4c4876c314
Until now, the GPU translation to NVVM or ROCDL intrinsics relied on the presence of the generic `gpu.kernel` attribute to attach additional LLVM IR metadata to the relevant functions. This would be problematic if each dialect were to handle the conversion of its own options, which is the intended direction for the translation infrastructure. Introduce `nvvm.kernel` and `rocdl.kernel` in addition to `gpu.kernel` and base translation on these new attributes instead. Reviewed By: herhut Differential Revision: https://reviews.llvm.org/D96591
41 lines
608 B
CMake
41 lines
608 B
CMake
if (MLIR_CUDA_CONVERSIONS_ENABLED)
|
|
set(NVPTX_LIBS
|
|
NVPTXCodeGen
|
|
NVPTXDesc
|
|
NVPTXInfo
|
|
)
|
|
endif()
|
|
|
|
if (MLIR_ROCM_CONVERSIONS_ENABLED)
|
|
set(AMDGPU_LIBS
|
|
AMDGPUCodeGen
|
|
AMDGPUDesc
|
|
AMDGPUInfo
|
|
)
|
|
endif()
|
|
|
|
add_mlir_conversion_library(MLIRGPUToGPURuntimeTransforms
|
|
ConvertLaunchFuncToRuntimeCalls.cpp
|
|
ConvertKernelFuncToBlob.cpp
|
|
GPUOpsLowering.cpp
|
|
|
|
DEPENDS
|
|
MLIRConversionPassIncGen
|
|
intrinsics_gen
|
|
|
|
LINK_COMPONENTS
|
|
Core
|
|
MC
|
|
${AMDGPU_LIBS}
|
|
${NVPTX_LIBS}
|
|
|
|
LINK_LIBS PUBLIC
|
|
MLIRAsyncToLLVM
|
|
MLIRGPU
|
|
MLIRIR
|
|
MLIRLLVMIR
|
|
MLIRPass
|
|
MLIRSupport
|
|
MLIRStandardToLLVM
|
|
)
|