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
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
|
//===- ARMLegalizerInfo.cpp --------------------------------------*- 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
//
//===----------------------------------------------------------------------===//
/// \file
/// This file implements the targeting of the Machinelegalizer class for ARM.
/// \todo This should be generated by TableGen.
//===----------------------------------------------------------------------===//
#include "ARMLegalizerInfo.h"
#include "ARMCallLowering.h"
#include "ARMSubtarget.h"
#include "llvm/CodeGen/GlobalISel/LegalizerHelper.h"
#include "llvm/CodeGen/GlobalISel/MachineIRBuilder.h"
#include "llvm/CodeGen/LowLevelTypeUtils.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/TargetOpcodes.h"
#include "llvm/CodeGen/ValueTypes.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Type.h"
using namespace llvm;
using namespace LegalizeActions;
/// 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(
LegacyLegalizerInfo::SizeAndActionsVec &result,
const LegacyLegalizerInfo::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, LegacyLegalizeActions::Unsupported});
}
}
static LegacyLegalizerInfo::SizeAndActionsVec
widen_8_16(const LegacyLegalizerInfo::SizeAndActionsVec &v) {
assert(v.size() >= 1);
assert(v[0].first > 17);
LegacyLegalizerInfo::SizeAndActionsVec result = {
{1, LegacyLegalizeActions::Unsupported},
{8, LegacyLegalizeActions::WidenScalar},
{9, LegacyLegalizeActions::Unsupported},
{16, LegacyLegalizeActions::WidenScalar},
{17, LegacyLegalizeActions::Unsupported}};
addAndInterleaveWithUnsupported(result, v);
auto Largest = result.back().first;
result.push_back({Largest + 1, LegacyLegalizeActions::Unsupported});
return result;
}
static bool AEABI(const ARMSubtarget &ST) {
return ST.isTargetAEABI() || ST.isTargetGNUAEABI() || ST.isTargetMuslAEABI();
}
ARMLegalizerInfo::ARMLegalizerInfo(const ARMSubtarget &ST) {
using namespace TargetOpcode;
const LLT p0 = LLT::pointer(0, 32);
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);
auto &LegacyInfo = getLegacyLegalizerInfo();
if (ST.isThumb1Only()) {
// Thumb1 is not supported yet.
LegacyInfo.computeTables();
verify(*ST.getInstrInfo());
return;
}
getActionDefinitionsBuilder({G_SEXT, G_ZEXT, G_ANYEXT})
.legalForCartesianProduct({s8, s16, s32}, {s1, s8, s16});
getActionDefinitionsBuilder(G_SEXT_INREG).lower();
getActionDefinitionsBuilder({G_MUL, G_AND, G_OR, G_XOR})
.legalFor({s32})
.clampScalar(0, s32, s32);
if (ST.hasNEON())
getActionDefinitionsBuilder({G_ADD, G_SUB})
.legalFor({s32, s64})
.minScalar(0, s32);
else
getActionDefinitionsBuilder({G_ADD, G_SUB})
.legalFor({s32})
.minScalar(0, s32);
getActionDefinitionsBuilder({G_ASHR, G_LSHR, G_SHL})
.legalFor({{s32, s32}})
.minScalar(0, s32)
.clampScalar(1, s32, s32);
bool HasHWDivide = (!ST.isThumb() && ST.hasDivideInARMMode()) ||
(ST.isThumb() && ST.hasDivideInThumbMode());
if (HasHWDivide)
getActionDefinitionsBuilder({G_SDIV, G_UDIV})
.legalFor({s32})
.clampScalar(0, s32, s32);
else
getActionDefinitionsBuilder({G_SDIV, G_UDIV})
.libcallFor({s32})
.clampScalar(0, s32, s32);
for (unsigned Op : {G_SREM, G_UREM}) {
LegacyInfo.setLegalizeScalarToDifferentSizeStrategy(Op, 0, widen_8_16);
if (HasHWDivide)
LegacyInfo.setAction({Op, s32}, LegacyLegalizeActions::Lower);
else if (AEABI(ST))
LegacyInfo.setAction({Op, s32}, LegacyLegalizeActions::Custom);
else
LegacyInfo.setAction({Op, s32}, LegacyLegalizeActions::Libcall);
}
getActionDefinitionsBuilder(G_INTTOPTR)
.legalFor({{p0, s32}})
.minScalar(1, s32);
getActionDefinitionsBuilder(G_PTRTOINT)
.legalFor({{s32, p0}})
.minScalar(0, s32);
getActionDefinitionsBuilder(G_CONSTANT)
.legalFor({s32, p0})
.clampScalar(0, s32, s32);
getActionDefinitionsBuilder(G_ICMP)
.legalForCartesianProduct({s1}, {s32, p0})
.minScalar(1, s32);
getActionDefinitionsBuilder(G_SELECT)
.legalForCartesianProduct({s32, p0}, {s1})
.minScalar(0, s32);
// We're keeping these builders around because we'll want to add support for
// floating point to them.
