[Codegen] Support multi-output consumers with permuted indexing maps (#24768) Extend lowering of fused & tiled consumer ops from the basic case (strictly identical indexing over the output operands). We now generalize the logic for input indexing to support different output maps that are simple permutations. This allows to support some fusion cases where a simple transposition from one of the consumer's connections get fused into the elementwise generic, and then the consumer gets fused & tiled together with the matmul. Whether we want such consumer fusion is a separate matter subject to performance investigations, and in my reproducer there'd also be an opportunity to fold redundant `tranpose(transpose(x))` instances, avoiding the multi-output fusion altogether. For better stability, this extension of the codegen is preferred as the first step. Signed-off-by: Artem Gindinson <gindinson@roofline.ai> Assisted by: Codex --------- Signed-off-by: Artem Gindinson <gindinson@roofline.ai>
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 |
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.