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
|
//===- LowerGPUToCUBIN.cpp - Convert GPU kernel to CUBIN blob -------------===//
//
// 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 a pass that serializes a gpu module into CUBIN blob and
// adds that blob as a string attribute of the module.
//
//===----------------------------------------------------------------------===//
#include "mlir/Dialect/GPU/Transforms/Passes.h"
#include "llvm/Support/Debug.h"
#if MLIR_GPU_TO_CUBIN_PASS_ENABLE
#include "mlir/Pass/Pass.h"
#include "mlir/Target/LLVMIR/Dialect/NVVM/NVVMToLLVMIRTranslation.h"
#include "mlir/Target/LLVMIR/Export.h"
#include "llvm/Support/TargetSelect.h"
#include "llvm/Support/Threading.h"
#include <cuda.h>
using namespace mlir;
static void emitCudaError(const llvm::Twine &expr, const char *buffer,
CUresult result, Location loc) {
const char *error;
cuGetErrorString(result, &error);
emitError(loc, expr.concat(" failed with error code ")
.concat(llvm::Twine{error})
.concat("[")
.concat(buffer)
.concat("]"));
}
#define RETURN_ON_CUDA_ERROR(expr) \
do { \
if (auto status = (expr)) { \
emitCudaError(#expr, jitErrorBuffer, status, loc); \
return {}; \
} \
} while (false)
namespace {
class SerializeToCubinPass
: public PassWrapper<SerializeToCubinPass, gpu::SerializeToBlobPass> {
static llvm::once_flag initializeBackendOnce;
public:
MLIR_DEFINE_EXPLICIT_INTERNAL_INLINE_TYPE_ID(SerializeToCubinPass)
SerializeToCubinPass(StringRef triple = "nvptx64-nvidia-cuda",
StringRef chip = "sm_35", StringRef features = "+ptx60",
int optLevel = 2, bool dumpPtx = false);
StringRef getArgument() const override { return "gpu-to-cubin"; }
StringRef getDescription() const override {
return "Lower GPU kernel function to CUBIN binary annotations";
}
private:
void getDependentDialects(DialectRegistry ®istry) const override;
// Serializes PTX to CUBIN.
std::unique_ptr<std::vector<char>>
serializeISA(const std::string &isa) override;
};
} // namespace
// Sets the 'option' to 'value' unless it already has a value.
static void maybeSetOption(Pass::Option<std::string> &option, StringRef value) {
if (!option.hasValue())
option = value.str();
}
llvm::once_flag SerializeToCubinPass::initializeBackendOnce;
SerializeToCubinPass::SerializeToCubinPass(StringRef triple, StringRef chip,
StringRef features, int optLevel,
bool dumpPtx) {
// No matter how this pass is constructed, ensure that the NVPTX backend
// is initialized exactly once.
llvm::call_once(initializeBackendOnce, []() {
// Initialize LLVM NVPTX backend.
LLVMInitializeNVPTXTarget();
LLVMInitializeNVPTXTargetInfo();
LLVMInitializeNVPTXTargetMC();
LLVMInitializeNVPTXAsmPrinter();
});
maybeSetOption(this->triple, triple);
maybeSetOption(this->chip, chip);
maybeSetOption(this->features, features);
this->dumpPtx = dumpPtx;
if (this->optLevel.getNumOccurrences() == 0)
this->optLevel.setValue(optLevel);
}
void SerializeToCubinPass::getDependentDialects(
DialectRegistry ®istry) const {
registerNVVMDialectTranslation(registry);
gpu::SerializeToBlobPass::getDependentDialects(registry);
}
std::unique_ptr<std::vector<char>>
SerializeToCubinPass::serializeISA(const std::string &isa) {
Location loc = getOperation().getLoc();
char jitErrorBuffer[4096] = {0};
RETURN_ON_CUDA_ERROR(cuInit(0));
// Linking requires a device context.
CUdevice device;
RETURN_ON_CUDA_ERROR(cuDeviceGet(&device, 0));
CUcontext context;
RETURN_ON_CUDA_ERROR(cuCtxCreate(&context, 0, device));
CUlinkState linkState;
CUjit_option jitOptions[] = {CU_JIT_ERROR_LOG_BUFFER,
CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES};
void *jitOptionsVals[] = {jitErrorBuffer,
reinterpret_cast<void *>(sizeof(jitErrorBuffer))};
RETURN_ON_CUDA_ERROR(cuLinkCreate(2, /* number of jit options */
jitOptions, /* jit options */
jitOptionsVals, /* jit option values */
&linkState));
auto kernelName = getOperation().getName().str();
if (dumpPtx) {
llvm::dbgs() << " Kernel Name : [" << kernelName << "]\n";
llvm::dbgs() << isa << "\n";
}
RETURN_ON_CUDA_ERROR(cuLinkAddData(
linkState, CUjitInputType::CU_JIT_INPUT_PTX,
const_cast<void *>(static_cast<const void *>(isa.c_str())), isa.length(),
kernelName.c_str(), 0, /* number of jit options */
nullptr, /* jit options */
nullptr /* jit option values */
));
void *cubinData;
size_t cubinSize;
RETURN_ON_CUDA_ERROR(cuLinkComplete(linkState, &cubinData, &cubinSize));
char *cubinAsChar = static_cast<char *>(cubinData);
auto result =
std::make_unique<std::vector<char>>(cubinAsChar, cubinAsChar + cubinSize);
// This will also destroy the cubin data.
RETURN_ON_CUDA_ERROR(cuLinkDestroy(linkState));
RETURN_ON_CUDA_ERROR(cuCtxDestroy(context));
return result;
}
// Register pass to serialize GPU kernel functions to a CUBIN binary annotation.
void mlir::registerGpuSerializeToCubinPass() {
PassRegistration<SerializeToCubinPass> registerSerializeToCubin(
[] { return std::make_unique<SerializeToCubinPass>(); });
}
std::unique_ptr<Pass> mlir::createGpuSerializeToCubinPass(StringRef triple,
StringRef arch,
StringRef features,
int optLevel,
bool dumpPtx) {
return std::make_unique<SerializeToCubinPass>(triple, arch, features,
optLevel, dumpPtx);
}
#else // MLIR_GPU_TO_CUBIN_PASS_ENABLE
void mlir::registerGpuSerializeToCubinPass() {}
#endif // MLIR_GPU_TO_CUBIN_PASS_ENABLE
|
