| commit | ab848fc2b876a7dd3665abafa00bb9ca29fc3924 | [log] [tgz] |
|---|---|---|
| author | Lei Zhang <antiagainst@google.com> | Tue Mar 21 12:18:04 2023 -0700 |
| committer | Lei Zhang <antiagainst@google.com> | Tue Jun 13 21:17:32 2023 -0700 |
| tree | ef5b04f057b0f3bc4fd75601ad7e37770d7b5145 | |
| parent | 472bbbe604e6cd9f272e2bdc6806b2fda94ad759 [diff] |
[metal] Enable real async execution on GPU This commit drops `legacy_sync` path from Metal HAL driver, where we were forcing waiting all semaphores before all queue execution. This requires us to track lifetimes of resources involved in queue execution better, particularly we need to make sure semaphores and command buffers aren't released until they are not needed by the GPU.
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.