commit | b07d60ccbe7753cb674d584d8a0ab3eb94c675af | [log] [tgz] |
---|---|---|
author | Lei Zhang <antiagainst@google.com> | Fri Dec 02 12:26:18 2022 -0800 |
committer | GitHub <noreply@github.com> | Fri Dec 02 12:26:18 2022 -0800 |
tree | 0a3cd20556bd6dcf05ea9ea8042db0b83056e77c | |
parent | 895cf38f45628351f8c618870504913dcbe72582 [diff] |
Plumb through support for controlling subgroup size in CodeGen (#11388) This commit plumbs through support for controlling subgroup size (i.e., VK_EXT_subgroup_size_control for Vulkan) in CodeGen: - Added a new subgroup size attribute to HAL ExecutableExportOp, similar to workgroup size there. - Extended various helper functions to optionally set subgroup size. - Defined VK_EXT_subgroup_size_control and updated various target triples regarding min/max subgroup size. This commit just thread support through CodeGen flow; it's not wired up into runtime to use yet, which will happen later.
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.