Google Git
Sign in
opensecura / 3p / openxla / iree / 571f28a87ba01482c8b24b87e4d2a1909ca61f1c
commit571f28a87ba01482c8b24b87e4d2a1909ca61f1c[log] [tgz]
authorBen Vanik <ben.vanik@gmail.com>Mon Jun 05 13:06:14 2023 -0700
committerGitHub <noreply@github.com>Mon Jun 05 13:06:14 2023 -0700
tree1e53c589244c476715b848cb522f2328e5062f59
parentdf71589e19fe6de33cdd03577f5ce807d0d129cd [diff]
Adding task system utilization tracing. (#13941)

Adds one new plot per executor in a process showing a 0-100% utilization
value as tracked by the workers (vs the CPU usage sampled a much lower
rate).


![image](https://github.com/openxla/iree/assets/75337/7fc353d2-3fe8-4e33-8b60-056751231381)

Inspecting the area under/over the curve is an easy way to spot
dispatches that could have improved distribution:

![image](https://github.com/openxla/iree/assets/75337/1383ad5d-c802-43ce-9352-e584eb040921)
(here 2x of the wall time is only 1x the utilization, meaning with
perfect distribution we could go 2x faster by 2xing the utilization)
5 files changed
tree: 1e53c589244c476715b848cb522f2328e5062f59
  1. .devcontainer/
  2. .github/
  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. .bazel_to_cmake.cfg.py
  16. .bazelignore
  17. .bazelrc
  18. .bazelversion
  19. .clang-format
  20. .dockerignore
  21. .gitignore
  22. .gitmodules
  23. .pylintrc
  24. .style.yapf
  25. .yamllint.yml
  26. AUTHORS
  27. BUILD.bazel
  28. CITATION.cff
  29. CMakeLists.txt
  30. configure_bazel.py
  31. CONTRIBUTING.md
  32. LICENSE
  33. README.md
  34. 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.