| commit | 407c7094fcb80c3d1a8ce7fdb05a7eaf4a34544e | [log] [tgz] |
|---|---|---|
| author | lorenzo chelini <l.chelini@icloud.com> | Thu Oct 06 22:21:35 2022 +0200 |
| committer | GitHub <noreply@github.com> | Thu Oct 06 13:21:35 2022 -0700 |
| tree | 0ac992af7b91db3812f930a19a13a5e266f24717 | |
| parent | db4ba02b85e4d50f88173b7f488d9a99f06dd9cc [diff] |
Add UnPackOp to LinalgExt dialect (#10592) The unpack operation converts a tiled and packed input to an unpacked output. See `pack` for more details on `inner_tiles` and `dims_pos`; it is UB if the tile does not perfectly divide the dimension. Example KCck_to_KC: ```mlir iree_linalg_ext.pack %arg0 dims_pos = [1, 0] inner_tiles = [32, 8] into %arg1 : (memref<16x8x32x8xf32> memref<128x256xf32>) ``` Example NCnc_to_NC: ```mlir iree_linalg_ext.pack %arg0 dims_pos = [0, 1] inner_tiles = [8, 32] into %arg1 : (memref<16x8x8x32xf32> memref<128x256xf32>) ``` Co-authored-by: Hanhan Wang <hanchung@google.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.
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.