auto &LoadStoreBuilder = getActionDefinitionsBuilder({G_LOAD, G_STORE})
.legalForTypesWithMemDesc({{s8, p0, s8, 8},
{s16, p0, s16, 8},
{s32, p0, s32, 8},
{p0, p0, p0, 8}})
.unsupportedIfMemSizeNotPow2();
getActionDefinitionsBuilder(G_FRAME_INDEX).legalFor({p0});
getActionDefinitionsBuilder(G_GLOBAL_VALUE).legalFor({p0});
auto &PhiBuilder =
getActionDefinitionsBuilder(G_PHI)
.legalFor({s32, p0})
.minScalar(0, s32);
getActionDefinitionsBuilder(G_PTR_ADD)
.legalFor({{p0, s32}})
.minScalar(1, s32);
getActionDefinitionsBuilder(G_BRCOND).legalFor({s1});
if (!ST.useSoftFloat() && ST.hasVFP2Base()) {
getActionDefinitionsBuilder(
{G_FADD, G_FSUB, G_FMUL, G_FDIV, G_FCONSTANT, G_FNEG})
.legalFor({s32, s64});
LoadStoreBuilder
.legalForTypesWithMemDesc({{s64, p0, s64, 32}})
.maxScalar(0, s32);
PhiBuilder.legalFor({s64});
getActionDefinitionsBuilder(G_FCMP).legalForCartesianProduct({s1},
{s32, s64});
getActionDefinitionsBuilder(G_MERGE_VALUES).legalFor({{s64, s32}});
getActionDefinitionsBuilder(G_UNMERGE_VALUES).legalFor({{s32, s64}});
getActionDefinitionsBuilder(G_FPEXT).legalFor({{s64, s32}});
getActionDefinitionsBuilder(G_FPTRUNC).legalFor({{s32, s64}});
getActionDefinitionsBuilder({G_FPTOSI, G_FPTOUI})
.legalForCartesianProduct({s32}, {s32, s64});
getActionDefinitionsBuilder({G_SITOFP, G_UITOFP})
.legalForCartesianProduct({s32, s64}, {s32});
} else {
getActionDefinitionsBuilder({G_FADD, G_FSUB, G_FMUL, G_FDIV})
.libcallFor({s32, s64});
LoadStoreBuilder.maxScalar(0, s32);
for (auto Ty : {s32, s64})
LegacyInfo.setAction({G_FNEG, Ty}, LegacyLegalizeActions::Lower);
getActionDefinitionsBuilder(G_FCONSTANT).customFor({s32, s64});
getActionDefinitionsBuilder(G_FCMP).customForCartesianProduct({s1},
{s32, s64});
if (AEABI(ST))
setFCmpLibcallsAEABI();
else
setFCmpLibcallsGNU();
getActionDefinitionsBuilder(G_FPEXT).libcallFor({{s64, s32}});
getActionDefinitionsBuilder(G_FPTRUNC).libcallFor({{s32, s64}});
getActionDefinitionsBuilder({G_FPTOSI, G_FPTOUI})
.libcallForCartesianProduct({s32}, {s32, s64});
getActionDefinitionsBuilder({G_SITOFP, G_UITOFP})
.libcallForCartesianProduct({s32, s64}, {s32});
}
// Just expand whatever loads and stores are left.
