SIPreAllocateWWMRegs.cpp
6.09 KB
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
//===- SIPreAllocateWWMRegs.cpp - WWM Register Pre-allocation -------------===//
//
// 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
/// Pass to pre-allocated WWM registers
//
//===----------------------------------------------------------------------===//
#include "AMDGPU.h"
#include "AMDGPUSubtarget.h"
#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
#include "SIInstrInfo.h"
#include "SIMachineFunctionInfo.h"
#include "SIRegisterInfo.h"
#include "llvm/ADT/PostOrderIterator.h"
#include "llvm/CodeGen/LiveInterval.h"
#include "llvm/CodeGen/LiveIntervals.h"
#include "llvm/CodeGen/LiveRegMatrix.h"
#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/RegisterClassInfo.h"
#include "llvm/CodeGen/VirtRegMap.h"
#include "llvm/InitializePasses.h"
using namespace llvm;
#define DEBUG_TYPE "si-pre-allocate-wwm-regs"
namespace {
class SIPreAllocateWWMRegs : public MachineFunctionPass {
private:
const SIInstrInfo *TII;
const SIRegisterInfo *TRI;
MachineRegisterInfo *MRI;
LiveIntervals *LIS;
LiveRegMatrix *Matrix;
VirtRegMap *VRM;
RegisterClassInfo RegClassInfo;
std::vector<unsigned> RegsToRewrite;
public:
static char ID;
SIPreAllocateWWMRegs() : MachineFunctionPass(ID) {
initializeSIPreAllocateWWMRegsPass(*PassRegistry::getPassRegistry());
}
bool runOnMachineFunction(MachineFunction &MF) override;
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<LiveIntervals>();
AU.addPreserved<LiveIntervals>();
AU.addRequired<VirtRegMap>();
AU.addRequired<LiveRegMatrix>();
AU.addPreserved<SlotIndexes>();
AU.setPreservesCFG();
MachineFunctionPass::getAnalysisUsage(AU);
}
private:
bool processDef(MachineOperand &MO);
void rewriteRegs(MachineFunction &MF);
};
} // End anonymous namespace.
INITIALIZE_PASS_BEGIN(SIPreAllocateWWMRegs, DEBUG_TYPE,
"SI Pre-allocate WWM Registers", false, false)
INITIALIZE_PASS_DEPENDENCY(LiveIntervals)
INITIALIZE_PASS_DEPENDENCY(VirtRegMap)
INITIALIZE_PASS_DEPENDENCY(LiveRegMatrix)
INITIALIZE_PASS_END(SIPreAllocateWWMRegs, DEBUG_TYPE,
"SI Pre-allocate WWM Registers", false, false)
char SIPreAllocateWWMRegs::ID = 0;
char &llvm::SIPreAllocateWWMRegsID = SIPreAllocateWWMRegs::ID;
FunctionPass *llvm::createSIPreAllocateWWMRegsPass() {
return new SIPreAllocateWWMRegs();
}
bool SIPreAllocateWWMRegs::processDef(MachineOperand &MO) {
if (!MO.isReg())
return false;
Register Reg = MO.getReg();
if (!TRI->isVGPR(*MRI, Reg))
return false;
if (Register::isPhysicalRegister(Reg))
return false;
if (VRM->hasPhys(Reg))
return false;
LiveInterval &LI = LIS->getInterval(Reg);
for (unsigned PhysReg : RegClassInfo.getOrder(MRI->getRegClass(Reg))) {
if (!MRI->isPhysRegUsed(PhysReg) &&
Matrix->checkInterference(LI, PhysReg) == LiveRegMatrix::IK_Free) {
Matrix->assign(LI, PhysReg);
assert(PhysReg != 0);
RegsToRewrite.push_back(Reg);
return true;
}
}
llvm_unreachable("physreg not found for WWM expression");
return false;
}
void SIPreAllocateWWMRegs::rewriteRegs(MachineFunction &MF) {
for (MachineBasicBlock &MBB : MF) {
for (MachineInstr &MI : MBB) {
for (MachineOperand &MO : MI.operands()) {
if (!MO.isReg())
continue;
const Register VirtReg = MO.getReg();
if (Register::isPhysicalRegister(VirtReg))
continue;
if (!VRM->hasPhys(VirtReg))
continue;
Register PhysReg = VRM->getPhys(VirtReg);
const unsigned SubReg = MO.getSubReg();
if (SubReg != 0) {
PhysReg = TRI->getSubReg(PhysReg, SubReg);
MO.setSubReg(0);
}
MO.setReg(PhysReg);
MO.setIsRenamable(false);
}
}
}
SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
for (unsigned Reg : RegsToRewrite) {
LIS->removeInterval(Reg);
const Register PhysReg = VRM->getPhys(Reg);
assert(PhysReg != 0);
MFI->ReserveWWMRegister(PhysReg);
}
RegsToRewrite.clear();
// Update the set of reserved registers to include WWM ones.
MRI->freezeReservedRegs(MF);
}
bool SIPreAllocateWWMRegs::runOnMachineFunction(MachineFunction &MF) {
LLVM_DEBUG(dbgs() << "SIPreAllocateWWMRegs: function " << MF.getName() << "\n");
const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
TII = ST.getInstrInfo();
TRI = &TII->getRegisterInfo();
MRI = &MF.getRegInfo();
LIS = &getAnalysis<LiveIntervals>();
Matrix = &getAnalysis<LiveRegMatrix>();
VRM = &getAnalysis<VirtRegMap>();
RegClassInfo.runOnMachineFunction(MF);
bool RegsAssigned = false;
// We use a reverse post-order traversal of the control-flow graph to
// guarantee that we visit definitions in dominance order. Since WWM
// expressions are guaranteed to never involve phi nodes, and we can only
// escape WWM through the special WWM instruction, this means that this is a
// perfect elimination order, so we can never do any better.
ReversePostOrderTraversal<MachineFunction*> RPOT(&MF);
for (MachineBasicBlock *MBB : RPOT) {
bool InWWM = false;
for (MachineInstr &MI : *MBB) {
if (MI.getOpcode() == AMDGPU::V_SET_INACTIVE_B32 ||
MI.getOpcode() == AMDGPU::V_SET_INACTIVE_B64)
RegsAssigned |= processDef(MI.getOperand(0));
if (MI.getOpcode() == AMDGPU::ENTER_WWM) {
LLVM_DEBUG(dbgs() << "entering WWM region: " << MI << "\n");
InWWM = true;
continue;
}
if (MI.getOpcode() == AMDGPU::EXIT_WWM) {
LLVM_DEBUG(dbgs() << "exiting WWM region: " << MI << "\n");
InWWM = false;
}
if (!InWWM)
continue;
LLVM_DEBUG(dbgs() << "processing " << MI << "\n");
for (MachineOperand &DefOpnd : MI.defs()) {
RegsAssigned |= processDef(DefOpnd);
}
}
}
if (!RegsAssigned)
return false;
rewriteRegs(MF);
return true;
}