Google Git
Sign in
opensecura / 3p / openxla / iree / 86de3ffe548a265d008fb9270ce839d4fd46843f
commit86de3ffe548a265d008fb9270ce839d4fd46843f[log] [tgz]
authorMaheshRavishankar <1663364+MaheshRavishankar@users.noreply.github.com>Mon Feb 01 10:58:09 2021 -0800
committerGitHub <noreply@github.com>Mon Feb 01 10:58:09 2021 -0800
tree93a0a6c2a880219d8322b7842a8f9954249d8239
parentd0cb6c2ba1e837ec2946595a38237829945cbfa3 [diff]
Add region to `hal.executable.entry_point` that computes number of  workgroups. (#4634)

While the code-generated through the linalg on tensors path works for
any number of workgroups used by the runtime, there is advantage to
expose the maximum number of workgroups that are actually needed to
perform the entire computation represented by the
`flow.dispatch.workgroup`. The runtime can then chose to
underprovision based on resource availability.
This is done by adding a region to `hal.executable.entry_point` op
that returns the maximum number of workgroups given the workload of
the dispatched computation.
Current implementation limitations are that it is assumed that the
workload is described in terms of [x, y, z]. Due to this only those
dispatch regions in flow dialect that have workload described in terms
of [x, y, z] are handled.

A consequence of allowing backends to specify number of workgroups is
that the translation pipeline now needs the entire
`hal.executable.target` operation for translation.

The Linalg on tensors path is adapted to use this which enables use of
multi-core CPU.
13 files changed
tree: 93a0a6c2a880219d8322b7842a8f9954249d8239
  1. .github/
  2. bindings/
  3. build_tools/
  4. colab/
  5. docs/
  6. experimental/
  7. integrations/
  8. iree/
  9. scripts/
  10. third_party/
  11. .bazelignore
  12. .bazelrc
  13. .bazelversion
  14. .clang-format
  15. .gitignore
  16. .gitmodules
  17. .style.yapf
  18. .yamllint.yml
  19. BUILD.bazel
  20. CMakeLists.txt
  21. configure_bazel.py
  22. CONTRIBUTING.md
  23. LICENSE
  24. README.md
  25. SUBMODULE_VERSIONS.txt
  26. WORKSPACE
README.md

IREE: Intermediate Representation Execution Environment

IREE (Intermediate Representation Execution Environment, pronounced as “eerie”) is an MLIR-based end-to-end compiler that lowers ML models to a unified IR optimized for real-time mobile/edge inference against heterogeneous hardware accelerators. IREE also provides flexible deployment solutions for the compiled ML models.

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.

Getting Started

Quick Start using Python

Python packages are published on the releases page. See the colab/ directory for examples.

Building from Source

IREE can be built from source using both Bazel and CMake on Windows and Linux. We also have experimental macOS support.

Please see the Getting Started pages on IREE's documentation hub to configure, compile, and run IREE in your favorite development environment!

Documentation and Talks

IREE hosts all its documentation and project status dashboards on GitHub Pages. We are still building up the website; please feel free to create issues for the documentation you'd like to see!

We also have some public talks that explain IREE's concepts and architecture:

  • 2020-03-18: Interactive HAL IR Walkthrough (Ben Vanik and core team) (recording)
  • 2020-01-31: End-to-end MLIR Workflow in IREE (recording and slides)

Architecture and Goals

IREE adopts a holistic approach towards ML model compilation: the IR produced contains both the scheduling logic, required to communicate data dependencies to low-level parallel pipelined hardware/API like Vulkan, and the execution logic, encoding dense computation on the hardware in the form of hardware/API-specific binaries like SPIR-V.

The architecture of IREE is best illustrated by the following picture:

IREE Architecture

Being compilation-based means IREE does not have a traditional runtime that dispatches “ops” to their fat kernel implementations. What IREE provides is a toolbox for different deployment scenarios. It scales from running generated code on a particular API (such as emitting C code calling external DSP kernels), to a HAL (Hardware Abstraction Layer) that allows the same generated code to target multiple APIs (like Vulkan and Direct3D 12), to a full VM allowing runtime model loading for flexible deployment options and heterogeneous execution.

IREE aims to

  • Support advanced models on mobile/edge devices. Dynamic shapes, dynamic flow control, dynamic multi-model dispatch, streaming models, tree-based search algorithms, and other are all good examples of exciting ML evolution. We are trying to build IREE from the ground-up to enable these models and run them efficiently on modern hardware, especially on mobile/edge devices.
  • Demonstrate MLIR‘s ability to develop non-traditional ML compiler backends and runtimes. MLIR enables IREE’s holistic approach of focusing on the math being performed and how that math is scheduled rather than graphs of “ops”.
  • Embrace standard-based ML via Vulkan. The graphics world is shifting towards favoring modern explicit APIs for performance and predictability and Vulkan is emerging as the “compatibility” layer. We would love to allow hardware vendors to be able to make ML efficient on their hardware without the need for bespoke runtimes and special access. We also would love to let developers and users utilize all the hardware available on as many platforms as possible.

Roadmap and Milestones

IREE is in the early stages of development and not yet ready for broad adoption. Check out the long-term design roadmap to get a sense of where we're headed.

We plan on a quarterly basis using OKRs. Review our latest objectives to get a sense of what we're up to in the near term.

We use GitHub Projects to track progress on IREE components and specific efforts. We use GitHub Milestones to track the work associated with plans for each quarter.

Build Status

CI SystemBuild SystemPlatformArchitectureComponentStatus
KokoroBazelLinuxx86Corekokoro_status_bazel_linux_x86_core
KokoroCMake & BazelLinuxx86-swiftshaderIntegrationskokoro_status_cmake-bazel_linux_x86-swiftshader_integrations
KokoroCMake & BazelLinuxx86-turingIntegrationskokoro_status_cmake-bazel_linux_x86-turing_integrations
KokoroCMakeLinuxx86-swiftshaderCore + Bindingskokoro_status_cmake_linux_x86-swiftshader
KokoroCMakeLinuxx86-turingCore + Bindingskokoro_status_cmake_linux_x86-turing
KokoroCMakeAndroidarm64-v8aRuntime (build only)kokoro_status_cmake_android_arm64-v8a
BuildKiteCMakeAndroidarm64-v8aRuntimebuildkite-status-cmake-android-arm

License

IREE is licensed under the terms of the Apache license. See LICENSE for more information.