Google Git
Sign in
opensecura / 3p / openxla / iree / 9d36cfa0a95a606387b65a551cf33ba5d1fb91ee
commit9d36cfa0a95a606387b65a551cf33ba5d1fb91ee[log] [tgz]
authorMax191 <44243577+Max191@users.noreply.github.com>Mon Oct 28 12:30:37 2024 -0700
committerGitHub <noreply@github.com>Mon Oct 28 15:30:37 2024 -0400
treef8942f123ec4d1a7c17d1d27316ae84c202c4775
parente66171aa4c928727a589ad016134f009140c8a03 [diff]
[Codegen] Don't require full slice to decompose boundary pack and unpack ops (#18906)

This PR loosens the restrictions on decomposing boundary pack and unpack
ops. The current restriction is that the dispatch.tensor.load/store ops
are full slices, but this is not necessary for the current use case in
the TileAndFuse pipeline.

Instead, it is better for the time being to decompose non-padded
pack/unpack ops at function boundaries regardless of the
dispatch.tensor.load/store ops being full slices, because decomposing
such ops later on can cause issues with DPS. The DPS issues are tracked
in https://github.com/iree-org/iree/issues/18902, but we can loosen the
restrictions regardless, since it does not pose any issues to decompose
in such cases.

Signed-off-by: Max Dawkins <max.dawkins@gmail.com>
2 files changed
tree: f8942f123ec4d1a7c17d1d27316ae84c202c4775
  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. .git-blame-ignore-revs
  20. .gitattributes
  21. .gitignore
  22. .gitmodules
  23. .pre-commit-config.yaml
  24. .yamllint.yml
  25. AUTHORS
  26. BUILD.bazel
  27. CITATION.cff
  28. CMakeLists.txt
  29. configure_bazel.py
  30. CONTRIBUTING.md
  31. LICENSE
  32. MAINTAINERS.md
  33. README.md
  34. RELEASING.md
  35. 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.

IREE Discord Status pre-commit OpenSSF Best Practices

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

Release status

PackageRelease status
GitHub release (stable)GitHub Release
GitHub release (nightly)GitHub Release
Python iree-compilerPyPI version
Python iree-runtimePyPI version

Build status

CI PkgCI

Host platformBuild status
LinuxCI - Linux x64 clang
CI - Linux arm64 clang
macOSCI - macOS x64 clang
WindowsCI - Windows x64 MSVC

For the full list of workflows see https://iree.dev/developers/general/github-actions/.

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.