-
Notifications
You must be signed in to change notification settings - Fork 10.8k
/
SelectObjectAttr.cpp
464 lines (396 loc) · 16.6 KB
/
SelectObjectAttr.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
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
//===- ObjectHandler.cpp - Implements base ObjectManager attributes -------===//
//
// 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 the `OffloadingLLVMTranslationAttrInterface` for the
// `SelectObject` attribute.
//
//===----------------------------------------------------------------------===//
#include "mlir/Dialect/GPU/IR/GPUDialect.h"
#include "mlir/Target/LLVMIR/Dialect/GPU/GPUToLLVMIRTranslation.h"
#include "mlir/Target/LLVMIR/Export.h"
#include "mlir/Target/LLVMIR/ModuleTranslation.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Module.h"
#include "llvm/Support/FormatVariadic.h"
using namespace mlir;
namespace {
// Implementation of the `OffloadingLLVMTranslationAttrInterface` model.
class SelectObjectAttrImpl
: public gpu::OffloadingLLVMTranslationAttrInterface::FallbackModel<
SelectObjectAttrImpl> {
public:
// Translates a `gpu.binary`, embedding the binary into a host LLVM module as
// global binary string.
LogicalResult embedBinary(Attribute attribute, Operation *operation,
llvm::IRBuilderBase &builder,
LLVM::ModuleTranslation &moduleTranslation) const;
// Translates a `gpu.launch_func` to a sequence of LLVM instructions resulting
// in a kernel launch call.
LogicalResult launchKernel(Attribute attribute,
Operation *launchFuncOperation,
Operation *binaryOperation,
llvm::IRBuilderBase &builder,
LLVM::ModuleTranslation &moduleTranslation) const;
// Returns the selected object for embedding.
gpu::ObjectAttr getSelectedObject(gpu::BinaryOp op) const;
};
// Returns an identifier for the global string holding the binary.
std::string getBinaryIdentifier(StringRef binaryName) {
return binaryName.str() + "_bin_cst";
}
} // namespace
void mlir::gpu::registerOffloadingLLVMTranslationInterfaceExternalModels(
DialectRegistry ®istry) {
registry.addExtension(+[](MLIRContext *ctx, gpu::GPUDialect *dialect) {
SelectObjectAttr::attachInterface<SelectObjectAttrImpl>(*ctx);
});
}
gpu::ObjectAttr
SelectObjectAttrImpl::getSelectedObject(gpu::BinaryOp op) const {
ArrayRef<Attribute> objects = op.getObjectsAttr().getValue();
// Obtain the index of the object to select.
int64_t index = -1;
if (Attribute target =
cast<gpu::SelectObjectAttr>(op.getOffloadingHandlerAttr())
.getTarget()) {
// If the target attribute is a number it is the index. Otherwise compare
// the attribute to every target inside the object array to find the index.
if (auto indexAttr = mlir::dyn_cast<IntegerAttr>(target)) {
index = indexAttr.getInt();
} else {
for (auto [i, attr] : llvm::enumerate(objects)) {
auto obj = mlir::dyn_cast<gpu::ObjectAttr>(attr);
if (obj.getTarget() == target) {
index = i;
}
}
}
} else {
// If the target attribute is null then it's selecting the first object in
// the object array.
index = 0;
}
if (index < 0 || index >= static_cast<int64_t>(objects.size())) {
op->emitError("the requested target object couldn't be found");
return nullptr;
}
return mlir::dyn_cast<gpu::ObjectAttr>(objects[index]);
}
LogicalResult SelectObjectAttrImpl::embedBinary(
Attribute attribute, Operation *operation, llvm::IRBuilderBase &builder,
LLVM::ModuleTranslation &moduleTranslation) const {
assert(operation && "The binary operation must be non null.");
if (!operation)
return failure();
auto op = mlir::dyn_cast<gpu::BinaryOp>(operation);
if (!op) {
operation->emitError("operation must be a GPU binary");
return failure();
}
gpu::ObjectAttr object = getSelectedObject(op);
if (!object)
return failure();
llvm::Module *module = moduleTranslation.getLLVMModule();
// Embed the object as a global string.
llvm::Constant *binary = llvm::ConstantDataArray::getString(
builder.getContext(), object.getObject().getValue(), false);
llvm::GlobalVariable *serializedObj =
new llvm::GlobalVariable(*module, binary->getType(), true,
llvm::GlobalValue::LinkageTypes::InternalLinkage,
binary, getBinaryIdentifier(op.getName()));
serializedObj->setLinkage(llvm::GlobalValue::LinkageTypes::InternalLinkage);
serializedObj->setAlignment(llvm::MaybeAlign(8));
serializedObj->setUnnamedAddr(llvm::GlobalValue::UnnamedAddr::None);
return success();
}
namespace llvm {
namespace {
class LaunchKernel {
public:
LaunchKernel(Module &module, IRBuilderBase &builder,
mlir::LLVM::ModuleTranslation &moduleTranslation);
// Get the kernel launch callee.
