aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm12/lib/Target/ARM/ARMCallingConv.cpp
blob: 67c822a5b6ef7e1dc4ef6f350f4e5fdde6147b0d (plain) (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
//=== ARMCallingConv.cpp - ARM Custom CC Routines ---------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file contains the custom routines for the ARM Calling Convention that
// aren't done by tablegen, and includes the table generated implementations.
//
//===----------------------------------------------------------------------===//

#include "ARM.h"
#include "ARMCallingConv.h"
#include "ARMSubtarget.h"
#include "ARMRegisterInfo.h"
using namespace llvm;

// APCS f64 is in register pairs, possibly split to stack
static bool f64AssignAPCS(unsigned ValNo, MVT ValVT, MVT LocVT,
                          CCValAssign::LocInfo LocInfo,
                          CCState &State, bool CanFail) {
  static const MCPhysReg RegList[] = { ARM::R0, ARM::R1, ARM::R2, ARM::R3 };

  // Try to get the first register.
  if (unsigned Reg = State.AllocateReg(RegList))
    State.addLoc(CCValAssign::getCustomReg(ValNo, ValVT, Reg, LocVT, LocInfo));
  else {
    // For the 2nd half of a v2f64, do not fail.
    if (CanFail)
      return false;

    // Put the whole thing on the stack.
    State.addLoc(CCValAssign::getCustomMem(
        ValNo, ValVT, State.AllocateStack(8, Align(4)), LocVT, LocInfo));
    return true;
  }

  // Try to get the second register.
  if (unsigned Reg = State.AllocateReg(RegList))
    State.addLoc(CCValAssign::getCustomReg(ValNo, ValVT, Reg, LocVT, LocInfo));
  else
    State.addLoc(CCValAssign::getCustomMem(
        ValNo, ValVT, State.AllocateStack(4, Align(4)), LocVT, LocInfo));
  return true;
}

static bool CC_ARM_APCS_Custom_f64(unsigned ValNo, MVT ValVT, MVT LocVT,
                                   CCValAssign::LocInfo LocInfo,
                                   ISD::ArgFlagsTy ArgFlags,
                                   CCState &State) {
  if (!f64AssignAPCS(ValNo, ValVT, LocVT, LocInfo, State, true))
    return false;
  if (LocVT == MVT::v2f64 &&
      !f64AssignAPCS(ValNo, ValVT, LocVT, LocInfo, State, false))
    return false;
  return true;  // we handled it
}

// AAPCS f64 is in aligned register pairs
static bool f64AssignAAPCS(unsigned ValNo, MVT ValVT, MVT LocVT,
                           CCValAssign::LocInfo LocInfo,
                           CCState &State, bool CanFail) {
  static const MCPhysReg HiRegList[] = { ARM::R0, ARM::R2 };
  static const MCPhysReg LoRegList[] = { ARM::R1, ARM::R3 };
  static const MCPhysReg ShadowRegList[] = { ARM::R0, ARM::R1 };
  static const MCPhysReg GPRArgRegs[] = { ARM::R0, ARM::R1, ARM::R2, ARM::R3 };

  unsigned Reg = State.AllocateReg(HiRegList, ShadowRegList);
  if (Reg == 0) {

    // If we had R3 unallocated only, now we still must to waste it.
    Reg = State.AllocateReg(GPRArgRegs);
    assert((!Reg || Reg == ARM::R3) && "Wrong GPRs usage for f64");

    // For the 2nd half of a v2f64, do not just fail.
    if (CanFail)
      return false;

    // Put the whole thing on the stack.
    State.addLoc(CCValAssign::getCustomMem(
        ValNo, ValVT, State.AllocateStack(8, Align(8)), LocVT, LocInfo));
    return true;
  }

  unsigned i;
  for (i = 0; i < 2; ++i)
    if (HiRegList[i] == Reg)
      break;

  unsigned T = State.AllocateReg(LoRegList[i]);
  (void)T;
  assert(T == LoRegList[i] && "Could not allocate register");

