llvm-project/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp

112 lines
4.9 KiB
C++

//===- LowerGpuOpsToROCDLOps.cpp - MLIR GPU to ROCDL lowering passes ------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file implements a pass to generate ROCDLIR operations for higher-level
// GPU operations.
//
//===----------------------------------------------------------------------===//
#include "mlir/Conversion/GPUToROCDL/GPUToROCDLPass.h"
#include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVMPass.h"
#include "mlir/Conversion/VectorToLLVM/ConvertVectorToLLVM.h"
#include "mlir/Conversion/VectorToROCDL/VectorToROCDL.h"
#include "mlir/Dialect/GPU/GPUDialect.h"
#include "mlir/Dialect/GPU/Passes.h"
#include "mlir/Dialect/LLVMIR/ROCDLDialect.h"
#include "mlir/Dialect/Vector/VectorOps.h"
#include "mlir/Pass/Pass.h"
#include "mlir/Transforms/DialectConversion.h"
#include "llvm/Support/FormatVariadic.h"
#include "../GPUCommon/GPUOpsLowering.h"
#include "../GPUCommon/IndexIntrinsicsOpLowering.h"
#include "../GPUCommon/OpToFuncCallLowering.h"
#include "../PassDetail.h"
using namespace mlir;
namespace {
/// Import the GPU Ops to ROCDL Patterns.
#include "GPUToROCDL.cpp.inc"
// A pass that replaces all occurrences of GPU device operations with their
// corresponding ROCDL equivalent.
//
// This pass only handles device code and is not meant to be run on GPU host
// code.
class LowerGpuOpsToROCDLOpsPass
: public ConvertGpuOpsToROCDLOpsBase<LowerGpuOpsToROCDLOpsPass> {
public:
void runOnOperation() override {
gpu::GPUModuleOp m = getOperation();
LLVMTypeConverter converter(m.getContext());
OwningRewritePatternList patterns;
populateGpuRewritePatterns(m.getContext(), patterns);
applyPatternsAndFoldGreedily(m, patterns);
patterns.clear();
populateVectorToLLVMConversionPatterns(converter, patterns);
populateVectorToROCDLConversionPatterns(converter, patterns);
populateStdToLLVMConversionPatterns(converter, patterns);
populateGpuToROCDLConversionPatterns(converter, patterns);
LLVMConversionTarget target(getContext());
target.addIllegalDialect<gpu::GPUDialect>();
target.addIllegalOp<LLVM::CosOp, LLVM::ExpOp, LLVM::FAbsOp, LLVM::FCeilOp,
LLVM::LogOp, LLVM::Log10Op, LLVM::Log2Op>();
target.addIllegalOp<FuncOp>();
target.addLegalDialect<ROCDL::ROCDLDialect>();
// TODO(whchung): Remove once we support replacing non-root ops.
target.addLegalOp<gpu::YieldOp, gpu::GPUModuleOp, gpu::ModuleEndOp>();
if (failed(applyPartialConversion(m, target, patterns, &converter)))
signalPassFailure();
}
};
} // anonymous namespace
void mlir::populateGpuToROCDLConversionPatterns(
LLVMTypeConverter &converter, OwningRewritePatternList &patterns) {
populateWithGenerated(converter.getDialect()->getContext(), &patterns);
patterns.insert<
GPUIndexIntrinsicOpLowering<gpu::ThreadIdOp, ROCDL::ThreadIdXOp,
ROCDL::ThreadIdYOp, ROCDL::ThreadIdZOp>,
GPUIndexIntrinsicOpLowering<gpu::BlockDimOp, ROCDL::BlockDimXOp,
ROCDL::BlockDimYOp, ROCDL::BlockDimZOp>,
GPUIndexIntrinsicOpLowering<gpu::BlockIdOp, ROCDL::BlockIdXOp,
ROCDL::BlockIdYOp, ROCDL::BlockIdZOp>,
GPUIndexIntrinsicOpLowering<gpu::GridDimOp, ROCDL::GridDimXOp,
ROCDL::GridDimYOp, ROCDL::GridDimZOp>,
GPUFuncOpLowering<5>, GPUReturnOpLowering>(converter);
patterns.insert<OpToFuncCallLowering<AbsFOp>>(converter, "__ocml_fabs_f32",
"__ocml_fabs_f64");
patterns.insert<OpToFuncCallLowering<CeilFOp>>(converter, "__ocml_ceil_f32",
"__ocml_ceil_f64");
patterns.insert<OpToFuncCallLowering<CosOp>>(converter, "__ocml_cos_f32",
"__ocml_cos_f64");
patterns.insert<OpToFuncCallLowering<ExpOp>>(converter, "__ocml_exp_f32",
"__ocml_exp_f64");
patterns.insert<OpToFuncCallLowering<LogOp>>(converter, "__ocml_log_f32",
"__ocml_log_f64");
patterns.insert<OpToFuncCallLowering<Log10Op>>(converter, "__ocml_log10_f32",
"__ocml_log10_f64");
patterns.insert<OpToFuncCallLowering<Log2Op>>(converter, "__ocml_log2_f32",
"__ocml_log2_f64");
patterns.insert<OpToFuncCallLowering<TanhOp>>(converter, "__ocml_tanh_f32",
"__ocml_tanh_f64");
}
std::unique_ptr<OperationPass<gpu::GPUModuleOp>>
mlir::createLowerGpuOpsToROCDLOpsPass() {
return std::make_unique<LowerGpuOpsToROCDLOpsPass>();
}