commit | d110d1b1a30da5b9134b6cb420a7c937c8933fe2 | [log] [tgz] |
---|---|---|
author | qcolombet <quentin.colombet@gmail.com> | Thu Dec 01 14:11:12 2022 -0800 |
committer | GitHub <noreply@github.com> | Thu Dec 01 14:11:12 2022 -0800 |
tree | c8811906b0f37549c1aad510b49099771271030d | |
parent | 0169788c17f788f3963219b6bd8600da5956eda1 [diff] | |
parent | 8b19b3c015e4f4c3d3324d6d4a27673d1ec0e5f8 [diff] |
Adopt the new memref lowering process (#11261) Subviews and other view like operations will soon require to be expanded via expand-strided-metadata before being able to be converted to the LLVM dialect (convert-memref-to-llvm). This change is a little bit ahead of the LLVM open source curve because the expansion is not yet required, but it doesn't hurt to do right now. By adopting this change early we avoid holding the LLVM integration when this requirements will be enforced (i.e., when https://reviews.llvm.org/D136377 lands in LLVM.)
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.