[DT][SVE] adjust tile sizes for mmt4d & disable transposition of narrow-N matmuls (#21701) This PR builds upon #21304 and takes a step forward to adjust tile sizes in the existence of scalable inner tiles with `mmt4d`. This is step 2/N to enable data-tiling with SVE. There will be others to adjust tile sizes for packs/unpacks as well. Also, since SVE requires the `N` dimension to be scalable - because of vectorization unrolling on the inner `M` dimension and this currently not being supported for scalable `M` dims - disables transposition of narrow-N matmuls. On another note, we currently walk the IR to retrieve the inner tile sizes of the `mmt4d`. This mechanism currently assumes that only `M` and `N` dimensions could be scalable, which holds for SME and SVE. Although for future references, we could either find another mechanism to communicate the inner tile sizes chosen during materialization to the tile size selection OR extend this method to handle the inputs - and therefore infer the scalable K as well. Note: materialization of SME is currently not supported. --------- Signed-off-by: Ege Beysel <beyselege@gmail.com>
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.