//
//===----------------------------------------------------------------------===//
-#ifndef X86SUBTARGET_H
-#define X86SUBTARGET_H
+#ifndef LLVM_LIB_TARGET_X86_X86SUBTARGET_H
+#define LLVM_LIB_TARGET_X86_X86SUBTARGET_H
+#include "X86FrameLowering.h"
+#include "X86ISelLowering.h"
+#include "X86InstrInfo.h"
+#include "X86SelectionDAGInfo.h"
#include "llvm/ADT/Triple.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/Target/TargetSubtargetInfo.h"
};
}
-class X86Subtarget : public X86GenSubtargetInfo {
+class X86Subtarget final : public X86GenSubtargetInfo {
+
protected:
enum X86SSEEnum {
NoMMXSSE, MMX, SSE1, SSE2, SSE3, SSSE3, SSE41, SSE42, AVX, AVX2, AVX512F
};
enum X86ProcFamilyEnum {
- Others, IntelAtom
+ Others, IntelAtom, IntelSLM
};
/// X86ProcFamily - X86 processor family: Intel Atom, and others
/// HasXOP - Target has XOP instructions
bool HasXOP;
+ /// HasTBM - Target has TBM instructions.
+ bool HasTBM;
+
/// HasMOVBE - True if the processor has the MOVBE instruction.
bool HasMOVBE;
/// HasADX - Processor has ADX instructions.
bool HasADX;
+ /// HasSHA - Processor has SHA instructions.
+ bool HasSHA;
+
+ /// HasSGX - Processor has SGX instructions.
+ bool HasSGX;
+
/// HasPRFCHW - Processor has PRFCHW instructions.
bool HasPRFCHW;
/// HasRDSEED - Processor has RDSEED instructions.
bool HasRDSEED;
+ /// HasSMAP - Processor has SMAP instructions.
+ bool HasSMAP;
+
/// IsBTMemSlow - True if BT (bit test) of memory instructions are slow.
bool IsBTMemSlow;
+ /// IsSHLDSlow - True if SHLD instructions are slow.
+ bool IsSHLDSlow;
+
/// IsUAMemFast - True if unaligned memory access is fast.
bool IsUAMemFast;
+ /// True if unaligned 32-byte memory accesses are slow.
+ bool IsUAMem32Slow;
+
/// HasVectorUAMem - True if SIMD operations can have unaligned memory
/// operands. This may require setting a feature bit in the processor.
bool HasVectorUAMem;
/// the stack pointer. This is an optimization for Intel Atom processors.
bool UseLeaForSP;
- /// HasSlowDivide - True if smaller divides are significantly faster than
- /// full divides and should be used when possible.
- bool HasSlowDivide;
+ /// HasSlowDivide32 - True if 8-bit divisions are significantly faster than
+ /// 32-bit divisions and should be used when possible.
+ bool HasSlowDivide32;
- /// PostRAScheduler - True if using post-register-allocation scheduler.
- bool PostRAScheduler;
+ /// HasSlowDivide64 - True if 16-bit divides are significantly faster than
+ /// 64-bit divisions and should be used when possible.
+ bool HasSlowDivide64;
/// PadShortFunctions - True if the short functions should be padded to prevent
/// a stall when returning too early.
/// address generation (AG) time.
bool LEAUsesAG;
+ /// SlowLEA - True if the LEA instruction with certain arguments is slow
+ bool SlowLEA;
+
+ /// SlowIncDec - True if INC and DEC instructions are slow when writing to flags
+ bool SlowIncDec;
+
+ /// Use the RSQRT* instructions to optimize square root calculations.
+ /// For this to be profitable, the cost of FSQRT and FDIV must be
+ /// substantially higher than normal FP ops like FADD and FMUL.
+ bool UseSqrtEst;
+
+ /// Use the RCP* instructions to optimize FP division calculations.
+ /// For this to be profitable, the cost of FDIV must be
+ /// substantially higher than normal FP ops like FADD and FMUL.
