| commit | 73b04d354f37168b4a4225418525ffd11579d7c9 | [log] [tgz] |
|---|---|---|
| author | Han-Chung Wang <hanchung@google.com> | Fri Sep 01 14:40:27 2023 -0700 |
| committer | GitHub <noreply@github.com> | Fri Sep 01 14:40:27 2023 -0700 |
| tree | 0ca21b914325eb5c6d84ba0b690c4acd4bd0b67f | |
| parent | fe8f79e930f708af2121b1241474d6229cb5593e [diff] |
Enable ConstEval for CPU data tiling path. (#14792) - Moves SetEncoding pass to GlobalOptimization stage, and renames `iree-flow-enable-data-tiling` to `iree-opt-enable-data-tiling` - Introduces MaterializeHomogeneousEncodings pass to GlobalOptimization phase. It materializes encodings to physicacl ops when there is a single executable. - Make CPU materialization passes take optional executable attributes. They look into the attributes if they are passed. Otherwise, they look into existing attributes. Fixes https://github.com/openxla/iree/issues/11360
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.