commit | 4a97b005b8bc553df8adcec7f78d3fddaa0a7d6b | [log] [tgz] |
---|---|---|
author | Cindy Liu <hcindyl@google.com> | Tue Jun 21 18:55:20 2022 -0700 |
committer | Cindy Liu <hcindyl@google.com> | Wed Jun 22 14:49:48 2022 -0700 |
tree | ad99ef4a09e594b6ec297b70e0cf897685c9d8d6 | |
parent | 49b844ad2d2873230b45a3faf5b5887ab904084e [diff] |
Update IREE_DATA_ALIGNAS_PTR to be 512b aligned It's the minimum alignment on avx512. For 32-bit targets, this could add 56 bytes of padding in the bytecode, which we can try to reduce later. The extra padding can resolve the misalignment issue in 32-bit targets.
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.