| commit | c54764e8dffa9e02c03ba28f28ccbdbc3504fd2b | [log] [tgz] |
|---|---|---|
| author | Quinn Dawkins <quinn.dawkins@gmail.com> | Fri Dec 12 09:24:56 2025 -0800 |
| committer | GitHub <noreply@github.com> | Fri Dec 12 12:24:56 2025 -0500 |
| tree | 77b6ee13b86b2dde57c5c8caed224c7ccdee44f0 | |
| parent | 5ed90416b82523b26d0d8fdc9919a25a30ea5fad [diff] |
[Codegen] Add PCF dialect (#22804) This introduces a new dialect for "Parallel Control Flow" (named a la scf). This is motivated by expressivity gaps in the current constructs we use to represent distributed compute for the next set of algorithms we're working towards supporting in the compiler. To name a few: - Stream-K - Warp/Clustered reductions - Named Barriers - Improved robustness of fusion support - Persistent-ish kernels (things that need to communicate across wkgps) Naturally the base added here does not directly cover all of the above but should make it much easier to do so. The core idea behind the dialect hinges on three concepts: 1. Shaped references of unspecified layout and memspace 2. Execution scopes which threads are forked out of 3. Synchronization scopes which control access to associated memory The dialect includes further documentation behind the above 3 points. The initial proposal can be found here: https://hackmd.io/iHdqgU7MQnSvX6H_y_6JrQ (Much of the naming/representation has changed since this writeup)
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.
Releases notes are published on GitHub releases.
| Package | Release status |
|---|---|
| GitHub release (stable) | |
| GitHub release (nightly) | |
iree-base-compiler | |
iree-base-runtime |
For more details on the release process, see https://iree.dev/developers/general/release-management/.
| Operating system | Build status |
|---|---|
| Linux | |
| macOS | |
| macOS |
For the full list of workflows see https://iree.dev/developers/general/github-actions/.
See our website for more information.
Community meeting recordings: IREE YouTube channel
| Date | Title | Recording | Slides |
|---|---|---|---|
| 2025-06-10 | Data-Tiling in IREE: Achieving High Performance Through Compiler Design (AsiaLLVM) | recording | slides |
| 2025-05-17 | Introduction to GPU architecture and IREE's GPU CodeGen Pipeline | recording | slides |
| 2025-02-12 | The Long Tail of AI: SPIR-V in IREE and MLIR (Vulkanised) | recording | slides |
| 2024-10-01 | Unveiling the Inner Workings of IREE: An MLIR-Based Compiler for Diverse Hardware | recording | |
| 2021-06-09 | IREE Runtime Design Tech Talk | recording | slides |
| 2020-08-20 | IREE CodeGen (MLIR Open Design Meeting) | recording | slides |
| 2020-03-18 | Interactive HAL IR Walkthrough | recording | |
| 2020-01-31 | End-to-end MLIR Workflow in IREE (MLIR Open Design Meeting) | recording | slides |
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.