Google Git
Sign in
opensecura / 3p / openxla / iree / fb4f8d2dd93ef8bd8fb6c16d508e6e006c516c36
commitfb4f8d2dd93ef8bd8fb6c16d508e6e006c516c36[log] [tgz]
authorStanley Winata <68087699+raikonenfnu@users.noreply.github.com>Fri Sep 30 16:04:03 2022 -0700
committerGitHub <noreply@github.com>Fri Sep 30 16:04:03 2022 -0700
treea07a770a16917debe76c4d689be2d0b29e1e35b2
parent5d75e54d9d71a9627e7519d6bacb6ff9888ac4a5 [diff]
[flow] Generalize 1x1 Conv2D to matmul for NCHW (#10616)

Most models from PyTorch uses NCHW Conv2D by default. To accelerate the
1x1 filter Conv2D workload with NCHW layout, we generalize the 1x1 filter
Conv2D to matmul pass to be able to handle NCHW as well.

Perf boost on ResNet50 (PyTorch):
- CPU (Threadripper PRO 3995WX): 100ms -> 80ms
- Vulkan (Threadripper PRO 3995WX): 48ms -> 31.7ms
8 files changed
tree: a07a770a16917debe76c4d689be2d0b29e1e35b2
  1. .github/
  2. benchmarks/
  3. build_tools/
  4. compiler/
  5. docs/
  6. experimental/
  7. integrations/
  8. llvm-external-projects/
  9. runtime/
  10. samples/
  11. tests/
  12. third_party/
  13. tools/
  14. .bazelignore
  15. .bazelrc
  16. .bazelversion
  17. .clang-format
  18. .gitignore
  19. .gitmodules
  20. .pylintrc
  21. .style.yapf
  22. .yamllint.yml
  23. AUTHORS
  24. BUILD.bazel
  25. CITATION.cff
  26. CMakeLists.txt
  27. configure_bazel.py
  28. CONTRIBUTING.md
  29. LICENSE
  30. README.md
  31. 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.