Google Git
Sign in
opensecura / 3p / openxla / iree / 9c9c74f083c1cd57467d139ca960aa68ffca766e
commit9c9c74f083c1cd57467d139ca960aa68ffca766e[log] [tgz]
authorStella Laurenzo <laurenzo@google.com>Wed Jun 23 18:00:07 2021 -0700
committerCopybara-Service <iree-copybara-bot@google.com>Wed Jun 23 18:01:27 2021 -0700
treec05c0c7a4bf50c02e327410b62c1f955799b3e0c
parent6e994d5435f3f6547bced0643a433670b894fa47 [diff]
Switch Softmax and LogSoftmax ops to be expansions instead of TF->HLO legalizations.

* The impetus for this was to enable a more effective dynamic shapes representation (staying high level vs doing manual shape massaging it better for code generation).
* The generated HLO is equivalent in the static shapes case.
* Side effect of making Softmax unranked compatible at the TF conversion level.
* The lower_tf.mlir test case was not actually piping to FileCheck. This has been fixed and a lot of unrelated test fixes are included (since this file had never effectively been tested).
* The tensorflow/transforms directory is pretty tortured. It feels like it should actually be half a dozen different directories. I found that there was no place to have not statically registered test passes, and tf_test_passes.td was namespaced/configured wrong for anything but saved model tests. I think I improved it and at least carved out a place for people to easily add more test passes (otherwise, no one will do proper unit testing -- which seems to be the situation that is prevalent). It's not great. This directory needs triage. Considering that the tests weren't even running before, I consider how I have it to be a minor improvement.

PiperOrigin-RevId: 381153956
1 file changed
tree: c05c0c7a4bf50c02e327410b62c1f955799b3e0c
  1. .github/
  2. bindings/
  3. build_tools/
  4. colab/
  5. docs/
  6. experimental/
  7. integrations/
  8. iree/
  9. scripts/
  10. third_party/
  11. .bazelignore
  12. .bazelrc
  13. .bazelversion
  14. .clang-format
  15. .gitignore
  16. .gitmodules
  17. .style.yapf
  18. .yamllint.yml
  19. AUTHORS
  20. BUILD.bazel
  21. CMakeLists.txt
  22. configure_bazel.py
  23. CONTRIBUTING.md
  24. LICENSE
  25. README.md
  26. SUBMODULE_VERSIONS.txt
  27. WORKSPACE
README.md

IREE: Intermediate Representation Execution Environment

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.

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.

Build Status

CI SystemBuild SystemPlatformArchitectureComponentStatus
KokoroBazelLinuxx86Corekokoro_status_bazel_linux_x86_core
KokoroCMake & BazelLinuxx86-swiftshaderIntegrationskokoro_status_cmake-bazel_linux_x86-swiftshader_integrations
KokoroCMake & BazelLinuxx86-turingIntegrationskokoro_status_cmake-bazel_linux_x86-turing_integrations
KokoroCMakeLinuxx86-swiftshaderCore + Bindingskokoro_status_cmake_linux_x86-swiftshader
KokoroCMakeLinuxx86-swiftshader-asanCore + Bindingskokoro_status_cmake_linux_x86-swiftshader-asan
KokoroCMakeLinuxx86-turingCore + Bindingskokoro_status_cmake_linux_x86-turing
KokoroCMakeAndroidarm64-v8aRuntime (build only)kokoro_status_cmake_android_arm64-v8a
BuildKiteCMakeAndroidarm64-v8aRuntimebuildkite-status-cmake-android-arm

Presentations and Talks

  • 2020-08-20: IREE CodeGen: MLIR Open Design Meeting Presentation (recording and slides)
  • 2020-03-18: Interactive HAL IR Walkthrough (recording)
  • 2020-01-31: End-to-end MLIR Workflow in IREE: MLIR Open Design Meeting Presentation (recording and slides)

License

IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.