summaryrefslogtreecommitdiff
path: root/lib/Target/AArch64/AArch64LegalizerInfo.cpp
blob: 3a456255224c5474adfa4323472bb206c8a99cda (plain)
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
//===- AArch64LegalizerInfo.cpp ----------------------------------*- C++ -*-==//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
/// \file
/// This file implements the targeting of the Machinelegalizer class for
/// AArch64.
/// \todo This should be generated by TableGen.
//===----------------------------------------------------------------------===//

#include "AArch64LegalizerInfo.h"
#include "llvm/CodeGen/GlobalISel/MachineIRBuilder.h"
#include "llvm/CodeGen/MachineInstr.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/ValueTypes.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Type.h"
#include "llvm/Target/TargetOpcodes.h"

using namespace llvm;

/// FIXME: The following static functions are SizeChangeStrategy functions
/// that are meant to temporarily mimic the behaviour of the old legalization
/// based on doubling/halving non-legal types as closely as possible. This is
/// not entirly possible as only legalizing the types that are exactly a power
/// of 2 times the size of the legal types would require specifying all those
/// sizes explicitly.
/// In practice, not specifying those isn't a problem, and the below functions
/// should disappear quickly as we add support for legalizing non-power-of-2
/// sized types further.
static void
addAndInterleaveWithUnsupported(LegalizerInfo::SizeAndActionsVec &result,
                                const LegalizerInfo::SizeAndActionsVec &v) {
  for (unsigned i = 0; i < v.size(); ++i) {
    result.push_back(v[i]);
    if (i + 1 < v[i].first && i + 1 < v.size() &&
        v[i + 1].first != v[i].first + 1)
      result.push_back({v[i].first + 1, LegalizerInfo::Unsupported});
  }
}

static LegalizerInfo::SizeAndActionsVec
widen_1_narrow_128_ToLargest(const LegalizerInfo::SizeAndActionsVec &v) {
  assert(v.size() >= 1);
  assert(v[0].first > 2);
  LegalizerInfo::SizeAndActionsVec result = {{1, LegalizerInfo::WidenScalar},
                                             {2, LegalizerInfo::Unsupported}};
  addAndInterleaveWithUnsupported(result, v);
  auto Largest = result.back().first;
  assert(Largest + 1 < 128);
  result.push_back({Largest + 1, LegalizerInfo::Unsupported});
  result.push_back({128, LegalizerInfo::NarrowScalar});
  result.push_back({129, LegalizerInfo::Unsupported});
  return result;
}

static LegalizerInfo::SizeAndActionsVec
widen_16(const LegalizerInfo::SizeAndActionsVec &v) {
  assert(v.size() >= 1);
  assert(v[0].first > 17);
  LegalizerInfo::SizeAndActionsVec result = {{1, LegalizerInfo::Unsupported},
                                             {16, LegalizerInfo::WidenScalar},
                                             {17, LegalizerInfo::Unsupported}};
  addAndInterleaveWithUnsupported(result, v);
  auto Largest = result.back().first;
  result.push_back({Largest + 1, LegalizerInfo::Unsupported});
  return result;
}

static LegalizerInfo::SizeAndActionsVec
widen_1_8(const LegalizerInfo::SizeAndActionsVec &v) {
  assert(v.size() >= 1);
  assert(v[0].first > 9);
  LegalizerInfo::SizeAndActionsVec result = {
      {1, LegalizerInfo::WidenScalar},  {2, LegalizerInfo::Unsupported},
      {8, LegalizerInfo::WidenScalar},  {9, LegalizerInfo::Unsupported}};
  addAndInterleaveWithUnsupported(result, v);
  auto Largest = result.back().first;
  result.push_back({Largest + 1, LegalizerInfo::Unsupported});
  return result;
}

