#ifndef X86SUBTARGET_H
#define X86SUBTARGET_H
-#include "llvm/CallingConv.h"
#include "llvm/ADT/Triple.h"
+#include "llvm/CallingConv.h"
#include "llvm/Target/TargetSubtargetInfo.h"
#include <string>
/// X86ProcFamily - X86 processor family: Intel Atom, and others
X86ProcFamilyEnum X86ProcFamily;
-
+
/// PICStyle - Which PIC style to use
///
PICStyles::Style PICStyle;
/// HasAES - Target has AES instructions
bool HasAES;
- /// HasCLMUL - Target has carry-less multiplication
- bool HasCLMUL;
+ /// HasPCLMUL - Target has carry-less multiplication
+ bool HasPCLMUL;
- /// HasFMA3 - Target has 3-operand fused multiply-add
- bool HasFMA3;
+ /// HasFMA - Target has 3-operand fused multiply-add
+ bool HasFMA;
/// HasFMA4 - Target has 4-operand fused multiply-add
bool HasFMA4;
/// HasBMI2 - Processor has BMI2 instructions.
bool HasBMI2;
+ /// HasRTM - Processor has RTM instructions.
+ bool HasRTM;
+
/// IsBTMemSlow - True if BT (bit test) of memory instructions are slow.
bool IsBTMemSlow;
/// 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;
+
/// PostRAScheduler - True if using post-register-allocation scheduler.
bool PostRAScheduler;
/// TargetTriple - What processor and OS we're targeting.
Triple TargetTriple;
-
+
/// Instruction itineraries for scheduling
InstrItineraryData InstrItins;
bool hasSSE42() const { return X86SSELevel >= SSE42; }
bool hasAVX() const { return X86SSELevel >= AVX; }
bool hasAVX2() const { return X86SSELevel >= AVX2; }
+ bool hasFp256() const { return hasAVX(); }
+ bool hasInt256() const { return hasAVX2(); }
bool hasSSE4A() const { return HasSSE4A; }
bool has3DNow() const { return X863DNowLevel >= ThreeDNow; }
bool has3DNowA() const { return X863DNowLevel >= ThreeDNowA; }
bool hasPOPCNT() const { return HasPOPCNT; }
bool hasAES() const { return HasAES; }
- bool hasCLMUL() const { return HasCLMUL; }
- bool hasFMA3() const { return HasFMA3; }
- bool hasFMA4() const { return HasFMA4; }
+ bool hasPCLMUL() const { return HasPCLMUL; }
+ bool hasFMA() const { return HasFMA; }
+ // 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 hasMOVBE() const { return HasMOVBE; }
bool hasRDRAND() const { return HasRDRAND; }
bool hasLZCNT() const { return HasLZCNT; }
bool hasBMI() const { return HasBMI; }
bool hasBMI2() const { return HasBMI2; }
+ bool hasRTM() const { return HasRTM; }
bool isBTMemSlow() const { return IsBTMemSlow; }
bool isUnalignedMemAccessFast() const { return IsUAMemFast; }
bool hasVectorUAMem() const { return HasVectorUAMem; }
bool hasCmpxchg16b() const { return HasCmpxchg16b; }
bool useLeaForSP() const { return UseLeaForSP; }
+ bool hasSlowDivide() const { return HasSlowDivide; }
bool isAtom() const { return X86ProcFamily == IntelAtom; }
bool isTargetSolaris() const {
return TargetTriple.getOS() == Triple::Solaris;
}
-
- // ELF is a reasonably sane default and the only other X86 targets we
- // support are Darwin and Windows. Just use "not those".
- bool isTargetELF() const { return TargetTriple.isOSBinFormatELF(); }
+ bool isTargetELF() const {
+ return (TargetTriple.getEnvironment() == Triple::ELF ||
+ TargetTriple.isOSBinFormatELF());
+ }
bool isTargetLinux() const { return TargetTriple.getOS() == Triple::Linux; }
bool isTargetNaCl() const {
- return TargetTriple.getOS() == Triple::NativeClient;
+ return TargetTriple.getOS() == Triple::NaCl;
}
bool isTargetNaCl32() const { return isTargetNaCl() && !is64Bit(); }
bool isTargetNaCl64() const { return isTargetNaCl() && is64Bit(); }
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.isOSBinFormatCOFF(); }
+ bool isTargetCOFF() const {
+ return (TargetTriple.getEnvironment() != Triple::ELF &&
+ TargetTriple.isOSBinFormatCOFF());
+ }
bool isTargetEnvMacho() const { return TargetTriple.isEnvironmentMachO(); }
bool isTargetWin64() const {
/// returns null.
const char *getBZeroEntry() const;
- /// getSpecialAddressLatency - For targets where it is beneficial to
- /// backschedule instructions that compute addresses, return a value
- /// indicating the number of scheduling cycles of backscheduling that
- /// should be attempted.
- unsigned getSpecialAddressLatency() const;
-
/// enablePostRAScheduler - run for Atom optimization.
bool enablePostRAScheduler(CodeGenOpt::Level OptLevel,
TargetSubtargetInfo::AntiDepBreakMode& Mode,