| commit | 8f387c65f556495a4b3537161dea018f82e7ae81 | [log] [tgz] |
|---|---|---|
| author | Quinn Dawkins <quinn@nod-labs.com> | Wed May 10 11:55:29 2023 -0400 |
| committer | GitHub <noreply@github.com> | Wed May 10 11:55:29 2023 -0400 |
| tree | 1009641d4169945b10642e3e26bcd5a70761f333 | |
| parent | 5b89a145d02fcad42cd375b7ae447bfd672471af [diff] |
[Transform] Capture the element types of the matmul in the matcher (#13497) In the future when more than just F32 is supported, the element type will need to be captured to properly select padding values. This captures the element types in the matcher in preparation for that. This patch is nearly NFC; some of the matcher cleanup also fixes boundary conditions for cases like `input(position, ...)` which previously checked `index <= 0`. Also cleans up a test case in set_transform_strategy that wasn't properly testing the alignment condition for using the strategy.
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.