Google Git
Sign in
opensecura / 3p / openxla / iree / a5537bc683b8476d12917ced00f3540859894de1
commita5537bc683b8476d12917ced00f3540859894de1[log] [tgz]
authorStanley Winata <68087699+raikonenfnu@users.noreply.github.com>Mon Nov 04 10:30:53 2024 -0800
committerGitHub <noreply@github.com>Mon Nov 04 10:30:53 2024 -0800
treedb410ff9a1f7c569df7948f16db9417738e3bafa
parentec7528cee889b6fe0c369420aff1094c333fd2b5 [diff]
 [LLVMGPU] Teach KernelConfig to set MMA schedules per op in LoweringConfig (#18984)

The main motivation for this change is to enable different
intrinsics/layout on different ops inside the same function/dispatch,
especially for attention. To that extend, we move the scheduling MMA
information such as mma_intrinsic, subgroup_m_count, and
subgroup_n_count, from the translation info attached to the function
onto the lowering_config per op. Here is a quick summary of things we
needed to do to achieve that:

1. Introduce setMmaKind, set/get subgroupMCount, and set/get
subgroupMCount on IREE::GPU::LoweringConfigAttr
2. Move configuring of QK matmul's schedule into KernelConfig from
LLVMGPUConfigureTensorLayout.
3. Now that qk and pv may have different intrinsic, update information
used to decide transposeIntrinsic and reuseIntrinsic in
LLVMGPUConfigureTensorLayout
4. Update a bunch of tests to use lowering config to configure MMAs now.

---------

Signed-off-by: Stanley Winata <stanley.winata@amd.com>
12 files changed
tree: db410ff9a1f7c569df7948f16db9417738e3bafa
  1. .github/
  2. build_tools/
  3. compiler/
  4. docs/
  5. experimental/
  6. integrations/
  7. lib/
  8. llvm-external-projects/
  9. runtime/
  10. samples/
  11. tests/
  12. third_party/
  13. tools/
  14. .bazel_to_cmake.cfg.py
  15. .bazelignore
  16. .bazelrc
  17. .bazelversion
  18. .clang-format
  19. .git-blame-ignore-revs
  20. .gitattributes
  21. .gitignore
  22. .gitmodules
  23. .pre-commit-config.yaml
  24. .yamllint.yml
  25. AUTHORS
  26. BUILD.bazel
  27. CITATION.cff
  28. CMakeLists.txt
  29. configure_bazel.py
  30. CONTRIBUTING.md
  31. LICENSE
  32. MAINTAINERS.md
  33. README.md
  34. RELEASING.md
  35. 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.

IREE Discord Status pre-commit OpenSSF Best Practices

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

Release status

PackageRelease status
GitHub release (stable)GitHub Release
GitHub release (nightly)GitHub Release
Python iree-compilerPyPI version
Python iree-runtimePyPI version

Build status

CI PkgCI

Host platformBuild status
LinuxCI - Linux x64 clang
CI - Linux arm64 clang
macOSCI - macOS x64 clang
WindowsCI - Windows x64 MSVC

For the full list of workflows see https://iree.dev/developers/general/github-actions/.

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

Community meeting recordings: IREE YouTube channel

  • 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.