static LegalizerInfo::SizeAndActionsVec
widen_1_8_16(const LegalizerInfo::SizeAndActionsVec &v) {
  assert(v.size() >= 1);
  assert(v[0].first > 17);
  LegalizerInfo::SizeAndActionsVec result = {
      {1, LegalizerInfo::WidenScalar},  {2, LegalizerInfo::Unsupported},
      {8, LegalizerInfo::WidenScalar},  {9, LegalizerInfo::Unsupported},
      {16, LegalizerInfo::WidenScalar}, {17, LegalizerInfo::Unsupported}};
  addAndInterleaveWithUnsupported(result, v);
  auto Largest = result.back().first;
  result.push_back({Largest + 1, LegalizerInfo::Unsupported});
  return result;
}

static LegalizerInfo::SizeAndActionsVec
widen_1_8_16_narrowToLargest(const LegalizerInfo::SizeAndActionsVec &v) {
  assert(v.size() >= 1);
  assert(v[0].first > 17);
  LegalizerInfo::SizeAndActionsVec result = {
      {1, LegalizerInfo::WidenScalar},  {2, LegalizerInfo::Unsupported},
      {8, LegalizerInfo::WidenScalar},  {9, LegalizerInfo::Unsupported},
      {16, LegalizerInfo::WidenScalar}, {17, LegalizerInfo::Unsupported}};
  addAndInterleaveWithUnsupported(result, v);
  auto Largest = result.back().first;
  result.push_back({Largest + 1, LegalizerInfo::NarrowScalar});
  return result;
}

static LegalizerInfo::SizeAndActionsVec
widen_1_8_16_32(const LegalizerInfo::SizeAndActionsVec &v) {
  assert(v.size() >= 1);
  assert(v[0].first > 33);
  LegalizerInfo::SizeAndActionsVec result = {
      {1, LegalizerInfo::WidenScalar},  {2, LegalizerInfo::Unsupported},
      {8, LegalizerInfo::WidenScalar},  {9, LegalizerInfo::Unsupported},
      {16, LegalizerInfo::WidenScalar}, {17, LegalizerInfo::Unsupported},
      {32, LegalizerInfo::WidenScalar}, {33, LegalizerInfo::Unsupported}};
  addAndInterleaveWithUnsupported(result, v);
  auto Largest = result.back().first;
  result.push_back({Largest + 1, LegalizerInfo::Unsupported});
  return result;
}

AArch64LegalizerInfo::AArch64LegalizerInfo() {
  using namespace TargetOpcode;
  const LLT p0 = LLT::pointer(0, 64);
  const LLT s1 = LLT::scalar(1);
  const LLT s8 = LLT::scalar(8);
  const LLT s16 = LLT::scalar(16);
  const LLT s32 = LLT::scalar(32);
  const LLT s64 = LLT::scalar(64);
  const LLT s128 = LLT::scalar(128);
  const LLT v2s32 = LLT::vector(2, 32);
  const LLT v4s32 = LLT::vector(4, 32);
  const LLT v2s64 = LLT::vector(2, 64);

  for (auto Ty : {p0, s1, s8, s16, s32, s64})
    setAction({G_IMPLICIT_DEF, Ty}, Legal);

  for (auto Ty : {s16, s32, s64, p0})
    setAction({G_PHI, Ty}, Legal);

  setLegalizeScalarToDifferentSizeStrategy(G_PHI, 0, widen_1_8);

  for (auto Ty : { s32, s64 })
    setAction({G_BSWAP, Ty}, Legal);

  for (unsigned BinOp : {G_ADD, G_SUB, G_MUL, G_AND, G_OR, G_XOR, G_SHL}) {
    // These operations naturally get the right answer when used on
    // GPR32, even if the actual type is narrower.
    for (auto Ty : {s32, s64, v2s32, v4s32, v2s64})
      setAction({BinOp, Ty}, Legal);

    if (BinOp != G_ADD)
      setLegalizeScalarToDifferentSizeStrategy(BinOp, 0,
                                               widen_1_8_16_narrowToLargest);
  }

