commit | 05a8804011162613bced92c776d390d6624b1502 | [log] [tgz] |
---|---|---|
author | Ben Vanik <benvanik@google.com> | Wed Jul 28 10:10:04 2021 -0700 |
committer | GitHub <noreply@github.com> | Wed Jul 28 10:10:04 2021 -0700 |
tree | 4553d382c12a23f7f6f2893f1b2c832335fb5fb4 | |
parent | 2b437729b5fa93a4c428b2d7183b8d86d79750b1 [diff] |
Adding -iree-flow-simplify-variable-accesses pass. (#6565) Since there's nothing like this upstream (I know about) this is a naive result of an afternoon of hacking to solve our immediate problem (variable accesses interleaved with logic we want to dispatch). This only operates within basic blocks and does no fancy dataflow analysis leaving a lot of potential optimizations on the table. Programs are still correct if this pass is not used but for any model with a lot of variable updates it's a big win.
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!
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.