+ bool UseReciprocalEst;
+
/// Processor has AVX-512 PreFetch Instructions
bool HasPFI;
-
+
/// Processor has AVX-512 Exponential and Reciprocal Instructions
bool HasERI;
-
+
/// Processor has AVX-512 Conflict Detection Instructions
bool HasCDI;
-
+
+ /// Processor has AVX-512 Doubleword and Quadword instructions
+ bool HasDQI;
+
+ /// Processor has AVX-512 Byte and Word instructions
+ bool HasBWI;
+
+ /// Processor has AVX-512 Vector Length eXtenstions
+ bool HasVLX;
+
/// stackAlignment - The minimum alignment known to hold of the stack frame on
/// entry to the function and which must be maintained by every function.
unsigned stackAlignment;
InstrItineraryData InstrItins;
private:
+ // Calculates type size & alignment
+ const DataLayout DL;
+
/// StackAlignOverride - Override the stack alignment.
unsigned StackAlignOverride;
- /// In64BitMode - True if compiling for 64-bit, false for 32-bit.
+ /// In64BitMode - True if compiling for 64-bit, false for 16-bit or 32-bit.
bool In64BitMode;
+ /// In32BitMode - True if compiling for 32-bit, false for 16-bit or 64-bit.
+ bool In32BitMode;
+
+ /// In16BitMode - True if compiling for 16-bit, false for 32-bit or 64-bit.
+ bool In16BitMode;
+
+ X86SelectionDAGInfo TSInfo;
+ // Ordering here is important. X86InstrInfo initializes X86RegisterInfo which
+ // X86TargetLowering needs.
+ X86InstrInfo InstrInfo;
+ X86TargetLowering TLInfo;
+ X86FrameLowering FrameLowering;
+
public:
/// This constructor initializes the data members to match that
/// of the specified triple.
///
X86Subtarget(const std::string &TT, const std::string &CPU,
- const std::string &FS,
- unsigned StackAlignOverride, bool is64Bit);
+ const std::string &FS, const X86TargetMachine &TM,
+ unsigned StackAlignOverride);
+
+ const X86TargetLowering *getTargetLowering() const override {
+ return &TLInfo;
+ }
+ const X86InstrInfo *getInstrInfo() const override { return &InstrInfo; }
+ const DataLayout *getDataLayout() const override { return &DL; }
+ const X86FrameLowering *getFrameLowering() const override {
+ return &FrameLowering;
+ }
+ const X86SelectionDAGInfo *getSelectionDAGInfo() const override {
+ return &TSInfo;
+ }
+ const X86RegisterInfo *getRegisterInfo() const override {
+ return &getInstrInfo()->getRegisterInfo();
+ }
/// getStackAlignment - Returns the minimum alignment known to hold of the
/// stack frame on entry to the function and which must be maintained by every
/// subtarget options. Definition of function is auto generated by tblgen.
void ParseSubtargetFeatures(StringRef CPU, StringRef FS);
- /// AutoDetectSubtargetFeatures - Auto-detect CPU features using CPUID
- /// instruction.
- void AutoDetectSubtargetFeatures();
-
- /// \brief Reset the features for the X86 target.
- virtual void resetSubtargetFeatures(const MachineFunction *MF);
private:
+ /// \brief Initialize the full set of dependencies so we can use an initializer
+ /// list for X86Subtarget.
+ X86Subtarget &initializeSubtargetDependencies(StringRef CPU, StringRef FS);
void initializeEnvironment();
- void resetSubtargetFeatures(StringRef CPU, StringRef FS);
+ void initSubtargetFeatures(StringRef CPU, StringRef FS);
public:
/// Is this x86_64? (disregarding specific ABI / programming model)
bool is64Bit() const {
return In64BitMode;
}
+ bool is32Bit() const {
+ return In32BitMode;
+ }
+
+ bool is16Bit() const {
+ return In16BitMode;
+ }
+
/// Is this x86_64 with the ILP32 programming model (x32 ABI)?
