned & /*AddressSpace*/,
+ unsigned & /*Offset*/) const {
+ return false;
+ }
+
/// Returns true if a cast between SrcAS and DestAS is a noop.
virtual bool isNoopAddrSpaceCast(unsigned SrcAS, unsigned DestAS) const {
return false;
int InstructionOpcodeToISD(unsigned Opcode) const;
/// Estimate the cost of type-legalization and the legalized type.
- std::pair<unsigned, MVT> getTypeLegalizationCost(const DataLayout &DL,
- Type *Ty) const;
+ std::pair<int, MVT> getTypeLegalizationCost(const DataLayout &DL,
+ Type *Ty) const;
/// @}
/// \name Helpers for atomic expansion.
/// @{
- /// True if AtomicExpandPass should use emitLoadLinked/emitStoreConditional
- /// and expand AtomicCmpXchgInst.
- virtual bool hasLoadLinkedStoreConditional() const { return false; }
-
/// Perform a load-linked operation on Addr, returning a "Value *" with the
/// corresponding pointee type. This may entail some non-trivial operations to
/// truncate or reconstruct types that will be illegal in the backend. See
}
/// @}
+ // Emits code that executes when the comparison result in the ll/sc
+ // expansion of a cmpxchg instruction is such that the store-conditional will
+ // not execute. This makes it possible to balance out the load-linked with
+ // a dedicated instruction, if desired.
+ // E.g., on ARM, if ldrex isn't followed by strex, the exclusive monitor would
+ // be unnecessarily held, except if clrex, inserted by this hook, is executed.
+ virtual void emitAtomicCmpXchgNoStoreLLBalance(IRBuilder<> &Builder) const {}
+
/// Returns true if the given (atomic) store should be expanded by the
/// IR-level AtomicExpand pass into an "atomic xchg" which ignores its input.
virtual bool shouldExpandAtomicStoreInIR(StoreInst *SI) const {
/// Returns true if arguments should be sign-extended in lib calls.
virtual bool shouldSignExtendTypeInLibCall(EVT Type, bool IsSigned) const {
return IsSigned;
- }
+ }
- /// Returns true if the given (atomic) load should be expanded by the
- /// IR-level AtomicExpand pass into a load-linked instruction
- /// (through emitLoadLinked()).
- virtual bool shouldExpandAtomicLoadInIR(LoadInst *LI) const { return false; }
+ /// Returns how the given (atomic) load should be expanded by the
+ /// IR-level AtomicExpand pass.
+ virtual AtomicExpansionKind shouldExpandAtomicLoadInIR(LoadInst *LI) const {
+ return AtomicExpansionKind::None;
+ }
+
+ /// Returns true if the given atomic cmpxchg should be expanded by the
+ /// IR-level AtomicExpand pass into a load-linked/store-conditional sequence
+ /// (through emitLoadLinked() and emitStoreConditional()).
+ virtual bool shouldExpandAtomicCmpXchgInIR(AtomicCmpXchgInst *AI) const {
+ return false;
+ }
/// Returns how the IR-level AtomicExpand pass should expand the given
/// AtomicRMW, if at all. Default is to never expand.
- virtual AtomicRMWExpansionKind
- shouldExpandAtomicRMWInIR(AtomicRMWInst *) const {
- return AtomicRMWExpansionKind::None;
+ virtual AtomicExpansionKind shouldExpandAtomicRMWInIR(AtomicRMWInst *) const {
+ return AtomicExpansionKind::None;
}
/// On some platforms, an AtomicRMW that never actually modifies the value
/// control.
void setJumpIsExpensive(bool isExpensive = true);
- /// Tells the code generator that integer divide is expensive, and if
- /// possible, should be replaced by an alternate sequence of instructions not
- /// containing an integer divide.
- void setIntDivIsCheap(bool isCheap = true) { IntDivIsCheap = isCheap; }
-
/// Tells the code generator that fsqrt is cheap, and should not be replaced
/// with an alternative sequence of instructions.
void setFsqrtIsCheap(bool isCheap = true) { FsqrtIsCheap = isCheap; }
BypassSlowDivWidths[SlowBitWidth] = FastBitWidth;
}
- /// Tells the code generator that it shouldn't generate sra/srl/add/sra for a
- /// signed divide by power of two; let the target handle it.
- void setPow2SDivIsCheap(bool isCheap = true) { Pow2SDivIsCheap = isCheap; }
-
/// Add the specified register class as an available regclass for the
/// specified value type. This indicates the selector can handle values of
/// that class natively.
return false;
}
- /// Return true if it's free to truncate a value of type Ty1 to type
- /// Ty2. e.g. On x86 it's free to truncate a i32 value in register EAX to i16
+ /// Return true if it's free to truncate a value of type FromTy to type
+ /// ToTy. e.g. On x86 it's free to truncate a i32 value in register EAX to i16
/// by referencing its sub-register AX.
- virtual bool isTruncateFree(Type * /*Ty1*/, Type * /*Ty2*/) const {
+ /// Targets must return false when FromTy <= ToTy.
+ virtual bool isTruncateFree(Type *FromTy, Type *ToTy) const {
return false;
}
- /// Return true if a truncation from Ty1 to Ty2 is permitted when deciding
+ /// Return true if a truncation from FromTy to ToTy is permitted when deciding
/// whether a call is in tail position. Typically this means that both results
/// would be assigned to the same register or stack slot, but it could mean
/// the target performs adequate checks of its own before proceeding with the
- /// tail call.
