Google Git
Sign in
opensecura / 3p / openxla / iree / b13d38b4b56370351b0b60478b4b74659a3c4b57
commitb13d38b4b56370351b0b60478b4b74659a3c4b57[log] [tgz]
authorHan-Chung Wang <hanhan0912@gmail.com>Thu Sep 26 09:11:26 2024 -0700
committerGitHub <noreply@github.com>Thu Sep 26 09:11:26 2024 -0700
tree1518d366ca2dea52937c640ea20ac2e74a562f89
parentd5839584547ec2a258b12399f56ea3d006668dbb [diff]
[DT] Collapse matmul_narrow_M/N field into round_dims_to attribute. (#18599)

The revision refines how we handle matmul_narrow_M/N in encodings. The
matmul_narrow_M/N attributes are retired in the patch. The information
is carried in `round_dims_to` attribute which is rounded to the next
power of two. E.g., if the value of `matmul_narrow_M` is `3`, it will be
`4` in the `round_dims_to` attribute.

The `kNarrowThreshold` constant is introduced to Encoding namespace. A
dimension is considered as "narrow" only if the size of the dimension is
less than `kNarrowThreshold`.

The revision implements `getMatmulNarrowM` and `getMatmulNarrowN`
helpers based on the definition of `round_dims_to` and the
`kNarrowThreshold` variable. Users can call the helpers to get the
narrow size of M/N. Again, you'll get the value that is rounded to the
next power of two if they are considered "narrow". E.g.,
`getMatmulNarrowM()` returns `4` if `M` equals to `3`.

The revision also fixes a bug in `chooseMatmulTile` on CPU side. The
hostDefinedUpperBound is not updated in the narrow-N cases.

Fixes https://github.com/iree-org/iree/issues/17729
Fixes https://github.com/iree-org/iree/issues/15466

---------

Signed-off-by: hanhanW <hanhan0912@gmail.com>
11 files changed
tree: 1518d366ca2dea52937c640ea20ac2e74a562f89
  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.