commit | 2912a2adbf99e1e2e7e3069bef3b06311b0b6229 | [log] [tgz] |
---|---|---|
author | MaheshRavishankar <1663364+MaheshRavishankar@users.noreply.github.com> | Mon Jul 15 13:03:52 2024 -0700 |
committer | GitHub <noreply@github.com> | Mon Jul 15 13:03:52 2024 -0700 |
tree | ca80c40c9e49dabe0c35d3f0cdcd152da081bba0 | |
parent | 0bc15180878b11473c9de25caceeffd49219fa30 [diff] |
[NFC][Flow] Remove use of fusion preprocessing when it isnt a preprocessing (#17899) The Fusion preprocessing pass was used in multiple places, which is not the intent of the pass. Remove the subsequent usage. The only reason for this double usage was for the pattern that moved reduction dimensions to the innermost. Consolidate that pattern with the pattern in `InterchangeTransposeGenericPass` (whose name is very convoluted and does not represent what it actually does). This commit also includes the following changes: - Rename `InterchangeTransposeGenericPass` to `TransposeGenericOpsPass`. - Reoder the passes in `Passes.td` to be alphabetical within each of the following portions - Dispatch region preprocessing passes - Dispatch region formation passes - General flow passes. --------- Signed-off-by: MaheshRavishankar <mahesh.ravishankar@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!
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.