| commit | a6a56a97ae070c2a1a290841e99ec1a396e99101 | [log] [tgz] |
|---|---|---|
| author | Ian Wood <75152913+IanWood1@users.noreply.github.com> | Tue May 28 12:35:45 2024 -0700 |
| committer | GitHub <noreply@github.com> | Tue May 28 12:35:45 2024 -0700 |
| tree | 2c43249cc6745e52a465d9c35f830972fc620be1 | |
| parent | 3d1364e1b184492165db2a1bf3556b281e8fcea3 [diff] |
Add `LinalgFusionInterface` to support fusion for linalg_ext ops (added `scatter` and `reverse`) (#17428) `LinalgFusionOpInterface` allows for fusion of both `Linalg` and `LinalgExt` operations. The new interface provides access to methods essential for performing fusion, allowing existing fusion logic to be used with `LinalgExt` operations. As noted in #17392, it probably makes sense to move this into the `TilingInterface` + probably make it a bit more abstracted #### Changes - **`LinalgFusionOpInterface`**: Interface for fusion operations for both `Linalg` and `LinalgExt` ops. - Implements methods to access indexing maps (or null - **Implementation for Linalg Ops**: The interface is implemented for standard Linalg operations by forwarding to preexisting methods (e.g `getIndexingMaps()`). No changes to the ops themselves. - **Implementation for LinalgExt Ops**: The interface currently only implemented for `iree_linalg_ext.scatter/reverse`. --------- Signed-off-by: Ian Wood <ianwood2024@u.northwestern.edu>
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.