Google Git
Sign in
opensecura / 3p / openxla / iree / e23561d2f61a46f55acaaa7f01dba4a32e52e7fb
commite23561d2f61a46f55acaaa7f01dba4a32e52e7fb[log] [tgz]
authorbjacob <benoitjacob@google.com>Fri Jun 02 13:50:06 2023 -0400
committerGitHub <noreply@github.com>Fri Jun 02 13:50:06 2023 -0400
treec26822e7ff0bbf7fd083bd3236ba4858d9f22e17
parent103864845ee3bd36c052b6473a3c52a66429aaa4 [diff]
Improvements to target CPU features variants in e2e tests (#13915)

* CPU feature variants now have a short mnemonic. Test names use it, so
they stay short regardless of the number of CPU features enabled. (Test
names were generated by joining all CPU feature strings, which was too
much with AVX-512 consisting of several sub-features such as
`+avx,+avx2,+fma,+avx512f,+avx512vl,+avx512cd,+avx512bw,+avx512dq,+avx512vnni`).
* The CMake helper functions `process_target_cpu_features` is much
simplified, and renamed `parse_target_cpu_features_variant`. It's also
made more correct: it was suggesting that it was taking names of
output-variables as arguments, but was actually ignoring them and
writing to fixed variables. Now it's honoring its output-var arguments.
* Some recently added tests used the `"large"` matmul shapes set, but
weren't tagged `noriscv` and `notsan`, and as a result, were hitting >
10s latencies, a potential timeout risk. Fixed.
4 files changed
tree: c26822e7ff0bbf7fd083bd3236ba4858d9f22e17
  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. .gitignore
  22. .gitmodules
  23. .pylintrc
  24. .style.yapf
  25. .yamllint.yml
  26. AUTHORS
  27. BUILD.bazel
  28. CITATION.cff
  29. CMakeLists.txt
  30. configure_bazel.py
  31. CONTRIBUTING.md
  32. LICENSE
  33. README.md
  34. 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.