Finally moving VM type registration to iree_vm_instance_t. (#12650)

This allows for thread-safe type registration scoped to instances and
unregistration of types as required by types in dynamically loaded
modules that may wink out of existence at some point. The main trick
here was changing the type ID from an ordinal in the type table to just
the pointer of the type descriptor. This requires an extra 4 bytes per
ref on 64-bit systems but who cares - now there's no round-tripping
through the type table for common operations.

As part of simplifying the way types are referenced VM type descriptors
are now hidden behind iree_vm_ref_type_t. This makes refs much easier to
work with as there's only one way to reference types and it always
bottoms out on the registered descriptor
handle. It also allows us to remove some type descriptor indirection
we'd previously required in order to get reference counter offsets as we
can share the same packed type identifier in type defs, refs, or lists.

Thanks to @simon-camp for the required EmitC changes!

---------

Co-authored-by: Simon Camphausen <simon.camphausen@iml.fraunhofer.de>
89 files changed
tree: 81808668f3dba4ecba794cff631f5095a4b54b06
  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. .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.