commit | ec36a086261dcde6fcf2ea35e7f875ad62a26f46 | [log] [tgz] |
---|---|---|
author | Ben Vanik <ben.vanik@gmail.com> | Tue Aug 30 17:39:03 2022 -0700 |
committer | Ben Vanik <ben.vanik@gmail.com> | Tue Aug 30 21:16:40 2022 -0700 |
tree | 1fb8227181ea7e8266957b25b7b4b5d39818079e | |
parent | 2b8438fc190af8c3f9cf0a1ac3ccfda254ecb4be [diff] |
Adding iree_processor_yield() for use in spin loops. If we're going to spin we should at least be less bad about it. Most processors use this as a strong hint that a particular core is spinning in order to allow cooperatively-scheduled smt workloads a chance to run. It also introduces latency that can help lighten the memory system load that sitting and hammering the spin condition can cause.
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.