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
|
//===- PPCMacroFusion.cpp - PowerPC Macro Fusion --------------------------===//
//
// 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 contains the PowerPC implementation of the DAG scheduling
/// mutation to pair instructions back to back.
//
//===----------------------------------------------------------------------===//
#include "PPC.h"
#include "PPCSubtarget.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/CodeGen/MacroFusion.h"
#include "llvm/CodeGen/ScheduleDAGMutation.h"
#include <optional>
using namespace llvm;
namespace {
class FusionFeature {
public:
typedef SmallDenseSet<unsigned> FusionOpSet;
enum FusionKind {
#define FUSION_KIND(KIND) FK_##KIND
#define FUSION_FEATURE(KIND, HAS_FEATURE, DEP_OP_IDX, OPSET1, OPSET2) \
FUSION_KIND(KIND),
#include "PPCMacroFusion.def"
FUSION_KIND(END)
};
private:
// Each fusion feature is assigned with one fusion kind. All the
// instructions with the same fusion kind have the same fusion characteristic.
FusionKind Kd;
// True if this feature is enabled.
bool Supported;
// li rx, si
// load rt, ra, rx
// The dependent operand index in the second op(load). And the negative means
// it could be any one.
int DepOpIdx;
// The first fusion op set.
FusionOpSet OpSet1;
// The second fusion op set.
FusionOpSet OpSet2;
public:
FusionFeature(FusionKind Kind, bool HasFeature, int Index,
const FusionOpSet &First, const FusionOpSet &Second) :
Kd(Kind), Supported(HasFeature), DepOpIdx(Index), OpSet1(First),
OpSet2(Second) {}
bool hasOp1(unsigned Opc) const { return OpSet1.contains(Opc); }
bool hasOp2(unsigned Opc) const { return OpSet2.contains(Opc); }
bool isSupported() const { return Supported; }
std::optional<unsigned> depOpIdx() const {
if (DepOpIdx < 0)
return std::nullopt;
return DepOpIdx;
}
FusionKind getKind() const { return Kd; }
};
static bool matchingRegOps(const MachineInstr &FirstMI,
int FirstMIOpIndex,
const MachineInstr &SecondMI,
int SecondMIOpIndex) {
const MachineOperand &Op1 = FirstMI.getOperand(FirstMIOpIndex);
const MachineOperand &Op2 = SecondMI.getOperand(SecondMIOpIndex);
if (!Op1.isReg() || !Op2.isReg())
return false;
return Op1.getReg() == Op2.getReg();
}
static bool matchingImmOps(const MachineInstr &MI,
int MIOpIndex,
int64_t Expect,
unsigned ExtendFrom = 64) {
const MachineOperand &Op = MI.getOperand(MIOpIndex);
if (!Op.isImm())
return false;
int64_t Imm = Op.getImm();
if (ExtendFrom < 64)
Imm = SignExtend64(Imm, ExtendFrom);
return Imm == Expect;
}
// Return true if the FirstMI meets the constraints of SecondMI according to
// fusion specification.
static bool checkOpConstraints(FusionFeature::FusionKind Kd,
const MachineInstr &FirstMI,
const MachineInstr &SecondMI) {
switch (Kd) {
// The hardware didn't require any specific check for the fused instructions'
// operands. Therefore, return true to indicate that, it is fusable.
default: return true;
// [addi rt,ra,si - lxvd2x xt,ra,rb] etc.
case FusionFeature::FK_AddiLoad: {
// lxvd2x(ra) cannot be zero
const MachineOperand &RA = SecondMI.getOperand(1);
if (!RA.isReg())
return true;
return RA.getReg().isVirtual() ||
(RA.getReg() != PPC::ZERO && RA.getReg() != PPC::ZERO8);
}
// [addis rt,ra,si - ld rt,ds(ra)] etc.
case FusionFeature::FK_AddisLoad: {
const MachineOperand &RT = SecondMI.getOperand(0);
if (!RT.isReg())
return true;
// Only check it for non-virtual register.
if (!RT.getReg().isVirtual())
// addis(rt) = ld(ra) = ld(rt)
// ld(rt) cannot be zero
if (!matchingRegOps(SecondMI, 0, SecondMI, 2) ||
(RT.getReg() == PPC::ZERO || RT.getReg() == PPC::ZERO8))
return false;
// addis(si) first 12 bits must be all 1s or all 0s
const MachineOperand &SI = FirstMI.getOperand(2);
if (!SI.isImm())
return true;
int64_t Imm = SI.getImm();
if (((Imm & 0xFFF0) != 0) && ((Imm & 0xFFF0) != 0xFFF0))
return false;
// If si = 1111111111110000 and the msb of the d/ds field of the load equals
// 1, then fusion does not occur.
if ((Imm & 0xFFF0) == 0xFFF0) {
const MachineOperand &D = SecondMI.getOperand(1);
if (!D.isImm())
return true;
// 14 bit for DS field, while 16 bit for D field.
int MSB = 15;
if (SecondMI.getOpcode() == PPC::LD)
MSB = 13;
return (D.getImm() & (1ULL << MSB)) == 0;
}
return true;
}
case FusionFeature::FK_SldiAdd:
return (matchingImmOps(FirstMI, 2, 3) && matchingImmOps(FirstMI, 3, 60)) ||
(matchingImmOps(FirstMI, 2, 6) && matchingImmOps(FirstMI, 3, 57));
// rldicl rx, ra, 1, 0 - xor
case FusionFeature::FK_RotateLeftXor:
return matchingImmOps(FirstMI, 2, 1) && matchingImmOps(FirstMI, 3, 0);
// rldicr rx, ra, 1, 63 - xor
case FusionFeature::FK_RotateRightXor:
return matchingImmOps(FirstMI, 2, 1) && matchingImmOps(FirstMI, 3, 63);
// We actually use CMPW* and CMPD*, 'l' doesn't exist as an operand in instr.
