Google Git
Sign in
opensecura / 3p / openxla / iree / 08237ac1c7bec3435cd7c626802dfad1b91bbd0e
commit08237ac1c7bec3435cd7c626802dfad1b91bbd0e[log] [tgz]
authorBen Vanik <ben.vanik@gmail.com>Mon May 11 13:14:22 2020 -0700
committerCopybara-Service <copybara-worker@google.com>Mon May 11 13:16:03 2020 -0700
tree4b9fe9d1eb4baa6056b56babf047cd94e5066b60
parente76bf09c16b6a0253f9f8069f4b5f1033d414015 [diff]
Merging API cleanup branch

This cleans up most of the compiler warnings we have and adds string parsing/formatting to the C API. This will allow us to replace the existing legacy types like iree/base/shaped_buffer.h and iree/base/shape.h and the glue in vm_util.h with the real C versions. The changes here result in a smaller compiled codesize (less giant template type expansion) and will make things really easy to use from java/etc. Most of the existing shaped buffer tests were ported over though with the new code organization far less duplication was required (and someone wasn't trying to go for readability at the time, which helps).

There's also some iteration on the C++ binding (that relies only on the C API). More to come on that.

Closes https://github.com/google/iree/pull/1862

PiperOrigin-RevId: 310977927
22 files changed
tree: 4b9fe9d1eb4baa6056b56babf047cd94e5066b60
  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. CONTRIBUTING.md
  21. LICENSE
  22. README.md
  23. repo_utils.bzl
  24. SUBMODULE_VERSIONS
  25. 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 ActionsBazelLinuxCoreWorkflow History
GitHub ActionsBazelLinuxBindingsWorkflow History
GitHub ActionsBazelLinuxIntegrationsWorkflow History
GitHub ActionsBazelLinuxOtherWorkflow History
KokoroBazelLinuxCorekokoro-status-bazel-linux
KokoroCMakeLinuxCore + Bindingskokoro-status-cmake-linux

License

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