commit | 74b04b7099d41e6cf71ee5b54ab6cc0a45e425a3 | [log] [tgz] |
---|---|---|
author | Stella Laurenzo <stellaraccident@gmail.com> | Wed Mar 02 10:21:11 2022 -0800 |
committer | GitHub <noreply@github.com> | Wed Mar 02 10:21:11 2022 -0800 |
tree | 0ba870e96b98a1cbfa71dc807b41361aeae6af75 | |
parent | 115b8d46a71d64a6dede653d3cad5821f03b5e6b [diff] |
Rework cmake test deps, target selection and presets. (#8423) * Rework cmake test deps, target selection and presets. This patch does a few things: * Marks all targets under iree/test/ as EXCLUDE_FROM_ALL. * Configures check-tests to add a dependency to the global iree-test-deps target. * Added a seperate build step for CIs to build iree-test-deps. * Reworks compiler target selection to distinguish between "default" targets and those not built by default. * Fine-grained LLVM_TARGETS_TO_BUILD are added based on the IREE targets. * lld is built if CPU targets are enabled. * CPU targets are expanded from a new IREE_CPU_LLVM_TARGETS option (defaults to what we had previously hard-coded).
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.