torch-mlir/include/npcomp/E2E/E2E.h

66 lines
2.1 KiB
C
Raw Normal View History

//===------------------------------------------------------------*- C++ -*-===//
//
// This file is licensed 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 NPCOMP_E2E_E2E_H
#define NPCOMP_E2E_E2E_H
#include "mlir/Pass/Pass.h"
#include "mlir/Pass/PassManager.h"
namespace mlir {
namespace NPCOMP {
/// Registers all E2E passes.
void registerE2EPasses();
// Look in createE2ELoweringPipeline for more information about how these
// passes fit together.
//
// Pass summaries are in Passes.td.
std::unique_ptr<OperationPass<FuncOp>> createLowerBroadcastToToLoopsPass();
std::unique_ptr<OperationPass<FuncOp>>
createLowerLinalgOnTensorToLinalgOnMemrefPass();
std::unique_ptr<OperationPass<ModuleOp>>
createLowerConstantTensorsToMemrefsPass();
std::unique_ptr<OperationPass<FuncOp>> createResolveShapeOfOpsPass();
std::unique_ptr<OperationPass<FuncOp>> createResolveTensorLoadStoreOpsPass();
std::unique_ptr<OperationPass<FuncOp>> createLowerLinalgLoopDimOpsPass();
std::unique_ptr<OperationPass<FuncOp>> createLowerRankedShapesPass();
Rework e2e flow to use new "npcomprt" This ~totally reworks the existing "runtime" stuff to be more principled and usable, such as from Python. It's still not fully production-quality, mainly in the department of memory management (e.g. it currently leaks memory; we need to figure out "who frees memrefs" + the analysis and transformation needed to do that (maybe use upstream buffer allocation pass?)). The user API is in include/npcomp/runtime/UserAPI.h, though include/npcomp/JITRuntime/JITModule.h is a friendlier wrapper. The stuff under {include,lib}/runtime is totally firewalled from the compiler and tiny (<6kB, though no attention has gone into optimizing that size). For example, we don't link in libSupport into the runtime, instead having our own bare bones replacements for basics like ArrayRef (the JITRuntime helps with bridging that gap, since it *can* depend on all common LLVM utilities). The overall features of npcomprt is that it exposes a module that with multiple function entry points. Each function has arguments and results that are tensor-valued, and npcomprt::Tensor is the runtime type that is used to interact with that (and a npcomprt::Ref<T> reference-counting wrapper is provided to wrap npcomprt::Tensor in the common case). From an implementation perspective, an npcomprt module at the LLVM/object/binary level exposes a single module descriptor struct that has pointers to other metadata (currently just a list of function metadata descriptors). All interactions with the npcomp runtime are keyed off of that module descriptor, including function lookups and dispatching. This is done to dodge platform ABI issues and also allow enough reflection to e.g. verify provided arguments. Most of the compiler-side work here was in LowerToNpcomprtABI and LowerToLLVM. Also, - Rename npcomp_rt/NpcompRt to npcomprt/Npcomprt; it was getting annoying to type the underscores/caps. - misc improvements to bash_helpers.sh
2020-07-09 08:15:40 +08:00
std::unique_ptr<OperationPass<ModuleOp>> createLowerToNpcomprtABIPass();
std::unique_ptr<OperationPass<FuncOp>> createLowerAllocMemRefOpsPass();
std::unique_ptr<OperationPass<ModuleOp>> createLowerToLLVMPass();
void createLowerToHybridTensorMemRefPipeline(OpPassManager &pm);
struct E2ELoweringPipelineOptions
: public PassPipelineOptions<E2ELoweringPipelineOptions> {
// If this option is true, then perform optimizations.
// If this option is false, only do the bare minimum for correctness.
Option<bool> optimize{*this, "optimize", llvm::cl::desc("Do optimizations."),
llvm::cl::init(false)};
};
// The main pipeline that encapsulates the full E2E lowering.
void createE2ELoweringPipeline(OpPassManager &pm,
const E2ELoweringPipelineOptions &options);
} // namespace NPCOMP
} // namespace mlir
#endif // NPCOMP_E2E_E2E_H