| commit | b697e7655bd2fe70a35a1636fb12f65a2c84a86f | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Wed Jun 15 12:07:58 2022 -0700 |
| committer | GitHub <noreply@github.com> | Wed Jun 15 12:07:58 2022 -0700 |
| tree | b4ee791e0a696109156a8fc7b63ef3777a44e8da | |
| parent | 7d464fa907e557e2f482c199b5e1fbe4e21cc0a1 [diff] |
Enabling bytecode module coroutine begin/resume. (#9497) iree_vm_bytecode_dispatch_begin now begins a call and if it does not complete prior to returning the caller can repeatedly issue iree_vm_bytecode_dispatch_resume until it does. Invocations are marked with fiber enter/leave to allow tracy to visualize them. Unfortunately due to proper nesting requirements we can't do the fiber management at a more common level and instead will need each implementation to manage it around their execution. Future changes will update iree/vm/invocation.h to support stateful coroutine-style invocations with a prettier API. This is just the internals to verify that the bytecode dispatch supports it. Progress on #8093.
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.