- virtual bool allowTruncateForTailCall(Type * /*Ty1*/, Type * /*Ty2*/) const {
+ /// tail call. Targets must return false when FromTy <= ToTy.
+ virtual bool allowTruncateForTailCall(Type *FromTy, Type *ToTy) const {
return false;
}
- virtual bool isTruncateFree(EVT /*VT1*/, EVT /*VT2*/) const {
+ virtual bool isTruncateFree(EVT FromVT, EVT ToVT) const {
return false;
}
return isExtFreeImpl(I);
}
- /// Return true if any actual instruction that defines a value of type Ty1
- /// implicitly zero-extends the value to Ty2 in the result register.
+ /// Return true if any actual instruction that defines a value of type FromTy
+ /// implicitly zero-extends the value to ToTy in the result register.
///
- /// This does not necessarily include registers defined in unknown ways, such
- /// as incoming arguments, or copies from unknown virtual registers. Also, if
- /// isTruncateFree(Ty2, Ty1) is true, this does not necessarily apply to
- /// truncate instructions. e.g. on x86-64, all instructions that define 32-bit
- /// values implicit zero-extend the result out to 64 bits.
- virtual bool isZExtFree(Type * /*Ty1*/, Type * /*Ty2*/) const {
+ /// The function should return true when it is likely that the truncate can
+ /// be freely folded with an instruction defining a value of FromTy. If
+ /// the defining instruction is unknown (because you're looking at a
+ /// function argument, PHI, etc.) then the target may require an
+ /// explicit truncate, which is not necessarily free, but this function
+ /// does not deal with those cases.
+ /// Targets must return false when FromTy >= ToTy.
+ virtual bool isZExtFree(Type *FromTy, Type *ToTy) const {
return false;
}
- virtual bool isZExtFree(EVT /*VT1*/, EVT /*VT2*/) const {
+ virtual bool isZExtFree(EVT FromTy, EVT ToTy) const {
return false;
}
return false;
}
+ // Return true if it is profitable to use a scalar input to a BUILD_VECTOR
+ // even if the vector itself has multiple uses.
+ virtual bool aggressivelyPreferBuildVectorSources(EVT VecVT) const {
+ return false;
+ }
+
//===--------------------------------------------------------------------===//
// Runtime Library hooks
//
/// combined with "shift" to BitExtract instructions.
bool HasExtractBitsInsn;
- /// Tells the code generator not to expand integer divides by constants into a
- /// sequence of muls, adds, and shifts. This is a hack until a real cost
- /// model is in place. If we ever optimize for size, this will be set to true
- /// unconditionally.
- bool IntDivIsCheap;
-
// Don't expand fsqrt with an approximation based on the inverse sqrt.
bool FsqrtIsCheap;
/// div/rem when the operands are positive and less than 256.
DenseMap <unsigned int, unsigned int> BypassSlowDivWidths;
- /// Tells the code generator that it shouldn't generate sra/srl/add/sra for a
- /// signed divide by power of two; let the target handle it.
- bool Pow2SDivIsCheap;
-
/// Tells the code generator that it shouldn't generate extra flow control
/// instructions and should attempt to combine flow control instructions via
/// predication.
unsigned MaxStoresPerMemmove;
/// Maximum number of store instructions that may be substituted for a call to
- /// memmove, used for functions with OpSize attribute.
+ /// memmove, used for functions with OptSize attribute.
unsigned MaxStoresPerMemmoveOptSize;
/// Tells the code generator that select is more expensive than a branch if
/// Return the register ID of the name passed in. Used by named register
/// global variables extension. There is no target-independent behaviour
/// so the default action is to bail.
- virtual unsigned getRegisterByName(const char* RegName, EVT VT) const {
+ virtual unsigned getRegisterByName(const char* RegName, EVT VT,
+ SelectionDAG &DAG) const {
report_fatal_error("Named registers not implemented for this target");
}
SDValue BuildUDIV(SDNode *N, const APInt &Divisor, SelectionDAG &DAG,
bool IsAfterLegalization,
std::vector<SDNode *> *Created) const;
+
+ /// Targets may override this function to provide custom SDIV lowering for
+ /// power-of-2 denominators. If the target returns an empty SDValue, LLVM
+ /// assumes SDIV is expensive and replaces it with a series of other integer
+ /// operations.
virtual SDValue BuildSDIVPow2(SDNode *N, const APInt &Divisor,
SelectionDAG &DAG,
- std::vector<SDNode *> *Created) const {
- return SDValue();
- }
+ std::vector<SDNode *> *Created) const;
- /// Indicate whether this target prefers to combine the given number of FDIVs
- /// with the same divisor.
- virtual bool combineRepeatedFPDivisors(unsigned NumUsers) const {
- return false;
+ /// Indicate whether this target prefers to combine FDIVs with the same
+ /// divisor. If the transform should never be done, return zero. If the
+ /// transform should be done, return the minimum number of divisor uses
+ /// that must exist.
+ virtual unsigned combineRepeatedFPDivisors() const {
+ return 0;
}
/// Hooks for building estimates in place of slower divisions and square
virtual bool useLoadStackGuardNode() const {
return false;
}
+
+ /// Lower TLS global address SDNode for target independent emulated TLS model.
+ virtual SDValue LowerToTLSEmulatedModel(const GlobalAddressSDNode *GA,
+ SelectionDAG &DAG) const;
};
/// Given an LLVM IR type and return type attributes, compute the return value
projects / oota-llvm.git / blobdiff