bool isTarget64BitILP32() const {
- return In64BitMode && (TargetTriple.getEnvironment() == Triple::GNUX32);
+ return In64BitMode && (TargetTriple.getEnvironment() == Triple::GNUX32 ||
+ TargetTriple.isOSNaCl());
}
/// Is this x86_64 with the LP64 programming model (standard AMD64, no x32)?
bool isTarget64BitLP64() const {
- return In64BitMode && (TargetTriple.getEnvironment() != Triple::GNUX32);
+ return In64BitMode && (TargetTriple.getEnvironment() != Triple::GNUX32 &&
+ !TargetTriple.isOSNaCl());
}
PICStyles::Style getPICStyle() const { return PICStyle; }
// FIXME: Favor FMA when both are enabled. Is this the right thing to do?
bool hasFMA4() const { return HasFMA4 && !HasFMA; }
bool hasXOP() const { return HasXOP; }
+ bool hasTBM() const { return HasTBM; }
bool hasMOVBE() const { return HasMOVBE; }
bool hasRDRAND() const { return HasRDRAND; }
bool hasF16C() const { return HasF16C; }
bool hasRTM() const { return HasRTM; }
bool hasHLE() const { return HasHLE; }
bool hasADX() const { return HasADX; }
+ bool hasSHA() const { return HasSHA; }
+ bool hasSGX() const { return HasSGX; }
bool hasPRFCHW() const { return HasPRFCHW; }
bool hasRDSEED() const { return HasRDSEED; }
+ bool hasSMAP() const { return HasSMAP; }
bool isBTMemSlow() const { return IsBTMemSlow; }
+ bool isSHLDSlow() const { return IsSHLDSlow; }
bool isUnalignedMemAccessFast() const { return IsUAMemFast; }
+ bool isUnalignedMem32Slow() const { return IsUAMem32Slow; }
bool hasVectorUAMem() const { return HasVectorUAMem; }
bool hasCmpxchg16b() const { return HasCmpxchg16b; }
bool useLeaForSP() const { return UseLeaForSP; }
- bool hasSlowDivide() const { return HasSlowDivide; }
+ bool hasSlowDivide32() const { return HasSlowDivide32; }
+ bool hasSlowDivide64() const { return HasSlowDivide64; }
bool padShortFunctions() const { return PadShortFunctions; }
bool callRegIndirect() const { return CallRegIndirect; }
bool LEAusesAG() const { return LEAUsesAG; }
+ bool slowLEA() const { return SlowLEA; }
+ bool slowIncDec() const { return SlowIncDec; }
+ bool useSqrtEst() const { return UseSqrtEst; }
+ bool useReciprocalEst() const { return UseReciprocalEst; }
bool hasCDI() const { return HasCDI; }
bool hasPFI() const { return HasPFI; }
bool hasERI() const { return HasERI; }
+ bool hasDQI() const { return HasDQI; }
+ bool hasBWI() const { return HasBWI; }
+ bool hasVLX() const { return HasVLX; }
bool isAtom() const { return X86ProcFamily == IntelAtom; }
+ bool isSLM() const { return X86ProcFamily == IntelSLM; }
const Triple &getTargetTriple() const { return TargetTriple; }
bool isTargetDarwin() const { return TargetTriple.isOSDarwin(); }
- bool isTargetFreeBSD() const {
- return TargetTriple.getOS() == Triple::FreeBSD;
+ bool isTargetFreeBSD() const { return TargetTriple.isOSFreeBSD(); }
+ bool isTargetSolaris() const { return TargetTriple.isOSSolaris(); }
+
+ bool isTargetELF() const { return TargetTriple.isOSBinFormatELF(); }
+ bool isTargetCOFF() const { return TargetTriple.isOSBinFormatCOFF(); }
+ bool isTargetMacho() const { return TargetTriple.isOSBinFormatMachO(); }
+
+ bool isTargetLinux() const { return TargetTriple.isOSLinux(); }
+ bool isTargetNaCl() const { return TargetTriple.isOSNaCl(); }
