commit | 402110945d4424f89fba2bd15633772624f3ba50 | [log] [tgz] |
---|---|---|
author | Max191 <44243577+Max191@users.noreply.github.com> | Wed May 15 10:15:43 2024 -0700 |
committer | GitHub <noreply@github.com> | Wed May 15 13:15:43 2024 -0400 |
tree | 3e0e3caaa661c6c21f963b2ebbb9ddf48bd05ad0 | |
parent | 0260947c60b374bff718545290ad693f3111646b [diff] |
[Winograd] Add filtering by annotations for Winograd rewrites (#17332) This PR adds filtering functionality to Winograd conv rewrites based on a `__winograd_conv` attribute. Convolutions are expected to be annotated with this attribute before the pass invocation, most likely by a transform script called from `iree-preprocessing-transform-interpreter` as preprocessing. Since Winograd affects numerical results, and the performance benefit is different for different shapes, it is usually necessary to select specific shapes to use Winograd. This PR enables users to make this selection based on shapes or parameters of specific convolutions.
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.
Community meeting recordings: IREE YouTube channel
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.