Google Git
Sign in
opensecura / 3p / openxla / iree / 5e6361321b7dd12d486bf92b10fe34d462c38cf3
commit5e6361321b7dd12d486bf92b10fe34d462c38cf3[log] [tgz]
authorrsuderman <5508949+rsuderman@users.noreply.github.com>Thu Aug 27 11:58:08 2020 -0700
committerCopybara-Service <iree-copybara-bot@google.com>Thu Aug 27 11:59:30 2020 -0700
tree0eeff80cc9411bae8bec376c82bfb65dba83e857
parent2013dec1dc8ddf2c271b18ebd123e742fca23362 [diff]
Merge main -> google

* aa8d1c0f Enable simple.mlir test for iree-benchmark-module on vulkan (#3016)
* 6db4e7bd [vulkan] Release timepoint fences more aggressively when possible (#2800)
* a1365d33 [vulkan] Do not request timeline semaphore if not available (#2904)
* a38c8905 Add more type support to model builder matmul benchmark. (#2977)
* a293ca7b Fix hyperlink to getting started docs on python page. (#3015)
* b022e70a Release inputs before closing the session. (#3004)
* f1678df2 Dynamicly register benchmark for entry_function with name BM_{entry_function} ..
* 6282700e Expand the tf_module_to_compiler_module API (#3009)
* f7e561a6 Merge pull request #3006 from rsuderman/google-to-main
* 8341d71c Explicitly insert dialects in conversion passes (#3002)
* b7c2b60e Fix format by changing to LLVM style (#3008)
* 4286f171 Merge branch 'main' into google-to-main
* f0a07f63 Allow iree.placeholder as an op between splittable ops. (#2999)
* 6bd3b1dc Use hidden visibility for all symbols by default (#2997)
* d6500826 VMLA Dynamic Iota support with Shape dialect work. (#2965)
* c724ee45 Add function to hide SavedModel roundtrip (#2995)
* 2fedce64 Merge pull request #2996
* c5f7030b Merge branch 'main' into google-to-main
* cf3211d9 [vulkan] Reset TimePointFence status when releasing back to pool (#2905)
* ebc6a833 Add lint action to check for tabs (#2984)
* 932339ce Merge pull request #2964 from silvasean/add-dynamic-dot-example
* df727ae3 Integrate MLIR-EmitC at iml130/mlir-emitc@560cd8c (#2990)
* e824d364 Refactor for explicit dialect registration (#2978)
* 38b7d2cf Allow ModelRunner to receive an array of extra symbols available during JITing..
* 264a97df Fuse linalg.tensor_reshape operations with hal.interface* operations. (#2973)
* 0e3c7373 Fold flow.tensor.update when all operands are constant (#2982)
* c7a21c2a Merge pull request #2983 from rsuderman/google-to-main
* fd55a860 Add a dynamically shaped mhlo.dot lowering example

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/iree/pull/3018 from rsuderman:main-to-google 4a9ea0209493968d189cb7099f51292422690eb0
PiperOrigin-RevId: 328784816
16 files changed
tree: 0eeff80cc9411bae8bec376c82bfb65dba83e857
  1. .github/
  2. bindings/
  3. build_tools/
  4. colab/
  5. docs/
  6. experimental/
  7. integrations/
  8. iree/
  9. packaging/
  10. scripts/
  11. third_party/
  12. .bazelignore
  13. .bazelrc
  14. .bazelversion
  15. .clang-format
  16. .gitignore
  17. .gitmodules
  18. .style.yapf
  19. .yamllint.yml
  20. BUILD.bazel
  21. CMakeLists.txt
  22. configure_bazel.py
  23. CONTRIBUTING.md
  24. LICENSE
  25. README.md
  26. repo_utils.bzl
  27. SUBMODULE_VERSIONS
  28. 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 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!

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 implementations. 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 modern 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 SystemPlatformArchitectureComponentStatus
KokoroBazelLinuxx86Corekokoro_status_bazel_linux_x86_core
KokoroBazelLinuxx86Bindingskokoro_status_bazel_linux_x86_bindings
KokoroBazelLinuxx86-swiftshaderIntegrationskokoro_status_bazel_linux_x86-swiftshader_integrations
KokoroBazelLinuxx86-turingIntegrationskokoro_status_bazel_linux_x86-turing_integrations
KokoroCMakeLinuxx86-swiftshaderCore + Bindingskokoro_status_cmake_linux_x86-swiftshader
KokoroCMakeLinuxx86-turingCore + Bindingskokoro_status_cmake_linux_x86-turing
KokoroCMakeAndroidarm64-v8aRuntime (build only)kokoro_status_cmake_android_arm64-v8a
BuildKiteCMakeAndroidarm64-v8aRuntimebuildkite-status-cmake-android-arm

License

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