commit | 3fee83df17d333f544e65284466ba190f8d3b90c | [log] [tgz] |
---|---|---|
author | Oleksandr "Alex" Zinenko <zinenko@google.com> | Fri Jan 13 12:55:40 2023 +0100 |
committer | GitHub <noreply@github.com> | Fri Jan 13 12:55:40 2023 +0100 |
tree | 1f9c1be9e5dc1f480a46423d03cd5c87a7637a22 | |
parent | 81d8dd68369cb2db493d0275bbd32278a55e920f [diff] |
Commonolize implementation of transform interpreters (#11810) Factor out the common components of TransformDialectInterpreterPass in Codegen, in iree-dialects, and of DispatchWithTransformDialect into a base class template that lives in iree-dialects. This includes the logic necessary for injecting transforms from a file, maintaining those alive in a separate module, debug targeting via attributes, and transform module identification in the IR. It is currently used for IREE codegen, and will be reused for Flow and standalone interpreter.
IREE (Intermediate Representation Execution Environment, pronounced as “eerie”) is an MLIR-based end-to-end compiler and runtime that lowers Machine Learning (ML) models to a unified IR that scales up to meet the needs of the datacenter and down to satisfy the constraints and special considerations of mobile and edge deployments.
See our website for project details, user guides, and instructions on building from source.
IREE is still in its early phase. We have settled down on the overarching infrastructure and are actively improving various software components as well as project logistics. It is still quite far from ready for everyday use and is made available without any support at the moment. With that said, we welcome any kind of feedback on any communication channels!
See our website for more information.
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.