Build tracy by default in the Python runtime packages. (#14639)

This is accomplished by:

* Re-organizing the native dependencies under `iree._runtime_libs` and
`iree._runtime_libs_tracy`, which can co-exist in the same wheel.
* Have `runtime/setup.py` do an additional CMake build for
`_runtime_libs_tracy` if the env var `IREE_RUNTIME_BUILD_TRACY=ON`.
* Re-mash `setup.py` to make it happy with the new layout and make
everything optional.
* Split the package prefixes for the source and built directories.
* Move generated version.py to the built _runtime_libs package and
trampoline from `iree.runtime.version` to preserve the API.
* Modify the `_binding.py` loader (loaded at `iree.runtime` init time)
to dynamically switch its backing runtime based on the value of the
environment variable `IREE_PY_RUNTIME`, which can be `default` or
`tracy`.
* Rework all of the `__main__.py` wrappers (for `iree-run-module` and
such) to use the runtime library path found in the previous step.

This can be improved in the future to eliminate more binary size
duplication by adopting a busybox-like strategy as used on the compiler
(would also be a good time to enable LTO, clang, and debug symbols).
As-is, this ~doubles the size to about 7MiB, which is acceptable given
the usability benefit. I expect with such re-organizations, we can get
it to roughly half of its size prior to this change (1/4 after).
19 files changed
tree: 6b285d1981aa5d4ba5dbe87e47a6eef6cf3b0eb3
  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.