Add C APIs sufficient for tunneling LLVM command line handling into derived tools. (#12710)

This does some delicate surgery to rationalize the normal LLVM
initialization sequence and make it suitable for API usage for the
limited use case of subordinating IREE compiler's command line
processing to an outer component (i.e. by having "--" style separators
or "-Xcompiler" like options in another command line library).

`iree-compile` itself still uses its privileged position as built-in to
actually define new global command line options, which the C API does
not expose. This works because it is always statically linked into the
main libIREECompiler.so shared library.

BREAKING C API CHANGE: `ireeCompilerGlobalInitialize()` now takes no
arguments whereas it used to take a boolean "usesCommandLine" option
which was a half-hearted attempt to make this case work previously. The
only use of this as true was in-tree and it wasn't really possible to
use right externally. If passing false, just drop the argument. If
passing true, use a combination of ireeCompilerGetProcessCLArgs and
ireeCompilerSetupGlobalCL as shown in iree_compile_lib.cc. Also, the
sequencing has been reworked to allow nested calls to
initialize/shutdown. The lack of this was causing unreliability in the
PJRT client, which is the major out of tree user of the API. Given the
low use and broken state of this API, it is preferable to just clean it
up now vs retain compatibility.
16 files changed
tree: 6ee6911c39a6300ad33ba2ee0bd4aee28ab55d6a
  1. .github/
  2. benchmarks/
  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. .bazelignore
  16. .bazelrc
  17. .bazelversion
  18. .clang-format
  19. .dockerignore
  20. .gitignore
  21. .gitmodules
  22. .pylintrc
  23. .style.yapf
  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.