commit | 5723e7ea78b8be3596f6cb89db5abaa9114779c0 | [log] [tgz] |
---|---|---|
author | Kunwar Grover <groverkss@gmail.com> | Mon Sep 08 22:10:40 2025 +0100 |
committer | GitHub <noreply@github.com> | Mon Sep 08 22:10:40 2025 +0100 |
tree | afe34771d47895a1ba802f241eb1bee57011330a | |
parent | 0aded2741bdf925d26ca6eb2bc531b8c8ff328c7 [diff] |
Reland "[VectorDistribute] Refactor layout configuration to a simpler logic" (#21895) This patch refactors the layout configuration for mma intrinsics to a much simpler implementation and documents it better. This implementation will eventually allow us to stop using subgroup_m_count/subgroup_n_count attributes and use subgroup_basis to control setting number of subgroups on each dimension. This patch is mostly NFC, except it removes the ability to greedily distribute multiple subgroups to multiple dimensions automatically. This path was not used or maintained. We will eventually have the ability to do it in following patches once we switch to subgroup_basis. The test deleted checks the greedy distribution to multiple subgroups ability which was not used anywhere else. The tuning spec is changed because it was actually wrong and the compiler was falsely accepting the configuration. The new configuration will crash on this invalid specification.
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.