Google Git
Sign in
opensecura / 3p / openxla / iree / 5c38bcc7068f486733584bd251c9596059c31b7f
commit5c38bcc7068f486733584bd251c9596059c31b7f[log] [tgz]
authorLei Zhang <antiagainst@google.com>Mon Jun 05 17:29:11 2023 -0400
committerGitHub <noreply@github.com>Mon Jun 05 14:29:11 2023 -0700
tree2019d84f5022c4c79eb2bace9aa94fa68f99fd21
parent2544efec2f33bcbd12d1a07e1b8eda354b7d0d3c [diff]
[cuda] Implement basics for a CUDA HAL driver rewrite (#13942)

This commit starts a CUDA HAL driver rewrite under `experimental/`.
We create a new `cuda2/` directory to host the new code to avoid
interrupting the current CodeGen development.

This commit just brings in the basics for boot up a new HAL driver,
including dynamic symbols management, error status management, and
IREE HAL driver implementation. Most of the code is directly copied
from existing HAL driver, with noticeable changes:

* Split CUDA and NCCL dynamic symbols into separate structures for
  better organziation and allowing optionality.
* Fleshed out CUDA error to IREE status conversions.
* Better organized code blocks and improved error messages and
  various comments.

Building this commmit with `-DIREE_EXTERNAL_HAL_DRIVERS=cuda2`,
we can have `tools/iree-run-module --dump_devices` showing `cuda2`
devices, in parallel to the existing CUDA one.

Progress towards https://github.com/openxla/iree/issues/13245
14 files changed
tree: 2019d84f5022c4c79eb2bace9aa94fa68f99fd21
  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.