llvm.org GIT mirror llvm / d0e93f2 lib / Target / X86 / X86Subtarget.h
d0e93f2

Tree @d0e93f2 (Download .tar.gz)

X86Subtarget.h @d0e93f2raw · history · blame

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
//===-- X86Subtarget.h - Define Subtarget for the X86 ----------*- C++ -*--===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file declares the X86 specific subclass of TargetSubtargetInfo.
//
//===----------------------------------------------------------------------===//

#ifndef X86SUBTARGET_H
#define X86SUBTARGET_H

#include "llvm/ADT/Triple.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/Target/TargetSubtargetInfo.h"
#include <string>

#define GET_SUBTARGETINFO_HEADER
#include "X86GenSubtargetInfo.inc"

namespace llvm {
class GlobalValue;
class StringRef;
class TargetMachine;

/// PICStyles - The X86 backend supports a number of different styles of PIC.
///
namespace PICStyles {
enum Style {
  StubPIC,          // Used on i386-darwin in -fPIC mode.
  StubDynamicNoPIC, // Used on i386-darwin in -mdynamic-no-pic mode.
  GOT,              // Used on many 32-bit unices in -fPIC mode.
  RIPRel,           // Used on X86-64 when not in -static mode.
  None              // Set when in -static mode (not PIC or DynamicNoPIC mode).
};
}

class X86Subtarget final : public X86GenSubtargetInfo {
protected:
  enum X86SSEEnum {
    NoMMXSSE, MMX, SSE1, SSE2, SSE3, SSSE3, SSE41, SSE42, AVX, AVX2, AVX512F
  };

  enum X863DNowEnum {
    NoThreeDNow, ThreeDNow, ThreeDNowA
  };

  enum X86ProcFamilyEnum {
    Others, IntelAtom, IntelSLM
  };

  /// X86ProcFamily - X86 processor family: Intel Atom, and others
  X86ProcFamilyEnum X86ProcFamily;

  /// PICStyle - Which PIC style to use
  ///
  PICStyles::Style PICStyle;

  /// X86SSELevel - MMX, SSE1, SSE2, SSE3, SSSE3, SSE41, SSE42, or
  /// none supported.
  X86SSEEnum X86SSELevel;

  /// X863DNowLevel - 3DNow or 3DNow Athlon, or none supported.
  ///
  X863DNowEnum X863DNowLevel;

  /// HasCMov - True if this processor has conditional move instructions
  /// (generally pentium pro+).
  bool HasCMov;

  /// HasX86_64 - True if the processor supports X86-64 instructions.
  ///
  bool HasX86_64;

  /// HasPOPCNT - True if the processor supports POPCNT.
  bool HasPOPCNT;

  /// HasSSE4A - True if the processor supports SSE4A instructions.
  bool HasSSE4A;

  /// HasAES - Target has AES instructions
  bool HasAES;

  /// HasPCLMUL - Target has carry-less multiplication
  bool HasPCLMUL;

  /// HasFMA - Target has 3-operand fused multiply-add
  bool HasFMA;

  /// HasFMA4 - Target has 4-operand fused multiply-add
  bool HasFMA4;

  /// 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;

  /// HasRDRAND - True if the processor has the RDRAND instruction.
  bool HasRDRAND;

  /// HasF16C - Processor has 16-bit floating point conversion instructions.
  bool HasF16C;

  /// HasFSGSBase - Processor has FS/GS base insturctions.
  bool HasFSGSBase;

  /// HasLZCNT - Processor has LZCNT instruction.
  bool HasLZCNT;

  /// HasBMI - Processor has BMI1 instructions.
  bool HasBMI;

  /// HasBMI2 - Processor has BMI2 instructions.
  bool HasBMI2;

  /// HasRTM - Processor has RTM instructions.
  bool HasRTM;

  /// HasHLE - Processor has HLE.
  bool HasHLE;