LoadStoreBuilder.lower();
if (!ST.useSoftFloat() && ST.hasVFP4Base())
getActionDefinitionsBuilder(G_FMA).legalFor({s32, s64});
else
getActionDefinitionsBuilder(G_FMA).libcallFor({s32, s64});
getActionDefinitionsBuilder({G_FREM, G_FPOW}).libcallFor({s32, s64});
if (ST.hasV5TOps()) {
getActionDefinitionsBuilder(G_CTLZ)
.legalFor({s32, s32})
.clampScalar(1, s32, s32)
.clampScalar(0, s32, s32);
getActionDefinitionsBuilder(G_CTLZ_ZERO_UNDEF)
.lowerFor({s32, s32})
.clampScalar(1, s32, s32)
.clampScalar(0, s32, s32);
} else {
getActionDefinitionsBuilder(G_CTLZ_ZERO_UNDEF)
.libcallFor({s32, s32})
.clampScalar(1, s32, s32)
.clampScalar(0, s32, s32);
getActionDefinitionsBuilder(G_CTLZ)
.lowerFor({s32, s32})
.clampScalar(1, s32, s32)
.clampScalar(0, s32, s32);
}
LegacyInfo.computeTables();
verify(*ST.getInstrInfo());
}
void ARMLegalizerInfo::setFCmpLibcallsAEABI() {
// FCMP_TRUE and FCMP_FALSE don't need libcalls, they should be
// default-initialized.
FCmp32Libcalls.resize(CmpInst::LAST_FCMP_PREDICATE + 1);
FCmp32Libcalls[CmpInst::FCMP_OEQ] = {
{RTLIB::OEQ_F32, CmpInst::BAD_ICMP_PREDICATE}};
FCmp32Libcalls[CmpInst::FCMP_OGE] = {
{RTLIB::OGE_F32, CmpInst::BAD_ICMP_PREDICATE}};
FCmp32Libcalls[CmpInst::FCMP_OGT] = {
{RTLIB::OGT_F32, CmpInst::BAD_ICMP_PREDICATE}};
FCmp32Libcalls[CmpInst::FCMP_OLE] = {
{RTLIB::OLE_F32, CmpInst::BAD_ICMP_PREDICATE}};
FCmp32Libcalls[CmpInst::FCMP_OLT] = {
{RTLIB::OLT_F32, CmpInst::BAD_ICMP_PREDICATE}};
FCmp32Libcalls[CmpInst::FCMP_ORD] = {{RTLIB::UO_F32, CmpInst::ICMP_EQ}};
FCmp32Libcalls[CmpInst::FCMP_UGE] = {{RTLIB::OLT_F32, CmpInst::ICMP_EQ}};
FCmp32Libcalls[CmpInst::FCMP_UGT] = {{RTLIB::OLE_F32, CmpInst::ICMP_EQ}};
FCmp32Libcalls[CmpInst::FCMP_ULE] = {{RTLIB::OGT_F32, CmpInst::ICMP_EQ}};
FCmp32Libcalls[CmpInst::FCMP_ULT] = {{RTLIB::OGE_F32, CmpInst::ICMP_EQ}};
FCmp32Libcalls[CmpInst::FCMP_UNE] = {{RTLIB::UNE_F32, CmpInst::ICMP_EQ}};
FCmp32Libcalls[CmpInst::FCMP_UNO] = {
{RTLIB::UO_F32, CmpInst::BAD_ICMP_PREDICATE}};
FCmp32Libcalls[CmpInst::FCMP_ONE] = {
{RTLIB::OGT_F32, CmpInst::BAD_ICMP_PREDICATE},
{RTLIB::OLT_F32, CmpInst::BAD_ICMP_PREDICATE}};
FCmp32Libcalls[CmpInst::FCMP_UEQ] = {
{RTLIB::OEQ_F32, CmpInst::BAD_ICMP_PREDICATE},
{RTLIB::UO_F32, CmpInst::BAD_ICMP_PREDICATE}};
FCmp64Libcalls.resize(CmpInst::LAST_FCMP_PREDICATE + 1);
FCmp64Libcalls[CmpInst::FCMP_OEQ] = {
{RTLIB::OEQ_F64, CmpInst::BAD_ICMP_PREDICATE}};
