Google Git
Sign in
opensecura / 3p / openxla / iree / 4e45a77fe10e31d0b48e978d8c895fab025669ef
commit4e45a77fe10e31d0b48e978d8c895fab025669ef[log] [tgz]
authorMarius Brehler <marius.brehler@iml.fraunhofer.de>Tue Jun 02 14:04:18 2020 -0700
committerCopybara-Service <copybara-worker@google.com>Tue Jun 02 14:06:43 2020 -0700
treeb39f64db2de29c52fe74c84d5b829e0ae82abb83
parent99fcd424092658bc9aa4d973d0cc0c6d682427ea [diff]
Add mlir-emitc submodule and extend CMake configuration

This add an EmitC dialect (forked from https://reviews.llvm.org/D76571) which is available under *Apache License v2.0 with LLVM Exceptions*. The idea is to make progress on #1173 and to utilize and extend the EmitC dialect proposed by @jpienaar for this.

Building the dialect can be enabled by `IREE_ENABLE_EMITC` in CMake. A Bazel configuration is not yet available. No additional LLVM/MLIR deps are pulled in, since `IREE_ENABLE_EMITC` results in using the `tools/init_mlir_{dialects,passes}.h` headers. No dep on the IREE target itself is introduced, instead the MLIR deps are "replicated". Also not super clean, this avoids a circular dependency and allows to avoid unnecessary dependencies (eg. on AVX512 and NVVMIR).

The final goal is to push EmitC upstream or to integrate it into IREE (at least). I am further happy to grant write access to the [mlir-emitc](https://github.com/iml130/mlir-emitc/) repo for outside collaborators as long as this doesn't prevent pushing towards MLIR or to integrate it into IREE.

Closes https://github.com/google/iree/pull/2060

PiperOrigin-RevId: 314400071
4 files changed
tree: b39f64db2de29c52fe74c84d5b829e0ae82abb83
  1. .github/
  2. bindings/
  3. build_tools/
  4. colab/
  5. docs/
  6. experimental/
  7. integrations/
  8. iree/
  9. kokoro/
  10. scripts/
  11. third_party/
  12. .bazelignore
  13. .bazelrc
  14. .bazelversion
  15. .clang-format
  16. .gitignore
  17. .gitmodules
  18. BUILD.bazel
  19. CMakeLists.txt
  20. configure_bazel.py
  21. CONTRIBUTING.md
  22. LICENSE
  23. README.md
  24. repo_utils.bzl
  25. SUBMODULE_VERSIONS
  26. WORKSPACE
README.md

IREE: Intermediate Representation Execution Environment

IREE (Intermediate Representation Execution Environment, pronounced as “eerie”) is an MLIR-based end-to-end compiler that lowers ML models to a unified IR optimized for real-time mobile/edge inference against heterogeneous hardware accelerators. IREE also provides flexible deployment solutions for the compiled ML models.

Project Status

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 logisitics. 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!

Communication Channels

Related Project Channels

  • MLIR topic within LLVM Discourse: IREE is enabled by and heavily relies on MLIR. IREE sometimes is referred to in certain MLIR discussions. Useful if you are also interested in MLIR evolution.

Getting Started

For development, IREE supports both Bazel and CMake on Windows and Linux. We are working on enabling macOS support. For deployment, IREE aims to additionally cover Android and iOS.

Please see the Getting Started pages on IREE's documentation hub to configure, compile, and run IREE in your favorite development environment!

Documentation and Talks

IREE hosts all its documentation and project status dashboards on GitHub Pages. We are still building up the website; please feel free to create issues for the documentation you'd like to see!

We also have some public talks that explain IREE's concepts and architecture:

  • 2020-03-18: Interactive HAL IR Walkthrough (Ben Vanik and core team) (recording)
  • 2020-01-31: End-to-end MLIR Workflow in IREE (recording and slides)

Architecture and Goals

IREE adopts a holistic approach towards ML model compilation: the IR produced contains both the scheduling logic, required to communicate data dependencies to low-level parallel pipelined hardware/API like Vulkan, and the execution logic, encoding dense computation on the hardware in the form of hardware/API-specific binaries like SPIR-V.

The architecture of IREE is best illustrated by the following picture:

IREE Architecture

Being compilation-based means IREE does not have a traditional runtime that dispatches “ops” to their fat kernel implemenations. What IREE provides is a toolbox for different deployment scenarios. It scales from running generated code on a particular API (such as emitting C code calling external DSP kernels), to a HAL (Hardware Abstraction Layer) that allows the same generated code to target multiple APIs (like Vulkan and Direct3D 12), to a full VM allowing runtime model loading for flexible deployment options and heterogeneous execution.

IREE aims to

  • Support advanced models on mobile/edge devices. Dynamic shapes, dynamic flow control, dynamic multi-model dispatch, streaming models, tree-based search algorithms, and other are all good examples of exciting ML evolution. We are trying to build IREE from the ground-up to enable these models and run them efficiently on modern hardware, especially on mobile/edge devices.
  • Demonstrate MLIR‘s ability to develop non-traditional ML compiler backends and runtimes. MLIR enables IREE’s holistic approach of focusing on the math being performed and how that math is scheduled rather than graphs of “ops”.
  • Embrace standard-based ML via Vulkan. The graphics world is shifting towards favoring mordern explicit APIs for performance and predictability and Vulkan is emerging as the “compatibility” layer. We would love to allow hardware vendors to be able to make ML efficient on their hardware without the need for bespoke runtimes and special access. We also would love to let developers and users utilize all the hardware available on as many platforms as possible.

Roadmap and Milestones

IREE is still at its early stage; we have lots of exciting future plans. Please check out the long-term design roadmap and short-term focus areas.

We use GitHub Projects to track various IREE components and GitHub Milestones for major features and quarterly plans. Please check out for updated information.

Build Status

CI SystemBuild SystemPlatformComponentStatus
GitHub ActionsBazelLinuxIntegrationsWorkflow History
GitHub ActionsBazelLinuxOtherWorkflow History
KokoroBazelLinuxCore + Bindingskokoro-status-bazel-linux
KokoroCMakeLinuxCore + Bindingskokoro-status-cmake-linux

License

IREE is licensed under the terms of the Apache license. See LICENSE for more information.