commit | 61c19bf851ae782e8730b00779766ed8e567ff66 | [log] [tgz] |
---|---|---|
author | bjacob <benoitjacob@google.com> | Tue Jan 17 15:57:14 2023 -0500 |
committer | GitHub <noreply@github.com> | Tue Jan 17 15:57:14 2023 -0500 |
tree | d2acac0b33659695d51a9f5889d744642db084ab | |
parent | 496ff0726e27808b42ce7bbdff9df29fb454c8b2 [diff] |
Simplify the build system following the removal of old `matmul-to-mmt4d` pass (#11752) This is part 7/9 of #11755: Finish the transition to `--iree-flow-enable-data-tiling`. This pass used to take target information in a custom format as pass options. Now that it's gone, the build system logic that was generating these pass options can go. The main complication was the `#pass_options_variant#` placeholder that the build-system was rewriting with specific options for each target CPU features variant. That goes away, along with some debt that existed only to support that.
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.