X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FTarget%2FX86%2FX86Subtarget.h;h=eb587a5761396378e05c3ace256e4b7a6bd43a33;hb=7fd324a31fbfd237f43d38d3a780a19fbf909ba3;hp=6841c5bafa32fab96a8ccaaef5be427be1be5aa7;hpb=a20e1e7ef596842127794372244fd5c646f71296;p=oota-llvm.git

diff --git a/lib/Target/X86/X86Subtarget.h b/lib/Target/X86/X86Subtarget.h
index 6841c5bafa3..eb587a57613 100644
--- a/lib/Target/X86/X86Subtarget.h
+++ b/lib/Target/X86/X86Subtarget.h
@@ -14,8 +14,8 @@
 #ifndef X86SUBTARGET_H
 #define X86SUBTARGET_H
 
-#include "llvm/CallingConv.h"
 #include "llvm/ADT/Triple.h"
+#include "llvm/IR/CallingConv.h"
 #include "llvm/Target/TargetSubtargetInfo.h"
 #include <string>
 
@@ -118,6 +118,9 @@ protected:
   /// 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;
 
@@ -136,9 +139,17 @@ protected:
   /// 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;
 
+  /// PadShortFunctions - True if the short functions should be padded to prevent
+  /// a stall when returning too early.
+  bool PadShortFunctions;
+
   /// 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;
@@ -183,7 +194,20 @@ public:
   /// instruction.
   void AutoDetectSubtargetFeatures();
 
-  bool is64Bit() const { return In64BitMode; }
+  /// Is this x86_64? (disregarding specific ABI / programming model)
+  bool is64Bit() const {
+    return In64BitMode;
+  }
+
+  /// Is this x86_64 with the ILP32 programming model (x32 ABI)?
+  bool isTarget64BitILP32() const {
+    return In64BitMode && (TargetTriple.getEnvironment() == Triple::GNUX32);
+  }
+
+  /// Is this x86_64 with the LP64 programming model (standard AMD64, no x32)?
+  bool isTarget64BitLP64() const {
+    return In64BitMode && (TargetTriple.getEnvironment() != Triple::GNUX32);
+  }
 
   PICStyles::Style getPICStyle() const { return PICStyle; }
   void setPICStyle(PICStyles::Style Style)  { PICStyle = Style; }
@@ -198,6 +222,8 @@ public:
   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; }
@@ -205,7 +231,8 @@ public:
   bool hasAES() const { return HasAES; }
   bool hasPCLMUL() const { return HasPCLMUL; }
   bool hasFMA() const { return HasFMA; }
-  bool hasFMA4() const { return HasFMA4; }
+  // 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; }
@@ -214,11 +241,14 @@ public:
   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 padShortFunctions() const { return PadShortFunctions; }
 
   bool isAtom() const { return X86ProcFamily == IntelAtom; }
 
@@ -231,13 +261,13 @@ public:
   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(); }
@@ -245,7 +275,10 @@ public:
   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 {
@@ -295,12 +328,10 @@ public:
   /// memset with zero passed as the second argument. Otherwise it
   /// 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;
+  
+  /// 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,