  setAction({G_GEP, p0}, Legal);
  setAction({G_GEP, 1, s64}, Legal);

  setLegalizeScalarToDifferentSizeStrategy(G_GEP, 1, widen_1_8_16_32);

  setAction({G_PTR_MASK, p0}, Legal);

  for (unsigned BinOp : {G_LSHR, G_ASHR, G_SDIV, G_UDIV}) {
    for (auto Ty : {s32, s64})
      setAction({BinOp, Ty}, Legal);

    setLegalizeScalarToDifferentSizeStrategy(BinOp, 0, widen_1_8_16);
  }

  for (unsigned BinOp : {G_SREM, G_UREM})
    for (auto Ty : { s1, s8, s16, s32, s64 })
      setAction({BinOp, Ty}, Lower);

  for (unsigned Op : {G_SMULO, G_UMULO}) {
    setAction({Op, 0, s64}, Lower);
    setAction({Op, 1, s1}, Legal);
  }

  for (unsigned Op : {G_UADDE, G_USUBE, G_SADDO, G_SSUBO, G_SMULH, G_UMULH}) {
    for (auto Ty : { s32, s64 })
      setAction({Op, Ty}, Legal);

    setAction({Op, 1, s1}, Legal);
  }

  for (unsigned BinOp : {G_FADD, G_FSUB, G_FMA, G_FMUL, G_FDIV})
    for (auto Ty : {s32, s64})
      setAction({BinOp, Ty}, Legal);

  for (unsigned BinOp : {G_FREM, G_FPOW}) {
    setAction({BinOp, s32}, Libcall);
    setAction({BinOp, s64}, Libcall);
  }

  for (auto Ty : {s32, s64, p0}) {
    setAction({G_INSERT, Ty}, Legal);
    setAction({G_INSERT, 1, Ty}, Legal);
  }
  setLegalizeScalarToDifferentSizeStrategy(G_INSERT, 0,
                                           widen_1_8_16_narrowToLargest);
  for (auto Ty : {s1, s8, s16}) {
    setAction({G_INSERT, 1, Ty}, Legal);
    // FIXME: Can't widen the sources because that violates the constraints on
    // G_INSERT (It seems entirely reasonable that inputs shouldn't overlap).
  }

  for (auto Ty : {s1, s8, s16, s32, s64, p0})
    setAction({G_EXTRACT, Ty}, Legal);

  for (auto Ty : {s32, s64})
    setAction({G_EXTRACT, 1, Ty}, Legal);

  for (unsigned MemOp : {G_LOAD, G_STORE}) {
    for (auto Ty : {s8, s16, s32, s64, p0, v2s32})
      setAction({MemOp, Ty}, Legal);

    setLegalizeScalarToDifferentSizeStrategy(MemOp, 0,
                                             widen_1_narrow_128_ToLargest);

    // And everything's fine in addrspace 0.
    setAction({MemOp, 1, p0}, Legal);
  }

  // Constants
  for (auto Ty : {s32, s64}) {
    setAction({TargetOpcode::G_CONSTANT, Ty}, Legal);
    setAction({TargetOpcode::G_FCONSTANT, Ty}, Legal);
  }

  setAction({G_CONSTANT, p0}, Legal);

  setLegalizeScalarToDifferentSizeStrategy(G_CONSTANT, 0, widen_1_8_16);
  setLegalizeScalarToDifferentSizeStrategy(G_FCONSTANT, 0, widen_16);

  setAction({G_ICMP, 1, s32}, Legal);
  setAction({G_ICMP, 1, s64}, Legal);
  setAction({G_ICMP, 1, p0}, Legal);

  setLegalizeScalarToDifferentSizeStrategy(G_ICMP, 0, widen_1_8_16);
  setLegalizeScalarToDifferentSizeStrategy(G_FCMP, 0, widen_1_8_16);
  setLegalizeScalarToDifferentSizeStrategy(G_ICMP, 1, widen_1_8_16);

  setAction({G_ICMP, s32}, Legal);
  setAction({G_FCMP, s32}, Legal);
  setAction({G_FCMP, 1, s32}, Legal);
  setAction({G_FCMP, 1, s64}, Legal);

