commit | ec8dc02c60349abf5ac3617109d53ae18026b036 | [log] [tgz] |
---|---|---|
author | Ben Vanik <ben.vanik@gmail.com> | Mon Oct 24 13:40:40 2022 -0700 |
committer | Ben Vanik <ben.vanik@gmail.com> | Mon Oct 24 15:09:06 2022 -0700 |
tree | 6fd1b885ead687873f4777c2ee2e7e872296e40c | |
parent | 7b823f11cd4ddf029585a0c15d2af410721a8abd [diff] |
Adding iree_hal_device_profiling_begin/end API. This extends the device interface to expose the common stateful/global capture behavior used by GPU tooling. Most of these tools have some pretty tricky requirements (some must be initialized before devices and some after, and some only ever allow one device creation per process, etc) and the intent is that these APIs are only enabled and used in very specific debugging scenarios instead of a user-facing flow.
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.