TestConvertGPUKernelToCubin.cpp
1.47 KB
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
//===- 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/Pass/Pass.h"
#include "mlir/Pass/PassManager.h"
#include "mlir/Target/NVVMIR.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);
}
namespace mlir {
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 mlir
#endif