FunctionCallee getKernelLaunchFn();
// Get the kernel launch callee.
FunctionCallee getClusterKernelLaunchFn();
// Get the module function callee.
FunctionCallee getModuleFunctionFn();
// Get the module load callee.
FunctionCallee getModuleLoadFn();
// Get the module load JIT callee.
FunctionCallee getModuleLoadJITFn();
// Get the module unload callee.
FunctionCallee getModuleUnloadFn();
// Get the stream create callee.
FunctionCallee getStreamCreateFn();
// Get the stream destroy callee.
FunctionCallee getStreamDestroyFn();
// Get the stream sync callee.
FunctionCallee getStreamSyncFn();
// Ger or create the function name global string.
Value *getOrCreateFunctionName(StringRef moduleName, StringRef kernelName);
// Create the void* kernel array for passing the arguments.
Value *createKernelArgArray(mlir::gpu::LaunchFuncOp op);
// Create the full kernel launch.
mlir::LogicalResult createKernelLaunch(mlir::gpu::LaunchFuncOp op,
mlir::gpu::ObjectAttr object);
private:
Module &module;
IRBuilderBase &builder;
mlir::LLVM::ModuleTranslation &moduleTranslation;
Type *i32Ty{};
Type *i64Ty{};
Type *voidTy{};
Type *intPtrTy{};
PointerType *ptrTy{};
};
} // namespace
} // namespace llvm
LogicalResult SelectObjectAttrImpl::launchKernel(
Attribute attribute, Operation *launchFuncOperation,
Operation *binaryOperation, llvm::IRBuilderBase &builder,
LLVM::ModuleTranslation &moduleTranslation) const {
assert(launchFuncOperation && "The launch func operation must be non null.");
if (!launchFuncOperation)
return failure();
auto launchFuncOp = mlir::dyn_cast<gpu::LaunchFuncOp>(launchFuncOperation);
if (!launchFuncOp) {
launchFuncOperation->emitError("operation must be a GPU launch func Op.");
return failure();
}
auto binOp = mlir::dyn_cast<gpu::BinaryOp>(binaryOperation);
if (!binOp) {
binaryOperation->emitError("operation must be a GPU binary.");
return failure();
}
gpu::ObjectAttr object = getSelectedObject(binOp);
if (!object)
return failure();
return llvm::LaunchKernel(*moduleTranslation.getLLVMModule(), builder,
moduleTranslation)
.createKernelLaunch(launchFuncOp, object);
}
llvm::LaunchKernel::LaunchKernel(
Module &module, IRBuilderBase &builder,
mlir::LLVM::ModuleTranslation &moduleTranslation)
: module(module), builder(builder), moduleTranslation(moduleTranslation) {
i32Ty = builder.getInt32Ty();
i64Ty = builder.getInt64Ty();
ptrTy = builder.getPtrTy(0);
voidTy = builder.getVoidTy();
intPtrTy = builder.getIntPtrTy(module.getDataLayout());
}
llvm::FunctionCallee llvm::LaunchKernel::getKernelLaunchFn() {
return module.getOrInsertFunction(
"mgpuLaunchKernel",
FunctionType::get(voidTy,
ArrayRef<Type *>({ptrTy, intPtrTy, intPtrTy, intPtrTy,
intPtrTy, intPtrTy, intPtrTy, i32Ty,
ptrTy, ptrTy, ptrTy, i64Ty}),
false));
}
llvm::FunctionCallee llvm::LaunchKernel::getClusterKernelLaunchFn() {
return module.getOrInsertFunction(
"mgpuLaunchClusterKernel",
FunctionType::get(
voidTy,
ArrayRef<Type *>({ptrTy, intPtrTy, intPtrTy, intPtrTy, intPtrTy,
intPtrTy, intPtrTy, intPtrTy, intPtrTy, intPtrTy,
i32Ty, ptrTy, ptrTy, ptrTy}),
false));
}
llvm::FunctionCallee llvm::LaunchKernel::getModuleFunctionFn() {
return module.getOrInsertFunction(
"mgpuModuleGetFunction",
FunctionType::get(ptrTy, ArrayRef<Type *>({ptrTy, ptrTy}), false));
}
llvm::FunctionCallee llvm::LaunchKernel::getModuleLoadFn() {
return module.getOrInsertFunction(
"mgpuModuleLoad",
FunctionType::get(ptrTy, ArrayRef<Type *>({ptrTy, i64Ty}), false));
}
llvm::FunctionCallee llvm::LaunchKernel::getModuleLoadJITFn() {
return module.getOrInsertFunction(
"mgpuModuleLoadJIT",
FunctionType::get(ptrTy, ArrayRef<Type *>({ptrTy, i32Ty}), false));
}
