commit | 651630eb01be0529b49249d560c10fe625de683e | [log] [tgz] |
---|---|---|
author | Jakub Kuderski <kubak@google.com> | Fri Jun 09 23:34:46 2023 -0400 |
committer | GitHub <noreply@github.com> | Sat Jun 10 03:34:46 2023 +0000 |
tree | bd0922a503eac456c234192e0592f245a0e5fc1f | |
parent | fa3a220eb7fcd8c48f4d34737d81b3fa3b892129 [diff] |
[StableHLO] Port reduce canon patterns (#14045) Turns out that linalg lowering depends on these. The code is ported from equivalent folds and rewrite patterns in the mlir-hlo repo. The only notable difference is that this implementation fixes bugs with rewrite patterns performing op updates without going through the pattern rewriter. Also added a new test for the second noop case. Fixes: https://github.com/openxla/iree/issues/14042 Issue: https://github.com/openxla/iree/issues/12678
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.