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
|
#include <torch/csrc/jit/mobile/interpreter.h>
#include <ATen/core/function.h>
#include <ATen/core/jit_type.h>
#include <ATen/core/operator_name.h>
#include <torch/csrc/jit/mobile/function.h>
#include <torch/csrc/jit/runtime/vararg_functions.h>
#include <ATen/record_function.h>
#include <torch/csrc/jit/mobile/observer.h>
namespace torch {
namespace jit {
char const* toString(OpCode op);
std::ostream& operator<<(std::ostream& out, Instruction inst);
namespace mobile {
InterpreterState::InterpreterState(std::shared_ptr<Code> code)
: code_(std::move(code)) {
registers_.resize(code_->register_size_);
}
using namespace at;
bool InterpreterState::run(Stack& stack) {
size_t pc = 0;
while (true) {
Instruction inst = code_->instructions_[pc];
// std::cout << "RUNNING " << pc << " " << code_->instructions_[pc];
// if (inst.op == OP) {
// std::cout << ", " << code_->op_names_[inst.X].name;
// if (!code_->op_names_[inst.X].overload_name.empty()) {
// std::cout << "." << code_->op_names_[inst.X].overload_name;
// }
// }
// std::cout << std::endl;
switch (inst.op) {
case OP: {
if (at::hasGlobalCallbacks()) {
if (auto debug_info = c10::ThreadLocalDebugInfo::get(
c10::DebugInfoKind::MOBILE_RUNTIME_INFO)) {
if (auto* mobile_debug_info =
dynamic_cast<MobileDebugInfo*>(debug_info.get())) {
mobile_debug_info->setOpIdx(pc);
}
}
}
// TODO(iliacher): remove the workaround after RecordFunction is in
// Dispatcher
bool prev_value = isRecordFunctionEnabled();
if (!prev_value) {
// enable only for the RecordFunction
enableRecordFunction(true);
}
RECORD_FUNCTION(code_->op_names_[inst.X].name, stack);
if (!prev_value) {
enableRecordFunction(false);
}
code_->operators_[inst.X](stack);
++pc;
} break;
case OPN: {
stack.push_back(inst.N);
code_->operators_[inst.X](stack);
++pc;
} break;
case INTERFACE_CALL: {
torch::jit::Function& method =
peek(stack, 0, inst.N)
.toObject()
->type()
->getMethod(code_->constants_[inst.X].toStringRef());
method.run(stack);
++pc;
} break;
case LOAD:
stack.emplace_back(reg(inst.X));
++pc;
break;
case MOVE:
stack.emplace_back(std::move(reg(inst.X)));
++pc;
break;
case STORE:
reg(inst.X) = pop(stack);
++pc;
break;
case STOREN:
for (size_t i = inst.N; i > 0; --i) {
reg(inst.X + i - 1) = pop(stack);
}
++pc;
break;
case DROP:
pop(stack);
++pc;
break;
case DROPR:
reg(inst.X) = IValue();
++pc;
break;
case LOADC:
stack.emplace_back(code_->constants_[inst.X]);
++pc;
break;
case GET_ATTR: {
auto userObj = pop(stack).toObject();
auto value = userObj->getSlot(inst.X);
push(stack, std::move(value));
++pc;
} break;
case SET_ATTR: {
auto v = pop(stack);
auto userObj = pop(stack).toObject();
// Mobile only: since the number of slots is not known, resize the
// numAttributes before setSlot.
while (userObj->type()->numAttributes() <= inst.X) {
std::stringstream ss;
ss << userObj->type()->numAttributes();
userObj->type()->addAttribute(ss.str(), c10::NoneType::create());
}
userObj->setSlot(inst.X, std::move(v));
++pc;
} break;
case JF:
pc += (pop(stack).toBool()) ? 1 : inst.X;
break;
case JMP:
pc += inst.X;
break;
case LOOP: {
// stack: iteration_count, max_iter, cond, loop_carried_deps...
auto frame = stack.end() - (inst.N + 1);
int64_t trip_count = frame[0].toInt();
int64_t max_trip_count = frame[1].toInt();
bool cond = frame[2].toBool();
if (trip_count < max_trip_count && cond) {
frame[2] = trip_count;
frame[0] = trip_count + 1;
++pc;
} else {
size_t n_loop_carried = inst.N - 2;
for (size_t i = 0; i < n_loop_carried; ++i) {
frame[i] = std::move(frame[i + 3]);
}
drop(stack, 3); // iteration_count, max_iter, cond
pc += inst.X;
}
} break;
case RET:
return false;
case LIST_CONSTRUCT: {
auto type = code_->types_[inst.X]->expect<at::ListType>();
listConstruct(stack, type, inst.N);
++pc;
} break;
case LIST_UNPACK: {
listUnpack(stack, inst.X);
++pc;
} break;
case TUPLE_CONSTRUCT: {
tupleConstruct(stack, inst.X);
++pc;
} break;
case TUPLE_SLICE: {
tupleSlice(stack, inst.X, inst.X + inst.N);
++pc;
} break;
case DICT_CONSTRUCT: {
auto type = code_->types_[inst.X]->expect<at::DictType>();
dictConstruct(stack, type, inst.N);
++pc;
} break;
case NAMED_TUPLE_CONSTRUCT: {
auto type = code_->types_[inst.X]->expect<at::TupleType>();
namedTupleConstruct(stack, type, inst.N);
++pc;
} break;
case WARN: {
drop(stack, 1);
TORCH_WARN(pop(stack).toStringRef());
++pc;
} break;
default:
AT_ERROR(toString(inst.op), " is invalid.");
}
// for (auto val : stack) {
// if (val.isTensor()) {
// std::cout << val.toTensor().sizes() << std::endl;
// } else {
// std::cout << val << std::endl;
// }
// }
}
return false;
}
IValue& InterpreterState::reg(size_t reg) {
return *(registers_.end() - reg);
}
} // namespace mobile
} // namespace jit
} // namespace torch
|