llvm::FunctionCallee llvm::LaunchKernel::getModuleUnloadFn() {
return module.getOrInsertFunction(
"mgpuModuleUnload",
FunctionType::get(voidTy, ArrayRef<Type *>({ptrTy}), false));
}
llvm::FunctionCallee llvm::LaunchKernel::getStreamCreateFn() {
return module.getOrInsertFunction("mgpuStreamCreate",
FunctionType::get(ptrTy, false));
}
llvm::FunctionCallee llvm::LaunchKernel::getStreamDestroyFn() {
return module.getOrInsertFunction(
"mgpuStreamDestroy",
FunctionType::get(voidTy, ArrayRef<Type *>({ptrTy}), false));
}
llvm::FunctionCallee llvm::LaunchKernel::getStreamSyncFn() {
return module.getOrInsertFunction(
"mgpuStreamSynchronize",
FunctionType::get(voidTy, ArrayRef<Type *>({ptrTy}), false));
}
// Generates an LLVM IR dialect global that contains the name of the given
// kernel function as a C string, and returns a pointer to its beginning.
llvm::Value *llvm::LaunchKernel::getOrCreateFunctionName(StringRef moduleName,
StringRef kernelName) {
std::string globalName =
std::string(formatv("{0}_{1}_kernel_name", moduleName, kernelName));
if (GlobalVariable *gv = module.getGlobalVariable(globalName))
return gv;
return builder.CreateGlobalString(kernelName, globalName);
}
// Creates a struct containing all kernel parameters on the stack and returns
// an array of type-erased pointers to the fields of the struct. The array can
// then be passed to the CUDA / ROCm (HIP) kernel launch calls.
// The generated code is essentially as follows:
//
// %struct = alloca(sizeof(struct { Parameters... }))
// %array = alloca(NumParameters * sizeof(void *))
// for (i : [0, NumParameters))
// %fieldPtr = llvm.getelementptr %struct[0, i]
// llvm.store parameters[i], %fieldPtr
// %elementPtr = llvm.getelementptr %array[i]
// llvm.store %fieldPtr, %elementPtr
// return %array
llvm::Value *
llvm::LaunchKernel::createKernelArgArray(mlir::gpu::LaunchFuncOp op) {
SmallVector<Value *> args =
moduleTranslation.lookupValues(op.getKernelOperands());
SmallVector<Type *> structTypes(args.size(), nullptr);
for (auto [i, arg] : llvm::enumerate(args))
structTypes[i] = arg->getType();
Type *structTy = StructType::create(module.getContext(), structTypes);
Value *argStruct = builder.CreateAlloca(structTy, 0u);
Value *argArray = builder.CreateAlloca(
ptrTy, ConstantInt::get(intPtrTy, structTypes.size()));
for (auto [i, arg] : enumerate(args)) {
Value *structMember = builder.CreateStructGEP(structTy, argStruct, i);
builder.CreateStore(arg, structMember);
Value *arrayMember = builder.CreateConstGEP1_32(ptrTy, argArray, i);
builder.CreateStore(structMember, arrayMember);
}
return argArray;
}
// Emits LLVM IR to launch a kernel function:
// %0 = call %binarygetter
// %1 = call %moduleLoad(%0)
// %2 = <see generateKernelNameConstant>
// %3 = call %moduleGetFunction(%1, %2)
// %4 = call %streamCreate()
// %5 = <see generateParamsArray>
// call %launchKernel(%3, <launchOp operands 0..5>, 0, %4, %5, nullptr)
// call %streamSynchronize(%4)
// call %streamDestroy(%4)
// call %moduleUnload(%1)
mlir::LogicalResult
llvm::LaunchKernel::createKernelLaunch(mlir::gpu::LaunchFuncOp op,
mlir::gpu::ObjectAttr object) {
auto llvmValue = [&](mlir::Value value) -> Value * {
Value *v = moduleTranslation.lookupValue(value);
assert(v && "Value has not been translated.");
return v;
};
// Get grid dimensions.
mlir::gpu::KernelDim3 grid = op.getGridSizeOperandValues();
Value *gx = llvmValue(grid.x), *gy = llvmValue(grid.y),
*gz = llvmValue(grid.z);
// Get block dimensions.
mlir::gpu::KernelDim3 block = op.getBlockSizeOperandValues();
Value *bx = llvmValue(block.x), *by = llvmValue(block.y),
*bz = llvmValue(block.z);
// Get dynamic shared memory size.
