commit | 3b7e2746a26ae322e48ed44694df0b8c5ce59dc1 | [log] [tgz] |
---|---|---|
author | bjacob <benoitjacob@google.com> | Tue Jul 19 13:15:35 2022 -0400 |
committer | GitHub <noreply@github.com> | Tue Jul 19 13:15:35 2022 -0400 |
tree | 7677f2c67fc643899e790d6ffe0df987c59f525c | |
parent | 7fa5674492cc00b8dbe23626f78c08e2ee09c809 [diff] |
Tweaks to atomics in iree_task_* - use acquire/release consistently These atomics were already accessed with acquire/release order at various places. I audited the places where they were accessed other other memory orders and changed them as follows: * Some places used seq_cst but that didn't seem necessary. Changed to acquire/release, and in one case relaxed (for the comparison-failure case in a compare_exchange as the loaded value was unused). * Some places used relaxed but it wasn't immediately clear that that was sufficient ordering. Changed to acquire/release - we can keep them relaxed if that's performance-critical and you can see why relaxed was sufficient.
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.