| commit | a60f2dc862f1538c69f9125a7b1e81c5c9e4ba14 | [log] [tgz] |
|---|---|---|
| author | Quinn Dawkins <quinn.dawkins@gmail.com> | Tue Jan 30 10:50:46 2024 -0800 |
| committer | GitHub <noreply@github.com> | Tue Jan 30 18:50:46 2024 +0000 |
| tree | b006907657dc495ca0862337da4a39ad763a3ec7 | |
| parent | cc2e2c210eaa29ebd15f861f2e213eee2e69e73e [diff] |
[Codegen] Use the lane ID to do transfer distribution (#16260) Previously the transfer distribution patterns were expecting a list of thread indices to distribute to, but then distributing along the lane dimensions. The lane dimensions are a logical grid based on the lane index, which is the linearized thread index % warp size, so we need to compute the lane index based on the particular layout of the transfer rather than passing in a global grid of threads.
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.