forked from OSchip/llvm-project
112 lines
4.9 KiB
C++
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>();
|
|
}
|