  State.addLoc(CCValAssign::getCustomReg(ValNo, ValVT, Reg, LocVT, LocInfo));
  State.addLoc(CCValAssign::getCustomReg(ValNo, ValVT, LoRegList[i],
                                         LocVT, LocInfo));
  return true;
}

static bool CC_ARM_AAPCS_Custom_f64(unsigned ValNo, MVT ValVT, MVT LocVT,
                                    CCValAssign::LocInfo LocInfo,
                                    ISD::ArgFlagsTy ArgFlags,
                                    CCState &State) {
  if (!f64AssignAAPCS(ValNo, ValVT, LocVT, LocInfo, State, true))
    return false;
  if (LocVT == MVT::v2f64 &&
      !f64AssignAAPCS(ValNo, ValVT, LocVT, LocInfo, State, false))
    return false;
  return true;  // we handled it
}

static bool f64RetAssign(unsigned ValNo, MVT ValVT, MVT LocVT,
                         CCValAssign::LocInfo LocInfo, CCState &State) {
  static const MCPhysReg HiRegList[] = { ARM::R0, ARM::R2 };
  static const MCPhysReg LoRegList[] = { ARM::R1, ARM::R3 };

  unsigned Reg = State.AllocateReg(HiRegList, LoRegList);
  if (Reg == 0)
    return false; // we didn't handle it

  unsigned i;
  for (i = 0; i < 2; ++i)
    if (HiRegList[i] == Reg)
      break;

  State.addLoc(CCValAssign::getCustomReg(ValNo, ValVT, Reg, LocVT, LocInfo));
  State.addLoc(CCValAssign::getCustomReg(ValNo, ValVT, LoRegList[i],
                                         LocVT, LocInfo));
  return true;
}

static bool RetCC_ARM_APCS_Custom_f64(unsigned ValNo, MVT ValVT, MVT LocVT,
                                      CCValAssign::LocInfo LocInfo,
                                      ISD::ArgFlagsTy ArgFlags,
                                      CCState &State) {
  if (!f64RetAssign(ValNo, ValVT, LocVT, LocInfo, State))
    return false;
  if (LocVT == MVT::v2f64 && !f64RetAssign(ValNo, ValVT, LocVT, LocInfo, State))
    return false;
  return true;  // we handled it
}

static bool RetCC_ARM_AAPCS_Custom_f64(unsigned ValNo, MVT ValVT, MVT LocVT,
                                       CCValAssign::LocInfo LocInfo,
                                       ISD::ArgFlagsTy ArgFlags,
                                       CCState &State) {
  return RetCC_ARM_APCS_Custom_f64(ValNo, ValVT, LocVT, LocInfo, ArgFlags,
                                   State);
}

static const MCPhysReg RRegList[] = { ARM::R0,  ARM::R1,  ARM::R2,  ARM::R3 };

static const MCPhysReg SRegList[] = { ARM::S0,  ARM::S1,  ARM::S2,  ARM::S3,
                                      ARM::S4,  ARM::S5,  ARM::S6,  ARM::S7,
                                      ARM::S8,  ARM::S9,  ARM::S10, ARM::S11,
                                      ARM::S12, ARM::S13, ARM::S14,  ARM::S15 };
static const MCPhysReg DRegList[] = { ARM::D0, ARM::D1, ARM::D2, ARM::D3,
                                      ARM::D4, ARM::D5, ARM::D6, ARM::D7 };
static const MCPhysReg QRegList[] = { ARM::Q0, ARM::Q1, ARM::Q2, ARM::Q3 };


// Allocate part of an AAPCS HFA or HVA. We assume that each member of the HA
// has InConsecutiveRegs set, and that the last member also has
// InConsecutiveRegsLast set. We must process all members of the HA before
// we can allocate it, as we need to know the total number of registers that
// will be needed in order to (attempt to) allocate a contiguous block.
static bool CC_ARM_AAPCS_Custom_Aggregate(unsigned ValNo, MVT ValVT,
                                          MVT LocVT,
                                          CCValAssign::LocInfo LocInfo,
                                          ISD::ArgFlagsTy ArgFlags,
                                          CCState &State) {
  SmallVectorImpl<CCValAssign> &PendingMembers = State.getPendingLocs();

  // AAPCS HFAs must have 1-4 elements, all of the same type
  if (PendingMembers.size() > 0)
    assert(PendingMembers[0].getLocVT() == LocVT);

  // Add the argument to the list to be allocated once we know the size of the
  // aggregate. Store the type's required alignment as extra info for later: in
  // the [N x i64] case all trace has been removed by the time we actually get
  // to do allocation.
  PendingMembers.push_back(CCValAssign::getPending(
      ValNo, ValVT, LocVT, LocInfo, ArgFlags.getNonZeroOrigAlign().value()));

  if (!ArgFlags.isInConsecutiveRegsLast())
    return true;

  // Try to allocate a contiguous block of registers, each of the correct
  // size to hold one member.
  auto &DL = State.getMachineFunction().getDataLayout();
  const Align StackAlign = DL.getStackAlignment();
  const Align FirstMemberAlign(PendingMembers[0].getExtraInfo());
  Align Alignment = std::min(FirstMemberAlign, StackAlign);

