English(EN) Ariel-ML: Computing Parallelization with Embedded Rust for Neural Networks on Heterogeneous Multi-core Microcontrollers

Ariel-ML工具包支持在多核微控制器上进行基于Rust的并行神经网络推理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-28 04:00

一个名为Ariel-ML的新工具包已被开发出来，用于使用嵌入式Rust在多核微控制器上自动化神经网络推理的并行化。该工具包旨在利用各种32位微控制器中存在的异构多核架构的能力，包括Arm Cortex-M、RISC-V和ESP-32系列。基准测试表明，与现有的解决方案相比，Ariel-ML实现了更低的推理延迟，同时保持了与使用C/C++的工具包相当的内存占用。 AI

影响能够更有效地在低功耗、多核嵌入式系统上部署AI模型。

排序理由详细介绍用于嵌入式AI的新软件工具包的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍用于嵌入式AI的新软件工具包的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 128 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Zhaolan Huang, Kaspar Schleiser, Gyungmin Myung, Emmanuel Baccelli · 2026-05-28 04:00

Ariel-ML：异构多核微控制器上用于神经网络的嵌入式 Rust 计算并行化

arXiv:2512.09800v2 Announce Type: replace Abstract: Low-power microcontroller (MCU) hardware is currently evolving from single-core architectures to predominantly multi-core architectures. In parallel, new embedded software building blocks are more and more written in Rust, while…

本文如何被排名

报道来源 [1]

Ariel-ML：异构多核微控制器上用于神经网络的嵌入式 Rust 计算并行化

相关实体

相关话题