Google Git
Sign in
opensecura / 3p / openxla / iree / 247de366d03d7a4dc0eb7a960e089abaa48a496d
commit247de366d03d7a4dc0eb7a960e089abaa48a496d[log] [tgz]
authormaxbartel <bartel@roofline.ai>Tue Jun 25 17:25:30 2024 +0200
committerGitHub <noreply@github.com>Tue Jun 25 17:25:30 2024 +0200
tree8405e79fcdc0d5cf8f0693d25b2f21ab52b0bc21
parent1f69b857fffb2367682b436684cd9868329cd109 [diff]
[Python API] Fix python api for bytecode (#17343)

This fixes an issue seen in https://github.com/iree-org/iree/pull/17278.
MLIR bytecode can have a zero as the last byte depending on the IR. If
this happens by accident parsing will fail. This PR checks if a buffer
begins with the _magic number_ from
https://mlir.llvm.org/docs/BytecodeFormat/#magic-number and sets
zero-termination to false if it does.

However I could not generate MLIR bytecode that ends with a zero other
than the one in the PR. Even if I save the IR used in textual format and
parse it again, some additional bytes are appended and it is not zero
terminated anymore. I think this is because of some behavior in TF.

Still after reading a bit through
https://mlir.llvm.org/docs/BytecodeFormat I think the check implemented
in this PR is the correct behavior for bytecode.

---------

Signed-off-by: Maximilian Bartel <bartel@roofline.ai>
6 files changed
tree: 8405e79fcdc0d5cf8f0693d25b2f21ab52b0bc21
  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. .git-blame-ignore-revs
  22. .gitattributes
  23. .gitignore
  24. .gitmodules
  25. .pre-commit-config.yaml
  26. .yamllint.yml
  27. AUTHORS
  28. BUILD.bazel
  29. CITATION.cff
  30. CMakeLists.txt
  31. configure_bazel.py
  32. CONTRIBUTING.md
  33. LICENSE
  34. MAINTAINERS.md
  35. README.md
  36. RELEASING.md
  37. 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.