Google Git
Sign in
opensecura / 3p / openxla / iree / 7497689acb7125046625bc78dfb43dc7da9eff38
commit7497689acb7125046625bc78dfb43dc7da9eff38[log] [tgz]
authorManish Gupta <manigupta@google.com>Wed Mar 15 14:37:15 2023 -0700
committerGitHub <noreply@github.com>Wed Mar 15 14:37:15 2023 -0700
tree7b1ba381138601b3825b86324ec866eb89f35070
parent62ee2f342484a1468abe5bc96a2be7c3192a6e63 [diff]
Mainloop multistaged pipeline and instruction scheduling for NVIDIA Ampere Tensor Cores (F16 and F32) (#12603)

This PR creates a coarse-grained multistage pipelining and fine-grained
instruction scheduling for optimal performance on NVIDIA Ampere Tensor
Cores.

Multi-staging is essential to hide the Global Memory load latency by
building longer software pipelines and using the available Shared Memory
capacity, especially on NVIDIA A100. Additionally, fine-grained
instruction scheduling hides the Shared Memory load latency by
prefetching the math operands into registers. The PR adds support for
F16 and F32 datatype using `mma.sync` native Tensor Core exposure.
4 files changed
tree: 7b1ba381138601b3825b86324ec866eb89f35070
  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. .bazelignore
  16. .bazelrc
  17. .bazelversion
  18. .clang-format
  19. .dockerignore
  20. .gitignore
  21. .gitmodules
  22. .pylintrc
  23. .style.yapf
  24. .yamllint.yml
  25. AUTHORS
  26. BUILD.bazel
  27. CITATION.cff
  28. CMakeLists.txt
  29. configure_bazel.py
  30. CONTRIBUTING.md
  31. LICENSE
  32. README.md
  33. 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.