  // Extensions
  for (auto Ty : { s1, s8, s16, s32, s64 }) {
    setAction({G_ZEXT, Ty}, Legal);
    setAction({G_SEXT, Ty}, Legal);
    setAction({G_ANYEXT, Ty}, Legal);
  }

  // FP conversions
  for (auto Ty : { s16, s32 }) {
    setAction({G_FPTRUNC, Ty}, Legal);
    setAction({G_FPEXT, 1, Ty}, Legal);
  }

  for (auto Ty : { s32, s64 }) {
    setAction({G_FPTRUNC, 1, Ty}, Legal);
    setAction({G_FPEXT, Ty}, Legal);
  }

  // Conversions
  for (auto Ty : { s32, s64 }) {
    setAction({G_FPTOSI, 0, Ty}, Legal);
    setAction({G_FPTOUI, 0, Ty}, Legal);
    setAction({G_SITOFP, 1, Ty}, Legal);
    setAction({G_UITOFP, 1, Ty}, Legal);
  }
  setLegalizeScalarToDifferentSizeStrategy(G_FPTOSI, 0, widen_1_8_16);
  setLegalizeScalarToDifferentSizeStrategy(G_FPTOUI, 0, widen_1_8_16);
  setLegalizeScalarToDifferentSizeStrategy(G_SITOFP, 1, widen_1_8_16);
  setLegalizeScalarToDifferentSizeStrategy(G_UITOFP, 1, widen_1_8_16);

  for (auto Ty : { s32, s64 }) {
    setAction({G_FPTOSI, 1, Ty}, Legal);
    setAction({G_FPTOUI, 1, Ty}, Legal);
    setAction({G_SITOFP, 0, Ty}, Legal);
    setAction({G_UITOFP, 0, Ty}, Legal);
  }

  // Control-flow
  for (auto Ty : {s1, s8, s16, s32})
    setAction({G_BRCOND, Ty}, Legal);
  setAction({G_BRINDIRECT, p0}, Legal);

  // Select
  setLegalizeScalarToDifferentSizeStrategy(G_SELECT, 0, widen_1_8_16);

  for (auto Ty : {s32, s64, p0})
    setAction({G_SELECT, Ty}, Legal);

  setAction({G_SELECT, 1, s1}, Legal);

  // Pointer-handling
  setAction({G_FRAME_INDEX, p0}, Legal);
  setAction({G_GLOBAL_VALUE, p0}, Legal);

  for (auto Ty : {s1, s8, s16, s32, s64})
    setAction({G_PTRTOINT, 0, Ty}, Legal);

  setAction({G_PTRTOINT, 1, p0}, Legal);

  setAction({G_INTTOPTR, 0, p0}, Legal);
  setAction({G_INTTOPTR, 1, s64}, Legal);

  // Casts for 32 and 64-bit width type are just copies.
  // Same for 128-bit width type, except they are on the FPR bank.
  for (auto Ty : {s1, s8, s16, s32, s64, s128}) {
    setAction({G_BITCAST, 0, Ty}, Legal);
    setAction({G_BITCAST, 1, Ty}, Legal);
  }