  /// HasADX - Processor has ADX instructions.
  bool HasADX;

  /// HasSHA - Processor has SHA instructions.
  bool HasSHA;

  /// HasPRFCHW - Processor has PRFCHW instructions.
  bool HasPRFCHW;

  /// HasRDSEED - Processor has RDSEED instructions.
  bool HasRDSEED;

  /// 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;

  /// HasVectorUAMem - True if SIMD operations can have unaligned memory
  /// operands. This may require setting a feature bit in the processor.
  bool HasVectorUAMem;

  /// HasCmpxchg16b - True if this processor has the CMPXCHG16B instruction;
  /// this is true for most x86-64 chips, but not the first AMD chips.
  bool HasCmpxchg16b;

  /// UseLeaForSP - True if the LEA instruction should be used for adjusting
  /// 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;

  /// CallRegIndirect - True if the Calls with memory reference should be converted
  /// to a register-based indirect call.
  bool CallRegIndirect;
  /// LEAUsesAG - True if the LEA instruction inputs have to be ready at
  ///             address generation (AG) time.
  bool LEAUsesAG;

  /// 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;
  
  /// 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;

  /// Max. memset / memcpy size that is turned into rep/movs, rep/stos ops.
  ///
  unsigned MaxInlineSizeThreshold;

  /// TargetTriple - What processor and OS we're targeting.
  Triple TargetTriple;

  /// Instruction itineraries for scheduling
  InstrItineraryData InstrItins;

private:
  /// StackAlignOverride - Override the stack alignment.
  unsigned StackAlignOverride;

  /// 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;

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);

  /// getStackAlignment - Returns the minimum alignment known to hold of the
  /// stack frame on entry to the function and which must be maintained by every
  /// function for this subtarget.
  unsigned getStackAlignment() const { return stackAlignment; }

  /// getMaxInlineSizeThreshold - Returns the maximum memset / memcpy size
  /// that still makes it profitable to inline the call.
  unsigned getMaxInlineSizeThreshold() const { return MaxInlineSizeThreshold; }

  /// ParseSubtargetFeatures - Parses features string setting specified
  /// subtarget options.  Definition of function is auto generated by tblgen.
  void ParseSubtargetFeatures(StringRef CPU, StringRef FS);

  /// \brief Reset the features for the X86 target.
  void resetSubtargetFeatures(const MachineFunction *MF) override;
private:
  void initializeEnvironment();
  void resetSubtargetFeatures(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 ||
                           TargetTriple.getOS() == Triple::NaCl);
  }

  /// 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; }

  bool hasCMov() const { return HasCMov; }
  bool hasMMX() const { return X86SSELevel >= MMX; }
  bool hasSSE1() const { return X86SSELevel >= SSE1; }
  bool hasSSE2() const { return X86SSELevel >= SSE2; }
  bool hasSSE3() const { return X86SSELevel >= SSE3; }
  bool hasSSSE3() const { return X86SSELevel >= SSSE3; }
  bool hasSSE41() const { return X86SSELevel >= SSE41; }
  bool hasSSE42() const { return X86SSELevel >= SSE42; }
  bool hasAVX() const { return X86SSELevel >= AVX; }
  bool hasAVX2() const { return X86SSELevel >= AVX2; }
  bool hasAVX512() const { return X86SSELevel >= AVX512F; }
  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 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 hasTBM() const { return HasTBM; }
  bool hasMOVBE() const { return HasMOVBE; }
  bool hasRDRAND() const { return HasRDRAND; }
  bool hasF16C() const { return HasF16C; }
  bool hasFSGSBase() const { return HasFSGSBase; }
  bool hasLZCNT() const { return HasLZCNT; }
  bool hasBMI() const { return HasBMI; }
  bool hasBMI2() const { return HasBMI2; }
  bool hasRTM() const { return HasRTM; }
  bool hasHLE() const { return HasHLE; }
  bool hasADX() const { return HasADX; }
  bool hasSHA() const { return HasSHA; }
  bool hasPRFCHW() const { return HasPRFCHW; }
  bool hasRDSEED() const { return HasRDSEED; }
  bool isBTMemSlow() const { return IsBTMemSlow; }
  bool isSHLDSlow() const { return IsSHLDSlow; }
  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 callRegIndirect() const { return CallRegIndirect; }
  bool LEAusesAG() const { return LEAUsesAG; }
  bool hasCDI() const { return HasCDI; }
  bool hasPFI() const { return HasPFI; }
  bool hasERI() const { return HasERI; }