// { lbz,lbzx,lhz,lhzx,lwz,lwzx } - cmpi 0,1,rx,{ 0,1,-1 }
// { lbz,lbzx,lhz,lhzx,lwz,lwzx } - cmpli 0,L,rx,{ 0,1 }
case FusionFeature::FK_LoadCmp1:
// { ld,ldx } - cmpi 0,1,rx,{ 0,1,-1 }
// { ld,ldx } - cmpli 0,1,rx,{ 0,1 }
case FusionFeature::FK_LoadCmp2: {
const MachineOperand &BT = SecondMI.getOperand(0);
if (!BT.isReg() || (!BT.getReg().isVirtual() && BT.getReg() != PPC::CR0))
return false;
if (SecondMI.getOpcode() == PPC::CMPDI &&
matchingImmOps(SecondMI, 2, -1, 16))
return true;
return matchingImmOps(SecondMI, 2, 0) || matchingImmOps(SecondMI, 2, 1);
}
// { lha,lhax,lwa,lwax } - cmpi 0,L,rx,{ 0,1,-1 }
case FusionFeature::FK_LoadCmp3: {
const MachineOperand &BT = SecondMI.getOperand(0);
if (!BT.isReg() || (!BT.getReg().isVirtual() && BT.getReg() != PPC::CR0))
return false;
return matchingImmOps(SecondMI, 2, 0) || matchingImmOps(SecondMI, 2, 1) ||
matchingImmOps(SecondMI, 2, -1, 16);
}
// mtctr - { bcctr,bcctrl }
case FusionFeature::FK_ZeroMoveCTR:
// ( mtctr rx ) is alias of ( mtspr 9, rx )
return (FirstMI.getOpcode() != PPC::MTSPR &&
FirstMI.getOpcode() != PPC::MTSPR8) ||
matchingImmOps(FirstMI, 0, 9);
// mtlr - { bclr,bclrl }
case FusionFeature::FK_ZeroMoveLR:
// ( mtlr rx ) is alias of ( mtspr 8, rx )
return (FirstMI.getOpcode() != PPC::MTSPR &&
FirstMI.getOpcode() != PPC::MTSPR8) ||
matchingImmOps(FirstMI, 0, 8);
// addis rx,ra,si - addi rt,rx,SI, SI >= 0
case FusionFeature::FK_AddisAddi: {
const MachineOperand &RA = FirstMI.getOperand(1);
const MachineOperand &SI = SecondMI.getOperand(2);
if (!SI.isImm() || !RA.isReg())
return false;
if (RA.getReg() == PPC::ZERO || RA.getReg() == PPC::ZERO8)
return false;
return SignExtend64(SI.getImm(), 16) >= 0;
}
// addi rx,ra,si - addis rt,rx,SI, ra > 0, SI >= 2
case FusionFeature::FK_AddiAddis: {
const MachineOperand &RA = FirstMI.getOperand(1);
const MachineOperand &SI = FirstMI.getOperand(2);
if (!SI.isImm() || !RA.isReg())
return false;
if (RA.getReg() == PPC::ZERO || RA.getReg() == PPC::ZERO8)
return false;
int64_t ExtendedSI = SignExtend64(SI.getImm(), 16);
return ExtendedSI >= 2;
}
}
llvm_unreachable("All the cases should have been handled");
return true;
}
/// Check if the instr pair, FirstMI and SecondMI, should be fused together.
/// Given SecondMI, when FirstMI is unspecified, then check if SecondMI may be
/// part of a fused pair at all.
static bool shouldScheduleAdjacent(const TargetInstrInfo &TII,
const TargetSubtargetInfo &TSI,
const MachineInstr *FirstMI,
const MachineInstr &SecondMI) {
// We use the PPC namespace to avoid the need to prefix opcodes with PPC:: in
// the def file.
using namespace PPC;
const PPCSubtarget &ST = static_cast<const PPCSubtarget&>(TSI);
static const FusionFeature FusionFeatures[] = {
#define FUSION_FEATURE(KIND, HAS_FEATURE, DEP_OP_IDX, OPSET1, OPSET2) { \
FusionFeature::FUSION_KIND(KIND), ST.HAS_FEATURE(), DEP_OP_IDX, { OPSET1 },\
{ OPSET2 } },
#include "PPCMacroFusion.def"
};
#undef FUSION_KIND
for (auto &Feature : FusionFeatures) {
// Skip if the feature is not supported.
if (!Feature.isSupported())
continue;
// Only when the SecondMI is fusable, we are starting to look for the
// fusable FirstMI.
if (Feature.hasOp2(SecondMI.getOpcode())) {
// If FirstMI == nullptr, that means, we're only checking whether SecondMI
// can be fused at all.
if (!FirstMI)
return true;
// Checking if the FirstMI is fusable with the SecondMI.
if (!Feature.hasOp1(FirstMI->getOpcode()))
continue;
auto DepOpIdx = Feature.depOpIdx();
if (DepOpIdx) {
// Checking if the result of the FirstMI is the desired operand of the
// SecondMI if the DepOpIdx is set. Otherwise, ignore it.
if (!matchingRegOps(*FirstMI, 0, SecondMI, *DepOpIdx))
return false;
}
// Checking more on the instruction operands.
if (checkOpConstraints(Feature.getKind(), *FirstMI, SecondMI))
return true;
}
}
return false;
}
} // end anonymous namespace
namespace llvm {
std::unique_ptr<ScheduleDAGMutation> createPowerPCMacroFusionDAGMutation () {
return createMacroFusionDAGMutation(shouldScheduleAdjacent);
}
} // end namespace llvm
|