commit | ba9ea8590cd01a3cfaf058a0000da47c052a1a7a | [log] [tgz] |
---|---|---|
author | Max191 <44243577+Max191@users.noreply.github.com> | Fri Aug 02 12:29:26 2024 -0700 |
committer | GitHub <noreply@github.com> | Fri Aug 02 15:29:26 2024 -0400 |
tree | a8b1041894aeb212c659407b38987ffaa50e0ce7 | |
parent | e40e64e23e3eaca95b9474e15000349b2c5203fb [diff] |
[LLVMGPU] Add im2col pipeline for convolution codegen (#18086) This PR adds the remaining needed passes for the IGEMM pipeline using the im2col op. It adds the `Conv2DToIm2colOp` pass with a flag `--iree-codegen-llvmgpu-use-igemm`, and it adds the im2col decomposition pass before vectorization passes. `--iree-codegen-llvmgpu-use-igemm` will be false by default until the IGEMM pipeline is more robust and performant. --------- Signed-off-by: Max Dawkins <max.dawkins@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.