Google Git
Sign in
opensecura / 3p / openxla / iree / 9a286397f776542f9da23b03eaea5be0d5ed870d
commit9a286397f776542f9da23b03eaea5be0d5ed870d[log] [tgz]
authorBen Vanik <ben.vanik@gmail.com>Fri May 20 19:45:23 2022 -0700
committerBen Vanik <ben.vanik@gmail.com>Thu May 26 14:22:29 2022 -0700
tree70d82d72429adc51d66b2ba123e492868976d287
parent41de9e65fafc3439e2759d060a811b8de2fbaa49 [diff]
Enabling split rodata blobs in VMFB archives.
This changes the VMFB files to contain a length prefix so that the
end of the module flatbuffer can be calculated and trailing rodata can be
located. With this the module flatbuffer is still limited to 2GB but any
amount of data may follow as all offsets are tracked as 64-bit values.

In order to make this work the polyglot zip emitter had to be reworked
as to not mess with the required rodata alignments. Since big file-like
blobs that would show in the zip are now stored outside the flatbuffer
there's also no need to do the crazy embedded zip headers and we can now
put a local file header in front of the module flatbuffer and show that
in the zip. A few bugs and compatibility issues were worked out and now
the vmfb files can be directly detected as zips by `file` and other tools
and everything I've tried (`unzip`, `7z`, Windows, etc) can open them.
15 files changed
tree: 70d82d72429adc51d66b2ba123e492868976d287
  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. .gitignore
  19. .gitmodules
  20. .pylintrc
  21. .style.yapf
  22. .yamllint.yml
  23. AUTHORS
  24. BUILD.bazel
  25. CMakeLists.txt
  26. configure_bazel.py
  27. CONTRIBUTING.md
  28. LICENSE
  29. README.md
  30. 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.

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.

Build Status

CI SystemBuild SystemPlatformArchitectureConfiguration / ComponentStatus
KokoroBazelLinuxx86-64kokoro status bazel/linux/x86-swiftshader/core
KokoroCMake & BazelLinuxx86-64 (swiftshader)Integrationskokoro status cmake-bazel/linux/x86-swiftshader
KokoroCMake & BazelLinuxx86-64 (turing)Integrationskokoro status cmake-bazel/linux/x86-turing
KokoroCMakeLinuxx86-64 (swiftshader)kokoro status cmake/linux/x86-swiftshader
KokoroCMakeLinuxx86-64 (swiftshader)asankokoro status cmake/linux/x86-swiftshader-asan
KokoroCMakeLinuxx86-64 (turing)kokoro status cmake/linux/x86-turing
KokoroCMakeAndroidarm64-v8aRuntime (build only)kokoro status cmake/android/arm64-v8a
KokoroCMakeBare Metalrisc-v-32Runtimekokoro status cmake/baremetal/riscv32
KokoroCMakeLinuxrisc-v-64Runtimekokoro status cmake/linux/riscv64
BuildkiteCMakeAndroidarm64-v8aRuntimebuildkite status iree-android-arm64-v8a
BuildKiteCMakeAndroidarm64-v8aRuntime Benchmarksbuildkite status iree-benchmark
BuildKiteCMakeLinuxx86-64Tracing + Standalone Runtimebuildkite status iree-build-configurations

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.