commit | 70e6e52c9ce84c82f5409c9836a3926d2fb98221 | [log] [tgz] |
---|---|---|
author | Nicolas Vasilache <nicolasvasilache@users.noreply.github.com> | Mon Mar 06 20:22:48 2023 +0100 |
committer | GitHub <noreply@github.com> | Mon Mar 06 20:22:48 2023 +0100 |
tree | ae6c12cc17fd056da58eb4a66b2ab0c63882f3cd | |
parent | 8007d749733c5109cddc323eb8b52a5f2a0bad9f [diff] |
Add additional options to the ApplyPatternsOp (#12519) The following upstream options are added to the ApplyPatternsOp: 1. rank-reduction of linalg ops via reshapes 2. pack/unpack propagation 3. split bubble_expand from bubble_collapse as these patterns exhibit an interference behavior 4. patterns for greedy fusion of linalg ops All these are extensively tested upstream, this PR provides the plumbing to be used with the transform dialect.
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.