  // For the sake of copying bits around, the type does not really
  // matter as long as it fits a register.
  for (int EltSize = 8; EltSize <= 64; EltSize *= 2) {
    setAction({G_BITCAST, 0, LLT::vector(128/EltSize, EltSize)}, Legal);
    setAction({G_BITCAST, 1, LLT::vector(128/EltSize, EltSize)}, Legal);
    if (EltSize >= 64)
      continue;

    setAction({G_BITCAST, 0, LLT::vector(64/EltSize, EltSize)}, Legal);
    setAction({G_BITCAST, 1, LLT::vector(64/EltSize, EltSize)}, Legal);
    if (EltSize >= 32)
      continue;

    setAction({G_BITCAST, 0, LLT::vector(32/EltSize, EltSize)}, Legal);
    setAction({G_BITCAST, 1, LLT::vector(32/EltSize, EltSize)}, Legal);
  }

  setAction({G_VASTART, p0}, Legal);

  // va_list must be a pointer, but most sized types are pretty easy to handle
  // as the destination.
  setAction({G_VAARG, 1, p0}, Legal);

  for (auto Ty : {s8, s16, s32, s64, p0})
    setAction({G_VAARG, Ty}, Custom);

  computeTables();
}

bool AArch64LegalizerInfo::legalizeCustom(MachineInstr &MI,
                                          MachineRegisterInfo &MRI,
                                          MachineIRBuilder &MIRBuilder) const {
  switch (MI.getOpcode()) {
  default:
    // No idea what to do.
    return false;
  case TargetOpcode::G_VAARG:
    return legalizeVaArg(MI, MRI, MIRBuilder);
  }

  llvm_unreachable("expected switch to return");
}

bool AArch64LegalizerInfo::legalizeVaArg(MachineInstr &MI,
                                         MachineRegisterInfo &MRI,
                                         MachineIRBuilder &MIRBuilder) const {
  MIRBuilder.setInstr(MI);
  MachineFunction &MF = MIRBuilder.getMF();
  unsigned Align = MI.getOperand(2).getImm();
  unsigned Dst = MI.getOperand(0).getReg();
  unsigned ListPtr = MI.getOperand(1).getReg();

  LLT PtrTy = MRI.getType(ListPtr);
  LLT IntPtrTy = LLT::scalar(PtrTy.getSizeInBits());

  const unsigned PtrSize = PtrTy.getSizeInBits() / 8;
  unsigned List = MRI.createGenericVirtualRegister(PtrTy);
  MIRBuilder.buildLoad(
      List, ListPtr,
      *MF.getMachineMemOperand(MachinePointerInfo(), MachineMemOperand::MOLoad,
                               PtrSize, /* Align = */ PtrSize));

  unsigned DstPtr;
  if (Align > PtrSize) {
    // Realign the list to the actual required alignment.
    auto AlignMinus1 = MIRBuilder.buildConstant(IntPtrTy, Align - 1);

    unsigned ListTmp = MRI.createGenericVirtualRegister(PtrTy);
    MIRBuilder.buildGEP(ListTmp, List, AlignMinus1->getOperand(0).getReg());

    DstPtr = MRI.createGenericVirtualRegister(PtrTy);
    MIRBuilder.buildPtrMask(DstPtr, ListTmp, Log2_64(Align));
  } else
    DstPtr = List;

  uint64_t ValSize = MRI.getType(Dst).getSizeInBits() / 8;
  MIRBuilder.buildLoad(
      Dst, DstPtr,
      *MF.getMachineMemOperand(MachinePointerInfo(), MachineMemOperand::MOLoad,
                               ValSize, std::max(Align, PtrSize)));

  unsigned SizeReg = MRI.createGenericVirtualRegister(IntPtrTy);
  MIRBuilder.buildConstant(SizeReg, alignTo(ValSize, PtrSize));

  unsigned NewList = MRI.createGenericVirtualRegister(PtrTy);
  MIRBuilder.buildGEP(NewList, DstPtr, SizeReg);

  MIRBuilder.buildStore(
      NewList, ListPtr,
      *MF.getMachineMemOperand(MachinePointerInfo(), MachineMemOperand::MOStore,
                               PtrSize, /* Align = */ PtrSize));

  MI.eraseFromParent();
  return true;
}