FCmp64Libcalls[CmpInst::FCMP_OGE] = {
{RTLIB::OGE_F64, CmpInst::BAD_ICMP_PREDICATE}};
FCmp64Libcalls[CmpInst::FCMP_OGT] = {
{RTLIB::OGT_F64, CmpInst::BAD_ICMP_PREDICATE}};
FCmp64Libcalls[CmpInst::FCMP_OLE] = {
{RTLIB::OLE_F64, CmpInst::BAD_ICMP_PREDICATE}};
FCmp64Libcalls[CmpInst::FCMP_OLT] = {
{RTLIB::OLT_F64, CmpInst::BAD_ICMP_PREDICATE}};
FCmp64Libcalls[CmpInst::FCMP_ORD] = {{RTLIB::UO_F64, CmpInst::ICMP_EQ}};
FCmp64Libcalls[CmpInst::FCMP_UGE] = {{RTLIB::OLT_F64, CmpInst::ICMP_EQ}};
FCmp64Libcalls[CmpInst::FCMP_UGT] = {{RTLIB::OLE_F64, CmpInst::ICMP_EQ}};
FCmp64Libcalls[CmpInst::FCMP_ULE] = {{RTLIB::OGT_F64, CmpInst::ICMP_EQ}};
FCmp64Libcalls[CmpInst::FCMP_ULT] = {{RTLIB::OGE_F64, CmpInst::ICMP_EQ}};
FCmp64Libcalls[CmpInst::FCMP_UNE] = {{RTLIB::UNE_F64, CmpInst::ICMP_EQ}};
FCmp64Libcalls[CmpInst::FCMP_UNO] = {
{RTLIB::UO_F64, CmpInst::BAD_ICMP_PREDICATE}};
FCmp64Libcalls[CmpInst::FCMP_ONE] = {
{RTLIB::OGT_F64, CmpInst::BAD_ICMP_PREDICATE},
{RTLIB::OLT_F64, CmpInst::BAD_ICMP_PREDICATE}};
FCmp64Libcalls[CmpInst::FCMP_UEQ] = {
{RTLIB::OEQ_F64, CmpInst::BAD_ICMP_PREDICATE},
{RTLIB::UO_F64, CmpInst::BAD_ICMP_PREDICATE}};
}
void ARMLegalizerInfo::setFCmpLibcallsGNU() {
// FCMP_TRUE and FCMP_FALSE don't need libcalls, they should be
// default-initialized.
FCmp32Libcalls.resize(CmpInst::LAST_FCMP_PREDICATE + 1);
FCmp32Libcalls[CmpInst::FCMP_OEQ] = {{RTLIB::OEQ_F32, CmpInst::ICMP_EQ}};
FCmp32Libcalls[CmpInst::FCMP_OGE] = {{RTLIB::OGE_F32, CmpInst::ICMP_SGE}};
FCmp32Libcalls[CmpInst::FCMP_OGT] = {{RTLIB::OGT_F32, CmpInst::ICMP_SGT}};
FCmp32Libcalls[CmpInst::FCMP_OLE] = {{RTLIB::OLE_F32, CmpInst::ICMP_SLE}};
FCmp32Libcalls[CmpInst::FCMP_OLT] = {{RTLIB::OLT_F32, CmpInst::ICMP_SLT}};
FCmp32Libcalls[CmpInst::FCMP_ORD] = {{RTLIB::UO_F32, CmpInst::ICMP_EQ}};
FCmp32Libcalls[CmpInst::FCMP_UGE] = {{RTLIB::OLT_F32, CmpInst::ICMP_SGE}};
FCmp32Libcalls[CmpInst::FCMP_UGT] = {{RTLIB::OLE_F32, CmpInst::ICMP_SGT}};
FCmp32Libcalls[CmpInst::FCMP_ULE] = {{RTLIB::OGT_F32, CmpInst::ICMP_SLE}};
FCmp32Libcalls[CmpInst::FCMP_ULT] = {{RTLIB::OGE_F32, CmpInst::ICMP_SLT}};
FCmp32Libcalls[CmpInst::FCMP_UNE] = {{RTLIB::UNE_F32, CmpInst::ICMP_NE}};
FCmp32Libcalls[CmpInst::FCMP_UNO] = {{RTLIB::UO_F32, CmpInst::ICMP_NE}};
FCmp32Libcalls[CmpInst::FCMP_ONE] = {{RTLIB::OGT_F32, CmpInst::ICMP_SGT},
{RTLIB::OLT_F32, CmpInst::ICMP_SLT}};
FCmp32Libcalls[CmpInst::FCMP_UEQ] = {{RTLIB::OEQ_F32, CmpInst::ICMP_EQ},
