torch-mlir/include/npcomp/Dialect/Torch/Transforms/Passes.h

64 lines
2.3 KiB
C
Raw Normal View History

//===------------------------------------------------------------*- 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 NPCOMP_DIALECT_TORCH_TRANSFORMS_PASSES_H
#define NPCOMP_DIALECT_TORCH_TRANSFORMS_PASSES_H
#include "mlir/Pass/Pass.h"
#include <memory>
namespace mlir {
namespace NPCOMP {
namespace Torch {
std::unique_ptr<OperationPass<ModuleOp>> createGlobalizeObjectGraphPass();
Support multiple instances of a class in GlobalizeObjectGraph. This happens in practice with e.g. ResNet from torchvision (multiple instances of the same BatchNorm class). The key observation is that for this program, and the expected set of programs, we can convert the program to the same globalized form with a bit more static analysis and effort to suitably monomorphize the program. Though what we are doing here is fairly annoying to implement, it saves any nontrivial later pass from having to do similar analyses (or worse). E.g. shape inference would need to be object-graph aware, mutation/lifetime analyses would have to be aware, etc. Additionally, it would make us front-load what it means to have a !torch.nn.Module type on an ABI boundary, which we are just not ready to handle. I'm really, really hoping that in practice we can get away with this, otherwise it's going to be really rough designing a representation (and implementing everything to back it) that is convenient to transform and gracefully scales from full object graph (in the most dynamic case) down to a fixed set of global slots like we have here (in the most static case, which we presume a lot of practical programs fall into). This also involved introducing a `torch-prepare-for-globalize-object-graph` pass that does a minimal set of lowerings to simplify the IR into a more orthogonal and analyzable form, and a `torch-globalize-pipeline` helper. Recommended review order: - updated documentation in Passes.td - new tests in `globalize-object-graph-multiple-instances*.mlir` - implementation of GlobalizeObjectGraph.cpp - PrepareForGlobalizeObjectGraph.cpp + prepare-for-globalize-object-graph.mlir - misc stuff like torch-globalize-pipeline pipeline definition. With this, we can import, globalize, and inline resnet18 from torchvision: https://gist.github.com/silvasean/821586afc19b67d9fb72030b2e0adeb8
2021-03-10 12:33:21 +08:00
std::unique_ptr<OperationPass<ModuleOp>>
createPrepareForGlobalizeObjectGraphPass();
struct TorchLoweringPipelineOptions
: public PassPipelineOptions<TorchLoweringPipelineOptions> {
// 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(true)};
};
/// Creates a pipeline that lowers the object graph IR that is produced by
/// TorchScript import into the form expected by npcomp-verify-backend-contract.
void createLowerObjectGraphPipeline(
OpPassManager &pm, const TorchLoweringPipelineOptions &options);
/// Creates a pipeline that lowers a flat list of funcs and global slots
/// with the torch and aten dialects and mutable arrays and converts it to
/// the form required by npcomp-verify-backend-contract, in particular
/// lowering most arrays to ranked tensors of known dtype, lowering aten ops to
/// linalg, converting torch.prim.* ops to elementary math operations.
