| commit | d5a9b1b86f244bbe3257d542d699eae344ad1c00 | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Mon Mar 06 12:06:27 2023 -0800 |
| committer | GitHub <noreply@github.com> | Mon Mar 06 20:06:27 2023 +0000 |
| tree | db439e7f5878a5de38d61fd403b199885658d061 | |
| parent | 70e6e52c9ce84c82f5409c9836a3926d2fb98221 [diff] |
Adding compilation reentrancy tests and new HAL pipeline phases. (#12503) Two new `--compile-to=` phases are supported: - `executable-sources`: run just past interface materialization where `hal.executable` ops with target configurations are present. - `executable-targets`: run just past executable translation where `hal.executable.variant` ops have been lowered to their final MLIR form before linking and serialization (LLVM dialect, SPIR-V dialect, etc). New tests are added that demonstrate and verify that iree-opt pipelines can be run piecewise to produce a final output and that `--compile-to=` at any particular phase can be passed back in and lowered down to a final output. A few passes were tweaked to ensure these tests pass.
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.