Google Git
Sign in
opensecura / 3p / openxla / iree / 33e54309bab0a49aaf79f98b8cc69adb1bac0617
commit33e54309bab0a49aaf79f98b8cc69adb1bac0617[log] [tgz]
authorScott Todd <scott.todd0@gmail.com>Thu Jul 18 10:34:32 2024 -0700
committerGitHub <noreply@github.com>Thu Jul 18 10:34:32 2024 -0700
tree758d353caaf977bf885fd5c774d495155e2f47c0
parent7def2abea2dc750580aa13ddd9cda7f87d15e548 [diff]
Disable arm64 runtime build while runner availability is low. (#17927)

We currently only have a single `t2a-standard-8` runner for arm64
presubmit jobs. The jobs we have are:

job name | when does it run?
-- | --
`build_test_runtime :: arm64` | all PRs
`build_test_all_arm64` | opt-in, always enabled on LLVM integrate PRs

While the runtime job is always fast (~4 minutes), the 'all' (compiler)
job takes 15 minutes with a warm cache and 1h30m with a cold cache.
Having only a single runner results in presubmit jobs getting starved
for up to several times our presubmit target (20-30 minutes).

For now this just disables the runtime job entirely, trusting that
changes affecting it will be infrequent. I also explored options for
making it opt-in, but support for conditional jobs in matrices within
GitHub Actions is a complete mess. We could split this back out into a
non-matrix job is we want to go down that path.
1 file changed
tree: 758d353caaf977bf885fd5c774d495155e2f47c0
  1. .github/
  2. build_tools/
  3. compiler/
  4. docs/
  5. experimental/
  6. integrations/
  7. lib/
  8. llvm-external-projects/
  9. runtime/
  10. samples/
  11. tests/
  12. third_party/
  13. tools/
  14. .bazel_to_cmake.cfg.py
  15. .bazelignore
  16. .bazelrc
  17. .bazelversion
  18. .clang-format
  19. .dockerignore
  20. .git-blame-ignore-revs
  21. .gitattributes
  22. .gitignore
  23. .gitmodules
  24. .pre-commit-config.yaml
  25. .yamllint.yml
  26. AUTHORS
  27. BUILD.bazel
  28. CITATION.cff
  29. CMakeLists.txt
  30. configure_bazel.py
  31. CONTRIBUTING.md
  32. LICENSE
  33. MAINTAINERS.md
  34. README.md
  35. RELEASING.md
  36. 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 IREE Discord 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

Community meeting recordings: IREE YouTube channel

  • 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.