| commit | fdb42dafc0e2010d0b021cedd4fb1ca6f42939ab | [log] [tgz] |
|---|---|---|
| author | MaheshRavishankar <1663364+MaheshRavishankar@users.noreply.github.com> | Wed Aug 31 17:07:45 2022 -0700 |
| committer | GitHub <noreply@github.com> | Wed Aug 31 17:07:45 2022 -0700 |
| tree | aef0aa1ad9e34d36b4454821ef71d858fdee72d9 | |
| parent | e818e8aeaeee1e21478b6fcd3d8b7473bac1a76e [diff] |
Handle multi-result operations and dispatches. (#10245) The TileAndDistributeToWorkgroups could only handle cases where fused producer has a single use. For multiple uses, each use would introduce new instance of the tiled producer with tile + fuse. To address this add a `TileAndFuse` pattern that fuses the producer right after tiling. This allows updating multiple uses of the producer and also update the `flow.dispatch.tensor.store` operations to use tiled versions of this operation. This also allows handling dispatches where multiple results are returned. Issue #10228
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.
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!
See our website for more information.
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.