  bool isAtom() const { return X86ProcFamily == IntelAtom; }

  const Triple &getTargetTriple() const { return TargetTriple; }

  bool isTargetDarwin() const { return TargetTriple.isOSDarwin(); }
  bool isTargetFreeBSD() const {
    return TargetTriple.getOS() == Triple::FreeBSD;
  }
  bool isTargetSolaris() const {
    return TargetTriple.getOS() == Triple::Solaris;
  }

  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 isTargetKnownWindowsMSVC() const {
    return TargetTriple.isKnownWindowsMSVCEnvironment();
  }

  bool isTargetWindowsCygwin() const {
    return TargetTriple.isWindowsCygwinEnvironment();
  }

  bool isTargetWindowsGNU() const {
    return TargetTriple.isWindowsGNUEnvironment();
  }

  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() || isTargetKnownWindowsMSVC());
  }

  bool isPICStyleSet() const { return PICStyle != PICStyles::None; }
  bool isPICStyleGOT() const { return PICStyle == PICStyles::GOT; }
  bool isPICStyleRIPRel() const { return PICStyle == PICStyles::RIPRel; }

  bool isPICStyleStubPIC() const {
    return PICStyle == PICStyles::StubPIC;
  }

  bool isPICStyleStubNoDynamic() const {
    return PICStyle == PICStyles::StubDynamicNoPIC;
  }
  bool isPICStyleStubAny() const {
    return PICStyle == PICStyles::StubDynamicNoPIC ||
           PICStyle == PICStyles::StubPIC;
  }

  bool isCallingConvWin64(CallingConv::ID CC) const {
    return (isTargetWin64() && CC != CallingConv::X86_64_SysV) ||
           CC == CallingConv::X86_64_Win64;
  }

  /// ClassifyGlobalReference - Classify a global variable reference for the
  /// current subtarget according to how we should reference it in a non-pcrel
  /// context.
  unsigned char ClassifyGlobalReference(const GlobalValue *GV,
                                        const TargetMachine &TM)const;

  /// ClassifyBlockAddressReference - Classify a blockaddress reference for the
  /// current subtarget according to how we should reference it in a non-pcrel
  /// context.
  unsigned char ClassifyBlockAddressReference() const;

  /// IsLegalToCallImmediateAddr - Return true if the subtarget allows calls
  /// to immediate address.
  bool IsLegalToCallImmediateAddr(const TargetMachine &TM) const;

  /// This function returns the name of a function which has an interface
  /// like the non-standard bzero function, if such a function exists on
  /// the current subtarget and it is considered prefereable over
  /// 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;

  /// Enable the MachineScheduler pass for all X86 subtargets.
  bool enableMachineScheduler() const override { return true; }

  /// enablePostRAScheduler - run for Atom optimization.
  bool enablePostRAScheduler(CodeGenOpt::Level OptLevel,
                             TargetSubtargetInfo::AntiDepBreakMode& Mode,
                             RegClassVector& CriticalPathRCs) const override;

  bool postRAScheduler() const { return PostRAScheduler; }

  /// getInstrItins = Return the instruction itineraries based on the
  /// subtarget selection.
  const InstrItineraryData &getInstrItineraryData() const { return InstrItins; }
};

} // End llvm namespace

#endif