Google Git
Sign in
opensecura / 3p / openxla / iree / 48fa0daa377295b1610a02eadcfa4a5833431bb0
commit48fa0daa377295b1610a02eadcfa4a5833431bb0[log] [tgz]
authorBen Vanik <ben.vanik@gmail.com>Fri Jan 20 13:21:55 2023 -0800
committerGitHub <noreply@github.com>Fri Jan 20 13:21:55 2023 -0800
tree100a4b1d71d1c9e2eed7808641b6019c3119165b
parent65208231dddac6872aef7603c25deccfe23ea4a9 [diff]
Supporting host memory registration in CUDA via external buffers. (#11899)

Re-landing #11848 that was reverted in #11895 due to performance
regressions.

The original commit included context push/pop during deallocation which
resulted in device synchronizes due to CUDA's context threading model.
For now a warning has been added that (like much of the current CUDA
driver) threading is not quite handled right. User APIs that may manage
buffer lifetime will need to be aware of the thread they are releasing
buffers on until a larger cleanup can be performed and that was the case
before the changes made here.

The original commit also incorrectly allowed requests for imports as
DEVICE_LOCAL usage to be performed when importing host allocations; this
led to program constant buffers being mapped from files and used as if
they were on device.

This reverts commit 3c78102749f8ceb3f82bf9a103a74d215adf160b.
5 files changed
tree: 100a4b1d71d1c9e2eed7808641b6019c3119165b
  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.