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
|
//===-- AMDGPUTargetMachine.cpp - TargetMachine for hw codegen targets-----===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// The AMDGPU target machine contains all of the hardware specific information
// needed to emit code for R600 and SI GPUs.
//
//===----------------------------------------------------------------------===//
#include "AMDGPUTargetMachine.h"
#include "AMDGPU.h"
#include "R600ISelLowering.h"
#include "R600InstrInfo.h"
#include "SIISelLowering.h"
#include "SIInstrInfo.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/Analysis/Verifier.h"
#include "llvm/CodeGen/MachineFunctionAnalysis.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/PassManager.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Support/raw_os_ostream.h"
#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/Scalar.h"
#include <llvm/CodeGen/Passes.h>
using namespace llvm;
extern "C" void LLVMInitializeAMDGPUTarget() {
// Register the target
RegisterTargetMachine<AMDGPUTargetMachine> X(TheAMDGPUTarget);
}
AMDGPUTargetMachine::AMDGPUTargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
TargetOptions Options,
Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OptLevel
)
:
LLVMTargetMachine(T, TT, CPU, FS, Options, RM, CM, OptLevel),
Subtarget(TT, CPU, FS),
DataLayout(Subtarget.getDataLayout()),
FrameLowering(TargetFrameLowering::StackGrowsUp,
Subtarget.device()->getStackAlignment(), 0),
IntrinsicInfo(this),
InstrItins(&Subtarget.getInstrItineraryData()),
mDump(false)
{
// TLInfo uses InstrInfo so it must be initialized after.
if (Subtarget.device()->getGeneration() <= AMDGPUDeviceInfo::HD6XXX) {
InstrInfo = new R600InstrInfo(*this);
TLInfo = new R600TargetLowering(*this);
} else {
InstrInfo = new SIInstrInfo(*this);
TLInfo = new SITargetLowering(*this);
}
}
AMDGPUTargetMachine::~AMDGPUTargetMachine()
{
}
bool AMDGPUTargetMachine::addPassesToEmitFile(PassManagerBase &PM,
formatted_raw_ostream &Out,
CodeGenFileType FileType,
bool DisableVerify) {
const AMDGPUSubtarget &STM = getSubtarget<AMDGPUSubtarget>();
std::string gpu = STM.getDeviceName();
if (gpu == "SI") {
return LLVMTargetMachine::addPassesToEmitFile(PM, Out, FileType,
DisableVerify);
} else if (Subtarget.device()->getGeneration() <= AMDGPUDeviceInfo::HD6XXX) {
// XXX: Hack here addPassesToEmitFile will fail, but this is Ok since we are
// only using it to access addPassesToGenerateCode()
bool fail = LLVMTargetMachine::addPassesToEmitFile(PM, Out, FileType,
DisableVerify);
assert(fail);
PM.add(createR600CodeEmitterPass(Out));
} else {
abort();
return true;
}
PM.add(createGCInfoDeleter());
return false;
}
namespace {
class AMDGPUPassConfig : public TargetPassConfig {
public:
AMDGPUPassConfig(AMDGPUTargetMachine *TM, PassManagerBase &PM)
: TargetPassConfig(TM, PM) {}
AMDGPUTargetMachine &getAMDGPUTargetMachine() const {
return getTM<AMDGPUTargetMachine>();
}
virtual bool addPreISel();
virtual bool addInstSelector();
virtual bool addPreRegAlloc();
virtual bool addPostRegAlloc();
virtual bool addPreSched2();
virtual bool addPreEmitPass();
};
} // End of anonymous namespace
TargetPassConfig *AMDGPUTargetMachine::createPassConfig(PassManagerBase &PM) {
return new AMDGPUPassConfig(this, PM);
}
bool
AMDGPUPassConfig::addPreISel()
{
const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>();
if (ST.device()->getGeneration() <= AMDGPUDeviceInfo::HD6XXX) {
PM->add(createR600KernelParametersPass(
getAMDGPUTargetMachine().getTargetData()));
}
return false;
}
bool AMDGPUPassConfig::addInstSelector() {
PM->add(createAMDGPUPeepholeOpt(*TM));
PM->add(createAMDGPUISelDag(getAMDGPUTargetMachine()));
return false;
}
bool AMDGPUPassConfig::addPreRegAlloc() {
const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>();
if (ST.device()->getGeneration() > AMDGPUDeviceInfo::HD6XXX) {
PM->add(createSIAssignInterpRegsPass(*TM));
}
PM->add(createAMDGPUConvertToISAPass(*TM));
return false;
}
bool AMDGPUPassConfig::addPostRegAlloc() {
return false;
}
bool AMDGPUPassConfig::addPreSched2() {
addPass(IfConverterID);
return false;
}
bool AMDGPUPassConfig::addPreEmitPass() {
PM->add(createAMDGPUCFGPreparationPass(*TM));
PM->add(createAMDGPUCFGStructurizerPass(*TM));
const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>();
if (ST.device()->getGeneration() <= AMDGPUDeviceInfo::HD6XXX) {
PM->add(createR600ExpandSpecialInstrsPass(*TM));
addPass(FinalizeMachineBundlesID);
}
return false;
}
|
