forked from llvm/llvm-project
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathAsyncRuntime.cpp
423 lines (351 loc) · 14.5 KB
/
AsyncRuntime.cpp
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
//===- AsyncRuntime.cpp - Async runtime reference implementation ----------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file implements basic Async runtime API for supporting Async dialect
// to LLVM dialect lowering.
//
//===----------------------------------------------------------------------===//
#include "mlir/ExecutionEngine/AsyncRuntime.h"
#ifdef MLIR_ASYNCRUNTIME_DEFINE_FUNCTIONS
#include <atomic>
#include <cassert>
#include <condition_variable>
#include <functional>
#include <iostream>
#include <mutex>
#include <thread>
#include <vector>
#include "llvm/ADT/StringMap.h"
#include "llvm/Support/ThreadPool.h"
using namespace mlir::runtime;
//===----------------------------------------------------------------------===//
// Async runtime API.
//===----------------------------------------------------------------------===//
namespace mlir {
namespace runtime {
namespace {
// Forward declare class defined below.
class RefCounted;
// -------------------------------------------------------------------------- //
// AsyncRuntime orchestrates all async operations and Async runtime API is built
// on top of the default runtime instance.
// -------------------------------------------------------------------------- //
class AsyncRuntime {
public:
AsyncRuntime() : numRefCountedObjects(0) {}
~AsyncRuntime() {
threadPool.wait(); // wait for the completion of all async tasks
assert(getNumRefCountedObjects() == 0 &&
"all ref counted objects must be destroyed");
}
int32_t getNumRefCountedObjects() {
return numRefCountedObjects.load(std::memory_order_relaxed);
}
llvm::ThreadPool &getThreadPool() { return threadPool; }
private:
friend class RefCounted;
// Count the total number of reference counted objects in this instance
// of an AsyncRuntime. For debugging purposes only.
void addNumRefCountedObjects() {
numRefCountedObjects.fetch_add(1, std::memory_order_relaxed);
}
void dropNumRefCountedObjects() {
numRefCountedObjects.fetch_sub(1, std::memory_order_relaxed);
}
std::atomic<int32_t> numRefCountedObjects;
llvm::ThreadPool threadPool;
};
// -------------------------------------------------------------------------- //
// A base class for all reference counted objects created by the async runtime.
// -------------------------------------------------------------------------- //
class RefCounted {
public:
RefCounted(AsyncRuntime *runtime, int32_t refCount = 1)
: runtime(runtime), refCount(refCount) {
runtime->addNumRefCountedObjects();
}
virtual ~RefCounted() {
assert(refCount.load() == 0 && "reference count must be zero");
runtime->dropNumRefCountedObjects();
}
RefCounted(const RefCounted &) = delete;
RefCounted &operator=(const RefCounted &) = delete;
void addRef(int32_t count = 1) { refCount.fetch_add(count); }
void dropRef(int32_t count = 1) {
int32_t previous = refCount.fetch_sub(count);
assert(previous >= count && "reference count should not go below zero");
if (previous == count)
destroy();
}
protected:
virtual void destroy() { delete this; }
private:
AsyncRuntime *runtime;
std::atomic<int32_t> refCount;
};
} // namespace
// Returns the default per-process instance of an async runtime.
static std::unique_ptr<AsyncRuntime> &getDefaultAsyncRuntimeInstance() {
static auto runtime = std::make_unique<AsyncRuntime>();
return runtime;
}
static void resetDefaultAsyncRuntime() {
return getDefaultAsyncRuntimeInstance().reset();
}
static AsyncRuntime *getDefaultAsyncRuntime() {
return getDefaultAsyncRuntimeInstance().get();
}
// Async token provides a mechanism to signal asynchronous operation completion.
struct AsyncToken : public RefCounted {
// AsyncToken created with a reference count of 2 because it will be returned
// to the `async.execute` caller and also will be later on emplaced by the
// asynchronously executed task. If the caller immediately will drop its
// reference we must ensure that the token will be alive until the
// asynchronous operation is completed.
AsyncToken(AsyncRuntime *runtime)
: RefCounted(runtime, /*count=*/2), ready(false) {}
std::atomic<bool> ready;
// Pending awaiters are guarded by a mutex.
std::mutex mu;
std::condition_variable cv;
std::vector<std::function<void()>> awaiters;
};
// Async value provides a mechanism to access the result of asynchronous
// operations. It owns the storage that is used to store/load the value of the
// underlying type, and a flag to signal if the value is ready or not.
struct AsyncValue : public RefCounted {
// AsyncValue similar to an AsyncToken created with a reference count of 2.