  ArrayRef<MCPhysReg> RegList;
  switch (LocVT.SimpleTy) {
  case MVT::i32: {
    RegList = RRegList;
    unsigned RegIdx = State.getFirstUnallocated(RegList);

    // First consume all registers that would give an unaligned object. Whether
    // we go on stack or in regs, no-one will be using them in future.
    unsigned RegAlign = alignTo(Alignment.value(), 4) / 4;
    while (RegIdx % RegAlign != 0 && RegIdx < RegList.size())
      State.AllocateReg(RegList[RegIdx++]);

    break;
  }
  case MVT::f16:
  case MVT::bf16:
  case MVT::f32:
    RegList = SRegList;
    break;
  case MVT::v4f16:
  case MVT::v4bf16:
  case MVT::f64:
    RegList = DRegList;
    break;
  case MVT::v8f16:
  case MVT::v8bf16:
  case MVT::v2f64:
    RegList = QRegList;
    break;
  default:
    llvm_unreachable("Unexpected member type for block aggregate");
    break;
  }

  unsigned RegResult = State.AllocateRegBlock(RegList, PendingMembers.size());
  if (RegResult) {
    for (SmallVectorImpl<CCValAssign>::iterator It = PendingMembers.begin();
         It != PendingMembers.end(); ++It) {
      It->convertToReg(RegResult);
      State.addLoc(*It);
      ++RegResult;
    }
    PendingMembers.clear();
    return true;
  }

  // Register allocation failed, we'll be needing the stack
  unsigned Size = LocVT.getSizeInBits() / 8;
  if (LocVT == MVT::i32 && State.getNextStackOffset() == 0) {
    // If nothing else has used the stack until this point, a non-HFA aggregate
    // can be split between regs and stack.
    unsigned RegIdx = State.getFirstUnallocated(RegList);
    for (auto &It : PendingMembers) {
      if (RegIdx >= RegList.size())
        It.convertToMem(State.AllocateStack(Size, Align(Size)));
      else
        It.convertToReg(State.AllocateReg(RegList[RegIdx++]));

      State.addLoc(It);
    }
    PendingMembers.clear();
    return true;
  } else if (LocVT != MVT::i32)
    RegList = SRegList;

  // Mark all regs as unavailable (AAPCS rule C.2.vfp for VFP, C.6 for core)
  for (auto Reg : RegList)
    State.AllocateReg(Reg);

  // After the first item has been allocated, the rest are packed as tightly as
  // possible. (E.g. an incoming i64 would have starting Align of 8, but we'll
  // be allocating a bunch of i32 slots).
  const Align RestAlign = std::min(Alignment, Align(Size));

  for (auto &It : PendingMembers) {
    It.convertToMem(State.AllocateStack(Size, Alignment));
    State.addLoc(It);
    Alignment = RestAlign;
  }

  // All pending members have now been allocated
  PendingMembers.clear();

  // This will be allocated by the last member of the aggregate
  return true;
}

static bool CustomAssignInRegList(unsigned ValNo, MVT ValVT, MVT LocVT,
                                  CCValAssign::LocInfo LocInfo, CCState &State,
                                  ArrayRef<MCPhysReg> RegList) {
  unsigned Reg = State.AllocateReg(RegList);
  if (Reg) {
    State.addLoc(CCValAssign::getCustomReg(ValNo, ValVT, Reg, LocVT, LocInfo));
    return true;
  }
  return false;
}

static bool CC_ARM_AAPCS_Custom_f16(unsigned ValNo, MVT ValVT, MVT LocVT,
                                    CCValAssign::LocInfo LocInfo,
                                    ISD::ArgFlagsTy ArgFlags, CCState &State) {
  // f16 arguments are extended to i32 and assigned to a register in [r0, r3]
  return CustomAssignInRegList(ValNo, ValVT, MVT::i32, LocInfo, State,
                               RRegList);
}

static bool CC_ARM_AAPCS_VFP_Custom_f16(unsigned ValNo, MVT ValVT, MVT LocVT,
                                        CCValAssign::LocInfo LocInfo,
                                        ISD::ArgFlagsTy ArgFlags,
                                        CCState &State) {
  // f16 arguments are extended to f32 and assigned to a register in [s0, s15]
  return CustomAssignInRegList(ValNo, ValVT, MVT::f32, LocInfo, State,
                               SRegList);
}

// Include the table generated calling convention implementations.
#include "ARMGenCallingConv.inc"