commit | 886ac3e269454180b149abd68e230ca079a3744a | [log] [tgz] |
---|---|---|
author | bjacob <benoitjacob@google.com> | Tue Mar 07 14:25:01 2023 -0500 |
committer | GitHub <noreply@github.com> | Tue Mar 07 14:25:01 2023 -0500 |
tree | df37444e6154c5a0aaaf15a8ecb684d9c35ec2d8 | |
parent | f1bbc5703cd907133b885e5807a09bd1afd5d3b8 [diff] |
Centralize CPU features, fix `iree_cpu_lookup_data_by_key`, add a `iree-cpuinfo` tool (#12498) The starting point of this PR was that I realized that I had forgotten to update `iree_cpu_lookup_data_by_key`. That sent me looking for a way to have it automatically sync'd with the rest of the code, resulting in the present `.inl` approach. As a bonus, I added a `iree-cpuinfo` tool, also automatically sync'd with the `.inl` and just a few lines of impl. This is a quick debugging tool allowing to answer quickly the question "which CPU features are we actually detecting on this machine". Obviously the point is not provide the best CPU feature detection tool, the point is that it's by construction bug-for-bug equivalent to IREE's actual CPU feature detection.
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.