| commit | 8fb26804c67978869a711b4bb4b8004322b2ae23 | [log] [tgz] |
|---|---|---|
| author | Benoit Jacob <benoitjacob@google.com> | Wed Jan 10 16:14:23 2024 -0500 |
| committer | GitHub <noreply@github.com> | Wed Jan 10 16:14:23 2024 -0500 |
| tree | 702570cbcb125f2e277fccc43c53b9e24273a326 | |
| parent | 4786ebcd0a536205e26e3a34cbe8ae1adaf021cb [diff] |
Disable loop unrolling in LLVM IR optimization passes (#16092) We've been discussing that for a long time and have been using that locally for benchmarking. With LLVM loop unrolling, the reduction loop in the mmt4d ukernel gets 8x-partially unrolled and pipelined, a large code size increase for no observable performance benefit.
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.