{RTLIB::UO_F32, CmpInst::ICMP_NE}};
FCmp64Libcalls.resize(CmpInst::LAST_FCMP_PREDICATE + 1);
FCmp64Libcalls[CmpInst::FCMP_OEQ] = {{RTLIB::OEQ_F64, CmpInst::ICMP_EQ}};
FCmp64Libcalls[CmpInst::FCMP_OGE] = {{RTLIB::OGE_F64, CmpInst::ICMP_SGE}};
FCmp64Libcalls[CmpInst::FCMP_OGT] = {{RTLIB::OGT_F64, CmpInst::ICMP_SGT}};
FCmp64Libcalls[CmpInst::FCMP_OLE] = {{RTLIB::OLE_F64, CmpInst::ICMP_SLE}};
FCmp64Libcalls[CmpInst::FCMP_OLT] = {{RTLIB::OLT_F64, CmpInst::ICMP_SLT}};
FCmp64Libcalls[CmpInst::FCMP_ORD] = {{RTLIB::UO_F64, CmpInst::ICMP_EQ}};
FCmp64Libcalls[CmpInst::FCMP_UGE] = {{RTLIB::OLT_F64, CmpInst::ICMP_SGE}};
FCmp64Libcalls[CmpInst::FCMP_UGT] = {{RTLIB::OLE_F64, CmpInst::ICMP_SGT}};
FCmp64Libcalls[CmpInst::FCMP_ULE] = {{RTLIB::OGT_F64, CmpInst::ICMP_SLE}};
FCmp64Libcalls[CmpInst::FCMP_ULT] = {{RTLIB::OGE_F64, CmpInst::ICMP_SLT}};
FCmp64Libcalls[CmpInst::FCMP_UNE] = {{RTLIB::UNE_F64, CmpInst::ICMP_NE}};
FCmp64Libcalls[CmpInst::FCMP_UNO] = {{RTLIB::UO_F64, CmpInst::ICMP_NE}};
FCmp64Libcalls[CmpInst::FCMP_ONE] = {{RTLIB::OGT_F64, CmpInst::ICMP_SGT},
{RTLIB::OLT_F64, CmpInst::ICMP_SLT}};
FCmp64Libcalls[CmpInst::FCMP_UEQ] = {{RTLIB::OEQ_F64, CmpInst::ICMP_EQ},
{RTLIB::UO_F64, CmpInst::ICMP_NE}};
}
ARMLegalizerInfo::FCmpLibcallsList
ARMLegalizerInfo::getFCmpLibcalls(CmpInst::Predicate Predicate,
unsigned Size) const {
assert(CmpInst::isFPPredicate(Predicate) && "Unsupported FCmp predicate");
if (Size == 32)
return FCmp32Libcalls[Predicate];
if (Size == 64)
return FCmp64Libcalls[Predicate];
llvm_unreachable("Unsupported size for FCmp predicate");
}
bool ARMLegalizerInfo::legalizeCustom(LegalizerHelper &Helper,
MachineInstr &MI) const {
using namespace TargetOpcode;
MachineIRBuilder &MIRBuilder = Helper.MIRBuilder;
MachineRegisterInfo &MRI = *MIRBuilder.getMRI();
LLVMContext &Ctx = MIRBuilder.getMF().getFunction().getContext();
switch (MI.getOpcode()) {
default:
return false;
case G_SREM:
case G_UREM: {
Register OriginalResult = MI.getOperand(0).getReg();
auto Size = MRI.getType(OriginalResult).getSizeInBits();
if (Size != 32)
return false;
auto Libcall =
MI.getOpcode() == G_SREM ? RTLIB::SDIVREM_I32 : RTLIB::UDIVREM_I32;
// Our divmod libcalls return a struct containing the quotient and the
// remainder. Create a new, unused register for the quotient and use the
// destination of the original instruction for the remainder.
