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
50 lines
1.8 KiB
C++
50 lines
1.8 KiB
C++
//===- GPUOpsLowering.h - GPU FuncOp / ReturnOp lowering -------*- C++ -*--===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
#ifndef MLIR_CONVERSION_GPUCOMMON_GPUOPSLOWERING_H_
|
|
#define MLIR_CONVERSION_GPUCOMMON_GPUOPSLOWERING_H_
|
|
|
|
#include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVM.h"
|
|
#include "mlir/Dialect/GPU/GPUDialect.h"
|
|
#include "mlir/Dialect/LLVMIR/LLVMDialect.h"
|
|
|
|
namespace mlir {
|
|
|
|
struct GPUFuncOpLowering : ConvertOpToLLVMPattern<gpu::GPUFuncOp> {
|
|
GPUFuncOpLowering(LLVMTypeConverter &converter, unsigned allocaAddrSpace,
|
|
Identifier kernelAttributeName)
|
|
: ConvertOpToLLVMPattern<gpu::GPUFuncOp>(converter),
|
|
allocaAddrSpace(allocaAddrSpace),
|
|
kernelAttributeName(kernelAttributeName) {}
|
|
|
|
LogicalResult
|
|
matchAndRewrite(gpu::GPUFuncOp gpuFuncOp, ArrayRef<Value> operands,
|
|
ConversionPatternRewriter &rewriter) const override;
|
|
|
|
private:
|
|
/// The address spcae to use for `alloca`s in private memory.
|
|
unsigned allocaAddrSpace;
|
|
|
|
/// The attribute name to use instead of `gpu.kernel`.
|
|
Identifier kernelAttributeName;
|
|
};
|
|
|
|
struct GPUReturnOpLowering : public ConvertOpToLLVMPattern<gpu::ReturnOp> {
|
|
using ConvertOpToLLVMPattern<gpu::ReturnOp>::ConvertOpToLLVMPattern;
|
|
|
|
LogicalResult
|
|
matchAndRewrite(gpu::ReturnOp op, ArrayRef<Value> operands,
|
|
ConversionPatternRewriter &rewriter) const override {
|
|
rewriter.replaceOpWithNewOp<LLVM::ReturnOp>(op, operands);
|
|
return success();
|
|
}
|
|
};
|
|
|
|
} // namespace mlir
|
|
|
|
#endif // MLIR_CONVERSION_GPUCOMMON_GPUOPSLOWERING_H_
|