commit | 8d56830ec9fc0e0590bda1c787a83f1b3d7d5121 | [log] [tgz] |
---|---|---|
author | Geoffrey Martin-Noble <gcmn@google.com> | Fri Dec 03 10:32:48 2021 -0800 |
committer | GitHub <noreply@github.com> | Fri Dec 03 10:32:48 2021 -0800 |
tree | 7e703d9ece5360b488308090e25aa2e58ad0308b | |
parent | d003d6c449261f9cb741ebb43d26b18d851181ea [diff] |
Add big-core multi-threaded benchmarks (#7807) This adds multi-threaded big-core benchmarks for the full configuration matrix. We are optimizing performance primarily on big cores right now. This also includes switching our single VMVX benchmark to use big cores instead of little. This benchmark is mostly for reference and big cores are more useful for this, plus the benchmark will take less time. Note that this will mean we are starting a new series for this and won't be able to easily compare with previous history. I don't think we care. Fixes https://github.com/google/iree/pull/7807
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.