Google Git
Sign in
opensecura / 3p / openxla / iree / 289b9a1ebf954be3995cc1895254d09f2623341f
commit289b9a1ebf954be3995cc1895254d09f2623341f[log] [tgz]
authorStella Laurenzo <laurenzo@google.com>Fri Feb 24 13:06:32 2023 -0800
committerGitHub <noreply@github.com>Fri Feb 24 13:06:32 2023 -0800
tree05f88b7180172655fac274250718d46878bb91e9
parent7a6b21b3c872477ac2d12ad7b8055d1d4fc0a65c [diff]
Add IREE_COMPILER_BUILD_SHARED_LIBS option. (#12310)

* Balances all of the angels on the head of the pin such that when using
it, trivial changes to the compiler that would usually require a lengthy
re-link happen in <1s.
* Fixes some indirect dependencies that were missing (and enforced with
stricter linking).
* This is the equivalent of how LLVM interprets -DBUILD_SHARED_LIBS=ON,
scoped to just IREE's bundled LLVM, LLVM sub-projects and compiler
sources.
* As with all uses of BUILD_SHARED_LIBS, the support matrix for this
feature is sparse: there are many ways it will not work outside of its
strict case for supporting development.
* iree-run-module is not happy (complaining of duplicate option
registration). Will triage separately.
* This probably only works on Linux right now. It likely can work on
MacOS, but the libIREECompiler.dylib will need to be rigged with
--reexport_library (which is effectively the default for dynamically
loaded ELF). I don't think this will work on Windows without substantial
work.
* I am intending to use this mode to enable rapid reload of dynamically
built plugins, etc.
11 files changed
tree: 05f88b7180172655fac274250718d46878bb91e9
  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. .dockerignore
  19. .gitignore
  20. .gitmodules
  21. .pylintrc
  22. .style.yapf
  23. .yamllint.yml
  24. AUTHORS
  25. BUILD.bazel
  26. CITATION.cff
  27. CMakeLists.txt
  28. configure_bazel.py
  29. CONTRIBUTING.md
  30. LICENSE
  31. README.md
  32. 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.