commit | 97710b3c51ba0d82b556e24e462963085398bad1 | [log] [tgz] |
---|---|---|
author | Quinn Dawkins <quinn.dawkins@gmail.com> | Mon Sep 09 10:22:53 2024 -0400 |
committer | GitHub <noreply@github.com> | Mon Sep 09 10:22:53 2024 -0400 |
tree | 7db98824d27c8c4f9af47c208179751cfe6ed057 | |
parent | 6c9aad0f7836f459ac89705f1deec326bae7b919 [diff] |
[Codegen] Add patterns for folding away no-op slices (#18419) Adds a pattern to fold away no-op slices to OptimizeTensorInsertExtractSlices that calls an upstream utility that uses the ValueBoundsInterface to determine whether the sizes of a `tensor.extract_slice`/`tensor.insert_slice` are no-ops. This is kept out of a static canonicalizer because the ValueBoundsInterface can be quite expensive due to walking up use-def chains indefinitely. This folding is a pass option because some other pipelines are sensitive to insert/extract_slice structure.
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
Package | Release status |
---|---|
GitHub release (stable) | |
GitHub release (nightly) | |
Python iree-compiler | |
Python iree-runtime |
Host platform | Build status |
---|---|
Linux | |
macOS | |
Windows |
For the full list of workflows see https://iree.dev/developers/general/github-actions/.
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.