Google Git
Sign in
opensecura / 3p / openxla / iree / 9691c91338feaaac26bdf14356ab7d5b877ce302
commit9691c91338feaaac26bdf14356ab7d5b877ce302[log] [tgz]
authorManish Gupta <manigupta@google.com>Mon Feb 06 09:37:48 2023 -0800
committerGitHub <noreply@github.com>Mon Feb 06 09:37:48 2023 -0800
tree5f2b36ea1d350afdc58385545d806489389ae127
parentcde68fdf16d3acab5bd5819f26ea9981abf77314 [diff]
Functional support mma.sync.1688.f32.tf32 for F32 datatype (#12054)

**Adds native Tensor Core (F32) support for NVIDIA A100 GPU** 

The PR targets`mma.sync.aligned.m16n8k8.row.col.f32.tf32.tf32.f32`,
`ldmatrix` for operandA and `ld.shared` for operandB on NVIDIA A100
GPUs. For now, these instructions are not enabled by default and are
behind iree-compile flag `--iree-codegen-llvmgpu-use-mma-sync=true`.

IREE runs row-row matmul, the native Tensor Core support is enabled
through `ldmatrix` for operandA. However,
`ldmatrix.trans` for operandB can only work at 16-bit granularity. Thus,
`ld.shared` instruction is used for operandB to transposes the data
while loading data into register. This allows the use of Tensor Core
`mma.sync*row.col*` instruction.
4 files changed
tree: 5f2b36ea1d350afdc58385545d806489389ae127
  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.