Google Git
Sign in
opensecura / 3p / openxla / iree / 13e6b7ea369945c63e5a0c9eadf56b716e81c40e
commit13e6b7ea369945c63e5a0c9eadf56b716e81c40e[log] [tgz]
authorBen Vanik <ben.vanik@gmail.com>Mon Jul 08 09:40:30 2024 -0700
committerGitHub <noreply@github.com>Mon Jul 08 16:40:30 2024 +0000
treee42d5eec61269fc0e32841c7b6b5563abce20863
parentdd7d4a1441b4be21db2b7ba038bf20d74899c13f [diff]
Removing nested command buffers and adding indirect execution. (#17724)

The compiler is unlikely to need nested execution and the concept of
nested command buffers makes HAL driver implementation trickier. Instead
now all command buffers have a single type which may optionally include
indirect bindings. HAL devices now optionally take a binding table per
command buffer to use when scheduling it. The compiler now has a
`hal.device.queue.execute.indirect` available that takes a single
command buffer and a binding table for it because having nested variadic
imports is not possible.

This is a non-breaking binary change as the compiler has never emitted
the removed execute call or nested command buffers.

Future changes will add command buffer recording and validation of
indirect bindings. Today they're ignored as there's no way to record
command buffers with indirect bindings.
51 files changed
tree: e42d5eec61269fc0e32841c7b6b5563abce20863
  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.