+ bool isTargetNaCl32() const { return isTargetNaCl() && !is64Bit(); }
+ bool isTargetNaCl64() const { return isTargetNaCl() && is64Bit(); }
+
+ bool isTargetWindowsMSVC() const {
+ return TargetTriple.isWindowsMSVCEnvironment();
}
- bool isTargetSolaris() const {
- return TargetTriple.getOS() == Triple::Solaris;
+
+ bool isTargetKnownWindowsMSVC() const {
+ return TargetTriple.isKnownWindowsMSVCEnvironment();
}
- bool isTargetELF() const {
- return (TargetTriple.getEnvironment() == Triple::ELF ||
- TargetTriple.isOSBinFormatELF());
+
+ bool isTargetWindowsCygwin() const {
+ return TargetTriple.isWindowsCygwinEnvironment();
}
- bool isTargetLinux() const { return TargetTriple.getOS() == Triple::Linux; }
- bool isTargetNaCl() const {
- return TargetTriple.getOS() == Triple::NaCl;
+
+ bool isTargetWindowsGNU() const {
+ return TargetTriple.isWindowsGNUEnvironment();
}
- bool isTargetNaCl32() const { return isTargetNaCl() && !is64Bit(); }
- bool isTargetNaCl64() const { return isTargetNaCl() && is64Bit(); }
- bool isTargetWindows() const { return TargetTriple.getOS() == Triple::Win32; }
- bool isTargetMingw() const { return TargetTriple.getOS() == Triple::MinGW32; }
- bool isTargetCygwin() const { return TargetTriple.getOS() == Triple::Cygwin; }
- bool isTargetCygMing() const { return TargetTriple.isOSCygMing(); }
- bool isTargetCOFF() const {
- return (TargetTriple.getEnvironment() != Triple::ELF &&
- TargetTriple.isOSBinFormatCOFF());
+
+ bool isTargetWindowsItanium() const {
+ return TargetTriple.isWindowsItaniumEnvironment();
}
- bool isTargetEnvMacho() const { return TargetTriple.isEnvironmentMachO(); }
+
+ bool isTargetCygMing() const { return TargetTriple.isOSCygMing(); }
+
+ bool isOSWindows() const { return TargetTriple.isOSWindows(); }
bool isTargetWin64() const {
return In64BitMode && TargetTriple.isOSWindows();
}
bool isTargetWin32() const {
- return !In64BitMode && (isTargetCygMing() || isTargetWindows());
+ return !In64BitMode && (isTargetCygMing() || isTargetKnownWindowsMSVC());
}
bool isPICStyleSet() const { return PICStyle != PICStyles::None; }
/// memset with zero passed as the second argument. Otherwise it
/// returns null.
const char *getBZeroEntry() const;
-
+
/// This function returns true if the target has sincos() routine in its
/// compiler runtime or math libraries.
bool hasSinCos() const;
- /// enablePostRAScheduler - run for Atom optimization.
- bool enablePostRAScheduler(CodeGenOpt::Level OptLevel,
- TargetSubtargetInfo::AntiDepBreakMode& Mode,
- RegClassVector& CriticalPathRCs) const;
+ /// Enable the MachineScheduler pass for all X86 subtargets.
+ bool enableMachineScheduler() const override { return true; }
- bool postRAScheduler() const { return PostRAScheduler; }
+ bool enableEarlyIfConversion() const override;
/// getInstrItins = Return the instruction itineraries based on the
/// subtarget selection.
- const InstrItineraryData &getInstrItineraryData() const { return InstrItins; }
+ const InstrItineraryData *getInstrItineraryData() const override {
+ return &InstrItins;
+ }
+
+ AntiDepBreakMode getAntiDepBreakMode() const override {
+ return TargetSubtargetInfo::ANTIDEP_CRITICAL;
+ }
};
} // End llvm namespace
projects / oota-llvm.git / blobdiff