| commit | 49de0b6b8a7f3a79538f596370bacb0036886e33 | [log] [tgz] |
|---|---|---|
| author | MaheshRavishankar <1663364+MaheshRavishankar@users.noreply.github.com> | Wed Feb 22 11:04:32 2023 -0800 |
| committer | GitHub <noreply@github.com> | Wed Feb 22 19:04:32 2023 +0000 |
| tree | d7f7ee593b8b467073da8e968ce2ce181f3f6ae8 | |
| parent | 987a86441353eaa6f429fc4a02a13cb53bbde653 [diff] |
Update `ResolveBufferDescriptors` to handle `memref.extract_strided_metadata` (#12205) The pass currently is meant to handle `vmvx.get_buffer_descriptors`. This operation is very similar to the `memref.extract_strided_memref` and the logic could be re-used to handle this operation as well. This allows using the ukernel path being added to IREE which is intended to work for both VMVX and LLVM CPU codegeneration paths. The only pattern that is a bit more harder to reuse is ``` %0 = hal.interface.binding.subspan .. = vmvx.get_buffer_descriptor %0 ``` since the base buffer used by the `vmvx.get_buffer_descriptor` isn't the same type as `memref.extract_strided_memref`. That pattern is not adapted yet.
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.