Type *ArgTy = Type::getInt32Ty(Ctx);
StructType *RetTy = StructType::get(Ctx, {ArgTy, ArgTy}, /* Packed */ true);
Register RetRegs[] = {MRI.createGenericVirtualRegister(LLT::scalar(32)),
OriginalResult};
auto Status = createLibcall(MIRBuilder, Libcall, {RetRegs, RetTy, 0},
{{MI.getOperand(1).getReg(), ArgTy, 0},
{MI.getOperand(2).getReg(), ArgTy, 0}});
if (Status != LegalizerHelper::Legalized)
return false;
break;
}
case G_FCMP: {
assert(MRI.getType(MI.getOperand(2).getReg()) ==
MRI.getType(MI.getOperand(3).getReg()) &&
"Mismatched operands for G_FCMP");
auto OpSize = MRI.getType(MI.getOperand(2).getReg()).getSizeInBits();
auto OriginalResult = MI.getOperand(0).getReg();
auto Predicate =
static_cast<CmpInst::Predicate>(MI.getOperand(1).getPredicate());
auto Libcalls = getFCmpLibcalls(Predicate, OpSize);
if (Libcalls.empty()) {
assert((Predicate == CmpInst::FCMP_TRUE ||
Predicate == CmpInst::FCMP_FALSE) &&
"Predicate needs libcalls, but none specified");
MIRBuilder.buildConstant(OriginalResult,
Predicate == CmpInst::FCMP_TRUE ? 1 : 0);
MI.eraseFromParent();
return true;
}
assert((OpSize == 32 || OpSize == 64) && "Unsupported operand size");
auto *ArgTy = OpSize == 32 ? Type::getFloatTy(Ctx) : Type::getDoubleTy(Ctx);
auto *RetTy = Type::getInt32Ty(Ctx);
SmallVector<Register, 2> Results;
for (auto Libcall : Libcalls) {
auto LibcallResult = MRI.createGenericVirtualRegister(LLT::scalar(32));
auto Status = createLibcall(MIRBuilder, Libcall.LibcallID,
{LibcallResult, RetTy, 0},
{{MI.getOperand(2).getReg(), ArgTy, 0},
{MI.getOperand(3).getReg(), ArgTy, 0}});
if (Status != LegalizerHelper::Legalized)
return false;
auto ProcessedResult =
Libcalls.size() == 1
? OriginalResult
: MRI.createGenericVirtualRegister(MRI.getType(OriginalResult));
// We have a result, but we need to transform it into a proper 1-bit 0 or
// 1, taking into account the different peculiarities of the values
// returned by the comparison functions.
CmpInst::Predicate ResultPred = Libcall.Predicate;
if (ResultPred == CmpInst::BAD_ICMP_PREDICATE) {
// We have a nice 0 or 1, and we just need to truncate it back to 1 bit
// to keep the types consistent.
MIRBuilder.buildTrunc(ProcessedResult, LibcallResult);
} else {
// We need to compare against 0.
assert(CmpInst::isIntPredicate(ResultPred) && "Unsupported predicate");
auto Zero = MIRBuilder.buildConstant(LLT::scalar(32), 0);
MIRBuilder.buildICmp(ResultPred, ProcessedResult, LibcallResult, Zero);
}
Results.push_back(ProcessedResult);
}
if (Results.size() != 1) {
assert(Results.size() == 2 && "Unexpected number of results");
MIRBuilder.buildOr(OriginalResult, Results[0], Results[1]);
}
break;
}
case G_FCONSTANT: {
// Convert to integer constants, while preserving the binary representation.
auto AsInteger =
MI.getOperand(1).getFPImm()->getValueAPF().bitcastToAPInt();
MIRBuilder.buildConstant(MI.getOperand(0),
*ConstantInt::get(Ctx, AsInteger));
break;
}
}
MI.eraseFromParent();
return true;
}
|