Value *dynamicMemorySize = nullptr;
if (mlir::Value dynSz = op.getDynamicSharedMemorySize())
dynamicMemorySize = llvmValue(dynSz);
else
dynamicMemorySize = ConstantInt::get(i32Ty, 0);
// Create the argument array.
Value *argArray = createKernelArgArray(op);
// Default JIT optimization level.
llvm::Constant *optV = llvm::ConstantInt::get(i32Ty, 0);
// Check if there's an optimization level embedded in the object.
DictionaryAttr objectProps = object.getProperties();
mlir::Attribute optAttr;
if (objectProps && (optAttr = objectProps.get("O"))) {
auto optLevel = dyn_cast<IntegerAttr>(optAttr);
if (!optLevel)
return op.emitError("the optimization level must be an integer");
optV = llvm::ConstantInt::get(i32Ty, optLevel.getValue());
}
// Load the kernel module.
StringRef moduleName = op.getKernelModuleName().getValue();
std::string binaryIdentifier = getBinaryIdentifier(moduleName);
Value *binary = module.getGlobalVariable(binaryIdentifier, true);
if (!binary)
return op.emitError() << "Couldn't find the binary: " << binaryIdentifier;
auto binaryVar = dyn_cast<llvm::GlobalVariable>(binary);
if (!binaryVar)
return op.emitError() << "Binary is not a global variable: "
<< binaryIdentifier;
llvm::Constant *binaryInit = binaryVar->getInitializer();
auto binaryDataSeq =
dyn_cast_if_present<llvm::ConstantDataSequential>(binaryInit);
if (!binaryDataSeq)
return op.emitError() << "Couldn't find binary data array: "
<< binaryIdentifier;
llvm::Constant *binarySize =
llvm::ConstantInt::get(i64Ty, binaryDataSeq->getNumElements() *
binaryDataSeq->getElementByteSize());
Value *moduleObject =
object.getFormat() == gpu::CompilationTarget::Assembly
? builder.CreateCall(getModuleLoadJITFn(), {binary, optV})
: builder.CreateCall(getModuleLoadFn(), {binary, binarySize});
// Load the kernel function.
Value *moduleFunction = builder.CreateCall(
getModuleFunctionFn(),
{moduleObject,
getOrCreateFunctionName(moduleName, op.getKernelName().getValue())});
// Get the stream to use for execution. If there's no async object then create
// a stream to make a synchronous kernel launch.
Value *stream = nullptr;
bool handleStream = false;
if (mlir::Value asyncObject = op.getAsyncObject()) {
stream = llvmValue(asyncObject);
} else {
handleStream = true;
stream = builder.CreateCall(getStreamCreateFn(), {});
}
llvm::Constant *paramsCount =
llvm::ConstantInt::get(i64Ty, op.getNumKernelOperands());
// Create the launch call.
Value *nullPtr = ConstantPointerNull::get(ptrTy);
// Launch kernel with clusters if cluster size is specified.
if (op.hasClusterSize()) {
mlir::gpu::KernelDim3 cluster = op.getClusterSizeOperandValues();
Value *cx = llvmValue(cluster.x), *cy = llvmValue(cluster.y),
*cz = llvmValue(cluster.z);
builder.CreateCall(
getClusterKernelLaunchFn(),
ArrayRef<Value *>({moduleFunction, cx, cy, cz, gx, gy, gz, bx, by, bz,
dynamicMemorySize, stream, argArray, nullPtr}));
} else {
builder.CreateCall(getKernelLaunchFn(),
ArrayRef<Value *>({moduleFunction, gx, gy, gz, bx, by,
bz, dynamicMemorySize, stream,
argArray, nullPtr, paramsCount}));
}
// Sync & destroy the stream, for synchronous launches.
if (handleStream) {
builder.CreateCall(getStreamSyncFn(), {stream});
builder.CreateCall(getStreamDestroyFn(), {stream});
}
// Unload the kernel module.
builder.CreateCall(getModuleUnloadFn(), {moduleObject});
return success();
}