AsyncValue(AsyncRuntime *runtime, int32_t size)
: RefCounted(runtime, /*count=*/2), ready(false), storage(size) {}
std::atomic<bool> ready;
// Use vector of bytes to store async value payload.
std::vector<int8_t> storage;
// Pending awaiters are guarded by a mutex.
std::mutex mu;
std::condition_variable cv;
std::vector<std::function<void()>> awaiters;
};
// Async group provides a mechanism to group together multiple async tokens or
// values to await on all of them together (wait for the completion of all
// tokens or values added to the group).
struct AsyncGroup : public RefCounted {
AsyncGroup(AsyncRuntime *runtime)
: RefCounted(runtime), pendingTokens(0), rank(0) {}
std::atomic<int> pendingTokens;
std::atomic<int> rank;
// Pending awaiters are guarded by a mutex.
std::mutex mu;
std::condition_variable cv;
std::vector<std::function<void()>> awaiters;
};
// Adds references to reference counted runtime object.
extern "C" void mlirAsyncRuntimeAddRef(RefCountedObjPtr ptr, int32_t count) {
RefCounted *refCounted = static_cast<RefCounted *>(ptr);
refCounted->addRef(count);
}
// Drops references from reference counted runtime object.
extern "C" void mlirAsyncRuntimeDropRef(RefCountedObjPtr ptr, int32_t count) {
RefCounted *refCounted = static_cast<RefCounted *>(ptr);
refCounted->dropRef(count);
}
// Creates a new `async.token` in not-ready state.
extern "C" AsyncToken *mlirAsyncRuntimeCreateToken() {
AsyncToken *token = new AsyncToken(getDefaultAsyncRuntime());
return token;
}
// Creates a new `async.value` in not-ready state.
extern "C" AsyncValue *mlirAsyncRuntimeCreateValue(int32_t size) {
AsyncValue *value = new AsyncValue(getDefaultAsyncRuntime(), size);
return value;
}
// Create a new `async.group` in empty state.
extern "C" AsyncGroup *mlirAsyncRuntimeCreateGroup() {
AsyncGroup *group = new AsyncGroup(getDefaultAsyncRuntime());
return group;
}
extern "C" int64_t mlirAsyncRuntimeAddTokenToGroup(AsyncToken *token,
AsyncGroup *group) {
std::unique_lock<std::mutex> lockToken(token->mu);
std::unique_lock<std::mutex> lockGroup(group->mu);
// Get the rank of the token inside the group before we drop the reference.
int rank = group->rank.fetch_add(1);
group->pendingTokens.fetch_add(1);
auto onTokenReady = [group]() {
// Run all group awaiters if it was the last token in the group.
if (group->pendingTokens.fetch_sub(1) == 1) {
group->cv.notify_all();
for (auto &awaiter : group->awaiters)
awaiter();
}
};
if (token->ready) {
// Update group pending tokens immediately and maybe run awaiters.
onTokenReady();
} else {
// Update group pending tokens when token will become ready. Because this
// will happen asynchronously we must ensure that `group` is alive until
// then, and re-ackquire the lock.
group->addRef();
token->awaiters.push_back([group, onTokenReady]() {
// Make sure that `dropRef` does not destroy the mutex owned by the lock.
{
std::unique_lock<std::mutex> lockGroup(group->mu);
onTokenReady();
}
group->dropRef();
});
}
return rank;
}
// Switches `async.token` to ready state and runs all awaiters.
extern "C" void mlirAsyncRuntimeEmplaceToken(AsyncToken *token) {
// Make sure that `dropRef` does not destroy the mutex owned by the lock.
{
std::unique_lock<std::mutex> lock(token->mu);
token->ready = true;
token->cv.notify_all();
for (auto &awaiter : token->awaiters)
awaiter();
}
// Async tokens created with a ref count `2` to keep token alive until the
// async task completes. Drop this reference explicitly when token emplaced.
token->dropRef();
}
// Switches `async.value` to ready state and runs all awaiters.
extern "C" void mlirAsyncRuntimeEmplaceValue(AsyncValue *value) {
// Make sure that `dropRef` does not destroy the mutex owned by the lock.
{
std::unique_lock<std::mutex> lock(value->mu);
value->ready = true;
value->cv.notify_all();
for (auto &awaiter : value->awaiters)
awaiter();
}
// Async values created with a ref count `2` to keep value alive until the
// async task completes. Drop this reference explicitly when value emplaced.
value->dropRef();
}
extern "C" void mlirAsyncRuntimeAwaitToken(AsyncToken *token) {
std::unique_lock<std::mutex> lock(token->mu);
if (!token->ready)
token->cv.wait(lock, [token] { return token->ready.load(); });
}
extern "C" void mlirAsyncRuntimeAwaitValue(AsyncValue *value) {
std::unique_lock<std::mutex> lock(value->mu);
if (!value->ready)
value->cv.wait(lock, [value] { return value->ready.load(); });
}
extern "C" void mlirAsyncRuntimeAwaitAllInGroup(AsyncGroup *group) {
std::unique_lock<std::mutex> lock(group->mu);
if (group->pendingTokens != 0)
group->cv.wait(lock, [group] { return group->pendingTokens == 0; });
}
// Returns a pointer to the storage owned by the async value.
