19db802e7b
There is no need for the interface implementations to be exposed, opaque registration functions are sufficient for all users, similarly to passes. Reviewed By: mehdi_amini Differential Revision: https://reviews.llvm.org/D97852
56 lines
2.0 KiB
C++
56 lines
2.0 KiB
C++
//===- TestConvertGPUKernelToCubin.cpp - Test gpu kernel cubin lowering ---===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "mlir/Conversion/GPUCommon/GPUCommonPass.h"
|
|
#include "mlir/Dialect/LLVMIR/NVVMDialect.h"
|
|
#include "mlir/Pass/Pass.h"
|
|
#include "mlir/Pass/PassManager.h"
|
|
#include "mlir/Target/LLVMIR/Dialect/LLVMIR/LLVMToLLVMIRTranslation.h"
|
|
#include "mlir/Target/LLVMIR/Dialect/NVVM/NVVMToLLVMIRTranslation.h"
|
|
#include "mlir/Target/LLVMIR/Export.h"
|
|
#include "llvm/Support/TargetSelect.h"
|
|
|
|
using namespace mlir;
|
|
|
|
#if MLIR_CUDA_CONVERSIONS_ENABLED
|
|
static OwnedBlob compilePtxToCubinForTesting(const std::string &, Location,
|
|
StringRef) {
|
|
const char data[] = "CUBIN";
|
|
return std::make_unique<std::vector<char>>(data, data + sizeof(data) - 1);
|
|
}
|
|
|
|
static std::unique_ptr<llvm::Module>
|
|
translateModuleToNVVMIR(Operation *m, llvm::LLVMContext &llvmContext,
|
|
StringRef moduleName) {
|
|
registerLLVMDialectTranslation(*m->getContext());
|
|
registerNVVMDialectTranslation(*m->getContext());
|
|
return translateModuleToLLVMIR(m, llvmContext, moduleName);
|
|
}
|
|
|
|
namespace mlir {
|
|
namespace test {
|
|
void registerTestConvertGPUKernelToCubinPass() {
|
|
PassPipelineRegistration<>(
|
|
"test-kernel-to-cubin",
|
|
"Convert all kernel functions to CUDA cubin blobs",
|
|
[](OpPassManager &pm) {
|
|
// Initialize LLVM NVPTX backend.
|
|
LLVMInitializeNVPTXTarget();
|
|
LLVMInitializeNVPTXTargetInfo();
|
|
LLVMInitializeNVPTXTargetMC();
|
|
LLVMInitializeNVPTXAsmPrinter();
|
|
|
|
pm.addPass(createConvertGPUKernelToBlobPass(
|
|
translateModuleToNVVMIR, compilePtxToCubinForTesting,
|
|
"nvptx64-nvidia-cuda", "sm_35", "+ptx60", "nvvm.cubin"));
|
|
});
|
|
}
|
|
} // namespace test
|
|
} // namespace mlir
|
|
#endif
|