| commit | a2ed5db42ffd7c457c227a9eed7ba6d8f2c3c9b7 | [log] [tgz] |
|---|---|---|
| author | Geoffrey Martin-Noble <gcmn@google.com> | Tue Dec 21 14:50:57 2021 -0800 |
| committer | GitHub <noreply@github.com> | Tue Dec 21 14:50:57 2021 -0800 |
| tree | d4da003bce54bc2153ecc96d71248c805763ce96 | |
| parent | 776d7e6072fd7ca42cab03fd68e9a04f5aeacebb [diff] |
Disable less-used benchmarks (#7927) See discussion at https://github.com/google/iree/pull/7807#issuecomment-985790882 and onwards. This disables a number of benchmarks that aren't super useful, and in particular aren't worth delaying presubmit (and in some cases per-commit postsubmit) runs. 1. All little-core experimental-flags benchmarks: we are not currently optimizing little-core. 2. 2 and 3 thread CPU benchmarks. 1 and 4 threads give us basically everything we need. Drops benchmarking phone time from [54 minutes](https://buildkite.com/iree/iree-benchmark/builds/1703) to [35 minutes](https://buildkite.com/iree/iree-benchmark/builds/1706)
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.