commit | 235e110f4809f3d5414619d36fac00c4e4c02551 | [log] [tgz] |
---|---|---|
author | Max191 <44243577+Max191@users.noreply.github.com> | Wed Aug 07 13:43:41 2024 -0700 |
committer | GitHub <noreply@github.com> | Wed Aug 07 20:43:41 2024 +0000 |
tree | 5347f9e897890d6a2f91e46bdad460681872a36e | |
parent | 352e05f741626c2b35e849b1a9d43165cf8378f3 [diff] |
[Codegen][GPU] Add pass to expand multi_mma op shapes to intrinsic layout (#18139) This PR adds a new pass to explicitly materialize the dimensions of intrinsic layouts for `iree_gpu.multi_mma` ops. This means adding an expand_shape on each of the inputs to go from the `OpaqueMmaLayout` shape to the `ConcreteMmaLayout` shape. This makes it easy to extract the correct data from the tensors when it is time to distribute the multi_mma op to lanes, since the shape will match the number of offsets and sizes needed for the slice. --------- Signed-off-by: Max Dawkins <max.dawkins@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.
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
Package | Release status |
---|---|
GitHub release (stable) | |
GitHub release (nightly) | |
Python iree-compiler | |
Python iree-runtime |
Host platform | Build status |
---|---|
Linux | |
macOS | |
Windows |
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
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.