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
|
if (MLIR_ENABLE_CUDA_CONVERSIONS)
set(NVPTX_LIBS
NVPTXCodeGen
NVPTXDesc
NVPTXInfo
)
endif()
if (MLIR_ENABLE_ROCM_CONVERSIONS)
set(AMDGPU_LIBS
IRReader
IPO
linker
MCParser
AMDGPUAsmParser
AMDGPUCodeGen
AMDGPUDesc
AMDGPUInfo
target
)
endif()
add_mlir_dialect_library(MLIRGPUDialect
IR/GPUDialect.cpp
IR/InferIntRangeInterfaceImpls.cpp
ADDITIONAL_HEADER_DIRS
${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/GPU
DEPENDS
MLIRGPUOpsIncGen
MLIRGPUOpsAttributesIncGen
MLIRGPUOpsEnumsGen
MLIRGPUOpInterfacesIncGen
LINK_LIBS PUBLIC
MLIRArithDialect
MLIRDLTIDialect
MLIRInferIntRangeInterface
MLIRIR
MLIRMemRefDialect
MLIRSideEffectInterfaces
MLIRSupport
)
add_mlir_dialect_library(MLIRGPUTransforms
Transforms/AllReduceLowering.cpp
Transforms/AsyncRegionRewriter.cpp
Transforms/GlobalIdRewriter.cpp
Transforms/KernelOutlining.cpp
Transforms/MemoryPromotion.cpp
Transforms/ParallelLoopMapper.cpp
Transforms/ShuffleRewriter.cpp
Transforms/SerializeToBlob.cpp
Transforms/SerializeToCubin.cpp
Transforms/SerializeToHsaco.cpp
ADDITIONAL_HEADER_DIRS
${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/GPU
LINK_COMPONENTS
Core
MC
Target
${NVPTX_LIBS}
${AMDGPU_LIBS}
DEPENDS
MLIRGPUPassIncGen
MLIRParallelLoopMapperEnumsGen
LINK_LIBS PUBLIC
MLIRAffineUtils
MLIRArithDialect
MLIRAsyncDialect
MLIRBuiltinToLLVMIRTranslation
MLIRDataLayoutInterfaces
MLIRExecutionEngineUtils
MLIRGPUDialect
MLIRIR
MLIRIndexDialect
MLIRLLVMDialect
MLIRGPUToLLVMIRTranslation
MLIRLLVMToLLVMIRTranslation
MLIRMemRefDialect
MLIRPass
MLIRSCFDialect
MLIRSideEffectInterfaces
MLIRSupport
MLIRTransformUtils
)
add_subdirectory(TransformOps)
if(MLIR_ENABLE_CUDA_RUNNER)
if(NOT MLIR_ENABLE_CUDA_CONVERSIONS)
message(SEND_ERROR
"Building mlir with cuda support requires the NVPTX backend")
endif()
# Configure CUDA language support. Using check_language first allows us to
# give a custom error message.
include(CheckLanguage)
check_language(CUDA)
if (CMAKE_CUDA_COMPILER)
enable_language(CUDA)
else()
message(SEND_ERROR
"Building mlir with cuda support requires a working CUDA install")
endif()
# Enable gpu-to-cubin pass.
target_compile_definitions(obj.MLIRGPUTransforms
PRIVATE
MLIR_GPU_TO_CUBIN_PASS_ENABLE=1
)
# Add CUDA headers includes and the libcuda.so library.
target_include_directories(obj.MLIRGPUTransforms
PRIVATE
${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES}
)
find_library(CUDA_DRIVER_LIBRARY cuda HINTS ${CMAKE_CUDA_IMPLICIT_LINK_DIRECTORIES} REQUIRED)
target_link_libraries(MLIRGPUTransforms
PRIVATE
MLIRNVVMToLLVMIRTranslation
${CUDA_DRIVER_LIBRARY}
)
endif()
if(MLIR_ENABLE_ROCM_CONVERSIONS)
if (NOT ("AMDGPU" IN_LIST LLVM_TARGETS_TO_BUILD))
message(SEND_ERROR
"Building mlir with ROCm support requires the AMDGPU backend")
endif()
set(DEFAULT_ROCM_PATH "/opt/rocm" CACHE PATH "Fallback path to search for ROCm installs")
target_compile_definitions(obj.MLIRGPUTransforms
PRIVATE
__DEFAULT_ROCM_PATH__="${DEFAULT_ROCM_PATH}"
MLIR_GPU_TO_HSACO_PASS_ENABLE=1
)
target_link_libraries(MLIRGPUTransforms
PRIVATE
MLIRROCDLToLLVMIRTranslation
)
endif()
|
