Google Git
Sign in
opensecura / 3p / openxla / iree / 3459833ae9c3f0fefe33ff08df7b99359d0c26b4
commit3459833ae9c3f0fefe33ff08df7b99359d0c26b4[log] [tgz]
authorMaheshRavishankar <1663364+MaheshRavishankar@users.noreply.github.com>Wed Jun 21 20:12:02 2023 -0700
committerGitHub <noreply@github.com>Thu Jun 22 03:12:02 2023 +0000
tree9eb0af53f5bab16487c35c3d575cf0f01613eb16
parent5757feba749787870aca120f01338d9d0677ed5d [diff]
Create dispatches for scalar computation using program slices. (#13711)

Current dispatch region formation logic is geared towards "large"
tensors. For computations on small tensors, these just need to be
moved into a dispatch and executed sequentially on the device. Unlike
the current dispatch region formation that is centered around tile and
fuse approach, the scalar computations just need to be lowered to
loops (which might be small trip loops that can be
canonicalized/unrolled). So the approach used here uses backward slice
to group together a DAG of operations that can be moved into a
sequential dispatch for execution on the device. It also does some
basic "horizontal fusion" to group together operations that are not
producer->consumer but are still scalar computations.

Fixes #13545
13 files changed
tree: 9eb0af53f5bab16487c35c3d575cf0f01613eb16
  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. .gitignore
  23. .gitmodules
  24. .yamllint.yml
  25. AUTHORS
  26. BUILD.bazel
  27. CITATION.cff
  28. CMakeLists.txt
  29. configure_bazel.py
  30. CONTRIBUTING.md
  31. LICENSE
  32. README.md
  33. 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.