commit | 8f13c64088f3733b52d43e8a7b2d155c799f5c3e | [log] [tgz] |
---|---|---|
author | Ben Vanik <benvanik@google.com> | Tue Dec 21 14:10:12 2021 -0800 |
committer | Ben Vanik <benvanik@google.com> | Tue Dec 21 14:42:44 2021 -0800 |
tree | c5986ed2258236c3c7772cc754cf3ba0cc737d52 | |
parent | 7a50053bb9fc81e6f1cf668ec200c60a2848d1dd [diff] |
Adding iree_hal_allocator_t::deallocate_buffer. This allows for allocators to control buffer deallocation including reusing the iree_hal_buffer_t allocs. The `device_allocator` specified on buffers is optionally used to do this routing and if omitted then the buffers are freed on their own. Nested allocator setsup can tag themselves on the iree_hal_buffer_t they provide and rely on allocated_buffer to chain. For example, a subspan buffer would have no device_allocator and reference an underlying allocated_buffer that may - and that allocated_buffer may have an allocated_buffer of its own having a different device_allocator.
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.