commit | 91bb1ba4607b91a51750ae7c4f9ddf506b600cf1 | [log] [tgz] |
---|---|---|
author | Lei Zhang <antiagainst@google.com> | Fri Nov 11 09:48:03 2022 -0800 |
committer | GitHub <noreply@github.com> | Fri Nov 11 17:48:03 2022 +0000 |
tree | 3848232fe1844e0665af5e6533ca667f8596bafa | |
parent | c4282ca4f3f516bde35bdb47cc57de9d1c23e981 [diff] |
[spirv] Fix missing tiling for bufferization generated fill ops (#11092) Bufferization, particularly `ConvertToDestinationPassingStyle`, can create new `linalg.fill` ops. These new ops won't have lowering configuration on them so they can miss tiling, which causes correctness issues. So this commit changes to avoid propagating lowering configuration at the time of deducing which pipeline to use; instead we query the only configuration in each pass pipeline before doing tiling.
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.