void createLowerToNpcompBackendPipeline(
OpPassManager &pm, const TorchLoweringPipelineOptions &options);
std::unique_ptr<OperationPass<ModuleOp>> createAdjustCallingConventionsPass();
std::unique_ptr<OperationPass<FuncOp>> createRefineTypesPass();
std::unique_ptr<OperationPass<ModuleOp>> createInlineGlobalSlotsPass();
Significantly restructure torch/aten import design. This is a really major and invasive restructuring of the way we get torch operators (`torch::jit::Operator` / `c10::OperatorHandle`) into MLIR. Please forgive the challenging review, but due to the sheer invasiveness, it wasn't really practical do do it in sane smaller pieces. This fully replaces everything that was already working on the TorchScript path (actually, more -- we added tanh support to TorchToLinalg in order to delete the older code paths). Additionally, I've kept the lights on for the acap path too, including what little e2e stuff was working before (for expediency I made a few tiny compromises along the way that will be easy to undo when we give that path proper attention). Overview of the new design: - The torch operator `somens::someunqualname.someoverloadname` is imported as `torch.somens.someunqualname.someoverloadname` (skip the last dotted part if the overload name is empty), OR, if we don't have such an op registered, it is imported as `torch.operator "somens.someunqualname.someoverloadname" (...) : ...`. - The addition of the "overload name" is a critical element here, as the `(ns,unqual,overload)` triple is unique, which solves a lot of problems we were having. - This involves having separate MLIR ops for the `trailing_` and `.out` variants and all the different overloads. This seemed necessary, because the set of overloads is so wild and varied and unstructured. The previous design was leaning into some underlying structure that just isn't there -- the default situation is the "random overload that we want to manage on the MLIR side", rather than that being an exception. E.g. `aten::ne` (not-equal) has 21 overloads, only 4 of which are c10 dispatcher ops see [gist](https://gist.github.com/silvasean/190ba918c550c956260e21254e1b8aa1), and the "out" variant is really called `.Tensor_out` instead of `.out` as it frequently is for other ops. - Rationale for all being in `torch` namespace: the set of operators are so varied and unstructured that "dialect per namespace" doesn't result in anything resembling the typical MLIR dialect boundary expectations. We could maybe draw the boundary at dispatcher ops vs non-dispatcher ops, but that doesn't seem to really result in very much useful structure at this point in time. - Note: within the torch operator registry, we effectively have a mini-basicpy subdialect (already type-resolved), which is reasonably structured. - The existing Torch op interfaces are also removed -- now that we track the overload name, we can losslessly find the original operator. - Instead of `ATenRecognizeKernelsPass`, we now have a `ReduceOpVariantsPass` that keys off certain traits (and perhaps eventually interfaces) to reduce variants of ops to a smaller set, ideally operating on immutable tensors and using surrounding ops to model the mutability/aliasing aspects. - Note: `torch.ns.unqual.overload` ops allow both immutable and mutable tensors (unlike the previous hard distinction in the common case). This is a premonition for a future change that will introduce a bona fide `!torch.tensor` type that will clean up a bunch of stuff. - `TorchToLinalg` / `TorchToStd` supercede the existing "ATen->TCF->TCP->Linalg" path. - The new `torch_ods_gen.py` supercedes `torch_signature_ods_gen.py`. It should look somewhat familiar, but the benefit of hindsight has allowed a lot of simplifications. The overall trend seems to be to make the `torch` dialect a nice layer independent of anything else. It feels like as a natural result of various future changes we will be removing the reliance on basicpy+numpy dialects and have a nice self-contained type system too that properly models the TorchScript type system (including proper subtyping, mutable/immutable tensors, optional dtype, etc.). Recommended review order: - Start at some of the new import IR, e.g. in `frontends/pytorch/test/node_import/prim.py`, `frontends/pytorch/test/acap_export/test_export_add3.py`, and other tests. - `frontends/pytorch/python/torch_mlir_utils/codegen/torch_ods_gen.py` and associated generated files: - `include/npcomp/Dialect/Torch/IR/GeneratedAtenOps.td` - `include/npcomp/Dialect/Torch/IR/GeneratedPrimOps.td` - Inspect `ReduceOpVariants.cpp` / `reduce-op-variants.mlir` and the new traits in `include/npcomp/Dialect/Torch/IR/TorchTraits.h` - Various code changes in the import path in `frontends/pytorch/csrc/builder`. Probably most interesting is the new code in `torch_to_mlir_utils.cpp` that has the logic to create the `torch.operator` ops or `torch.ns.unqual.overload` ops. This is the [new ResNet IR](https://gist.github.com/silvasean/5407aafb710d07612b7b5b92eabecebe), just to be able to look at a substantial sample of IR in the new style.
2021-05-05 05:42:50 +08:00
std::unique_ptr<OperationPass<FuncOp>> createReduceOpVariantsPass();
} // namespace Torch
/// Registers all Torch transformation passes.
void registerTorchPasses();
} // namespace NPCOMP
} // namespace mlir
#endif // NPCOMP_DIALECT_TORCH_TRANSFORMS_PASSES_H