Google Git
Sign in
opensecura / 3p / openxla / iree / fef4534bb3a92cf82dfe8ca2960ed2a66e3f1418
commitfef4534bb3a92cf82dfe8ca2960ed2a66e3f1418[log] [tgz]
authorStella Laurenzo <laurenzo@google.com>Fri Mar 03 18:09:43 2023 -0800
committerGitHub <noreply@github.com>Fri Mar 03 18:09:43 2023 -0800
tree57de32b69c7cd1ecf9615090b0810fa78d1cc613
parent98a9105433df150590214b3e9e5a3c998ee979a9 [diff]
Build libIREECompiler.so in bazel. (#12507)

* Moves the deeply nested build rule to lib/. Unlike CMake, Bazel offers
no control on where things are output in the tree (or name), so we just
put the binary target in the place where CMake puts it, preserving the
directory layout of artifacts between them. This results in a small
deviation on where this target is actually declared (lib/ in bazel and
iree/compiler/API2:SharedImpl in CMake) but the same output path.
* Wires up the loader_test in bazel and makes it able to find the shared
library data dependency.
* Extends bazel_to_cmake to respect the `skip-bazel_to_cmake` tag to
make it skip conversion of common targets. I've needed this for some
time and I expect will let us normalize more build files that only
differ by a target or two.
* I've confirmed that this works in Google's internal build system (with
appropriate buildozer path changes and such).
3 files changed
tree: 57de32b69c7cd1ecf9615090b0810fa78d1cc613
  1. .github/
  2. benchmarks/
  3. build_tools/
  4. compiler/
  5. docs/
  6. experimental/
  7. integrations/
  8. lib/
  9. llvm-external-projects/
  10. runtime/
  11. samples/
  12. tests/
  13. third_party/
  14. tools/
  15. .bazelignore
  16. .bazelrc
  17. .bazelversion
  18. .clang-format
  19. .dockerignore
  20. .gitignore
  21. .gitmodules
  22. .pylintrc
  23. .style.yapf
  24. .yamllint.yml
  25. AUTHORS
  26. BUILD.bazel
  27. CITATION.cff
  28. CMakeLists.txt
  29. configure_bazel.py
  30. CONTRIBUTING.md
  31. LICENSE
  32. README.md
  33. 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.

CI Status

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.

Architecture Overview

IREE Architecture IREE Architecture

See our website for more information.

Presentations and Talks

  • 2021-06-09: IREE Runtime Design Tech Talk (recording and slides)
  • 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.