extern "C" ValueStorage mlirAsyncRuntimeGetValueStorage(AsyncValue *value) {
return value->storage.data();
}
extern "C" void mlirAsyncRuntimeExecute(CoroHandle handle, CoroResume resume) {
auto *runtime = getDefaultAsyncRuntime();
runtime->getThreadPool().async([handle, resume]() { (*resume)(handle); });
}
extern "C" void mlirAsyncRuntimeAwaitTokenAndExecute(AsyncToken *token,
CoroHandle handle,
CoroResume resume) {
auto execute = [handle, resume]() { (*resume)(handle); };
std::unique_lock<std::mutex> lock(token->mu);
if (token->ready) {
lock.unlock();
execute();
} else {
token->awaiters.push_back([execute]() { execute(); });
}
}
extern "C" void mlirAsyncRuntimeAwaitValueAndExecute(AsyncValue *value,
CoroHandle handle,
CoroResume resume) {
auto execute = [handle, resume]() { (*resume)(handle); };
std::unique_lock<std::mutex> lock(value->mu);
if (value->ready) {
lock.unlock();
execute();
} else {
value->awaiters.push_back([execute]() { execute(); });
}
}
extern "C" void mlirAsyncRuntimeAwaitAllInGroupAndExecute(AsyncGroup *group,
CoroHandle handle,
CoroResume resume) {
auto execute = [handle, resume]() { (*resume)(handle); };
std::unique_lock<std::mutex> lock(group->mu);
if (group->pendingTokens == 0) {
lock.unlock();
execute();
} else {
group->awaiters.push_back([execute]() { execute(); });
}
}
//===----------------------------------------------------------------------===//
// Small async runtime support library for testing.
//===----------------------------------------------------------------------===//
extern "C" void mlirAsyncRuntimePrintCurrentThreadId() {
static thread_local std::thread::id thisId = std::this_thread::get_id();
std::cout << "Current thread id: " << thisId << std::endl;
}
//===----------------------------------------------------------------------===//
// MLIR Runner (JitRunner) dynamic library integration.
//===----------------------------------------------------------------------===//
// Export symbols for the MLIR runner integration. All other symbols are hidden.
#ifdef _WIN32
#define API __declspec(dllexport)
#else
#define API __attribute__((visibility("default")))
#endif
extern "C" API void __mlir_runner_init(llvm::StringMap<void *> &exportSymbols) {
auto exportSymbol = [&](llvm::StringRef name, auto ptr) {
assert(exportSymbols.count(name) == 0 && "symbol already exists");
exportSymbols[name] = reinterpret_cast<void *>(ptr);
};
exportSymbol("mlirAsyncRuntimeAddRef",
&mlir::runtime::mlirAsyncRuntimeAddRef);
exportSymbol("mlirAsyncRuntimeDropRef",
&mlir::runtime::mlirAsyncRuntimeDropRef);
exportSymbol("mlirAsyncRuntimeExecute",
&mlir::runtime::mlirAsyncRuntimeExecute);
exportSymbol("mlirAsyncRuntimeGetValueStorage",
&mlir::runtime::mlirAsyncRuntimeGetValueStorage);
exportSymbol("mlirAsyncRuntimeCreateToken",
&mlir::runtime::mlirAsyncRuntimeCreateToken);
exportSymbol("mlirAsyncRuntimeCreateValue",
&mlir::runtime::mlirAsyncRuntimeCreateValue);
exportSymbol("mlirAsyncRuntimeEmplaceToken",
&mlir::runtime::mlirAsyncRuntimeEmplaceToken);
exportSymbol("mlirAsyncRuntimeEmplaceValue",
&mlir::runtime::mlirAsyncRuntimeEmplaceValue);
exportSymbol("mlirAsyncRuntimeAwaitToken",
&mlir::runtime::mlirAsyncRuntimeAwaitToken);
exportSymbol("mlirAsyncRuntimeAwaitValue",
&mlir::runtime::mlirAsyncRuntimeAwaitValue);
exportSymbol("mlirAsyncRuntimeAwaitTokenAndExecute",
&mlir::runtime::mlirAsyncRuntimeAwaitTokenAndExecute);
exportSymbol("mlirAsyncRuntimeAwaitValueAndExecute",
&mlir::runtime::mlirAsyncRuntimeAwaitValueAndExecute);
exportSymbol("mlirAsyncRuntimeCreateGroup",
&mlir::runtime::mlirAsyncRuntimeCreateGroup);
exportSymbol("mlirAsyncRuntimeAddTokenToGroup",
&mlir::runtime::mlirAsyncRuntimeAddTokenToGroup);
exportSymbol("mlirAsyncRuntimeAwaitAllInGroup",
&mlir::runtime::mlirAsyncRuntimeAwaitAllInGroup);
exportSymbol("mlirAsyncRuntimeAwaitAllInGroupAndExecute",
&mlir::runtime::mlirAsyncRuntimeAwaitAllInGroupAndExecute);
exportSymbol("mlirAsyncRuntimePrintCurrentThreadId",
&mlir::runtime::mlirAsyncRuntimePrintCurrentThreadId);
}
extern "C" API void __mlir_runner_destroy() { resetDefaultAsyncRuntime(); }
} // namespace runtime
} // namespace mlir
#endif // MLIR_ASYNCRUNTIME_DEFINE_FUNCTIONS