| commit | 853dd6ead922cc0115beddc3d74b88af8b437172 | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Thu Sep 01 10:51:11 2022 -0700 |
| committer | Ben Vanik <ben.vanik@gmail.com> | Fri Sep 02 10:34:59 2022 -0700 |
| tree | ff249935814b4157ae3a8a76479216b8a848be93 | |
| parent | 4b4b8546e7b8731d94dc32a61931baf51c7a9036 [diff] |
Adding cpu_data.h and CPU data queries into iree/base/internal/cpu.h. This is like the linux hwcaps in that it's a subset of the architectural registers that are useful for us and available to query on all of our platforms. Since the compiler will emit code that uses this data it is defined as part of the stable schema and sharable across the compiler, builtin libraries, and runtime. Only two sample aarch64 bits fetched on linux are supported. Additional platforms and architectures can be added as needed.
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.