arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.03531cs.ARcs.AI
收藏

一种用于安全纳米无人机导航的异构RISC-V片上系统

A Heterogeneous RISC-V based SoC for Secure Nano-UAV Navigation

University of Bologna(博洛尼亚大学);Khalifa University(哈利法大学);University of Minho(米尼奥大学);ETH Zürich(苏黎世联邦理工学院);Technology Innovation Institute(技术创新研究院);Dalle Molle Institute for Artificial Intelligence (IDSIA)(达勒·莫勒人工智能研究所(IDSIA))
Luca Valente, Alessandro Nadalini, Asif Veeran, Mattia Sinigaglia, Bruno Sa, Nils Wistoff, Yvan Tortorella, Simone Benatti, Rafail Psiakis, Ari Kulmala, Baker M… 展开作者

Luca Valente, Alessandro Nadalini, Asif Veeran, Mattia Sinigaglia, Bruno Sa, Nils Wistoff, Yvan Tortorella, Simone Benatti, Rafail Psiakis, Ari Kulmala, Baker Mohammad, Sandro Pinto, Daniele Palossi, Luca Benini, Davide Rossi

AI总结:

提出Shaheen,一款22nm FDX工艺的9mm²、200mW异构RISC-V SoC,集成支持虚拟化的RV64核与RV32多核簇,实现高性能低功耗ML计算,适用于安全纳米无人机导航。

摘要:

节能型并行超低功耗(ULP)微控制器单元(MCU)的快速发展正在推动自主纳米级无人驾驶飞行器(nano-UAV)的开发。这些亚10厘米的无人机代表了下一代不显眼的机器人助手和无处不在的智能传感器。然而,纳米无人机面临显著的功率和有效载荷限制,同时需要类似于标准无人机的先进计算能力,包括实时机器学习(ML)性能和通用与实时操作系统安全共存的能力。尽管一些先进的并行ULP MCU在规定的功率限制内提供了必要的ML计算能力,但它们依赖小型主存储器(<1MB)和缺乏虚拟化或安全功能的微控制器级CPU,因此仅支持简单的裸机运行时。在这项工作中,我们提出了Shaheen,一款在22nm FDX技术中实现的9mm²、200mW的SoC。与最先进的MCU不同,Shaheen集成了一个支持Linux的RV64核心,符合已批准的v1.0 Hypervisor扩展,并配备时序通道保护,以及一个低成本和低功耗的内存控制器,直接向CPU提供高达512MB的片外低成本低功耗HyperRAM。同时,它集成了一个完全可编程的、能源和面积高效的多核RV32核心簇,针对通用DSP以及降低和混合精度ML进行了优化。据作者所知,这是首个将RV64和RV32核心在完全基于RISC-V ISA的异构主机+加速器架构中耦合的ULP SoC硅原型。我们在与纳米无人机应用相关的广泛基准上展示了所提出的SoC的能力。该簇在2位整数内核上可提供高达90GOp/s和高达1.8TOp/s/W的性能,在16位浮点内核上可提供高达7.9GFLOp/s和高达150GFLOp/s/W的性能。

英文摘要:

The rapid advancement of energy-efficient parallel ultra-low-power (ULP) ucontrollers units (MCUs) is enabling the development of autonomous nano-sized unmanned aerial vehicles (nano-UAVs). These sub-10cm drones represent the next generation of unobtrusive robotic helpers and ubiquitous smart sensors. However, nano-UAVs face significant power and payload constraints while requiring advanced computing capabilities akin to standard drones, including real-time Machine Learning (ML) performance and the safe co-existence of general-purpose and real-time OSs. Although some advanced parallel ULP MCUs offer the necessary ML computing capabilities within the prescribed power limits, they rely on small main memories (<1MB) and ucontroller-class CPUs with no virtualization or security features, and hence only support simple bare-metal runtimes. In this work, we present Shaheen, a 9mm2 200mW SoC implemented in 22nm FDX technology. Differently from state-of-the-art MCUs, Shaheen integrates a Linux-capable RV64 core, compliant with the v1.0 ratified Hypervisor extension and equipped with timing channel protection, along with a low-cost and low-power memory controller exposing up to 512MB of off-chip low-cost low-power HyperRAM directly to the CPU. At the same time, it integrates a fully programmable energy- and area-efficient multi-core cluster of RV32 cores optimized for general-purpose DSP as well as reduced- and mixed-precision ML. To the best of the authors' knowledge, it is the first silicon prototype of a ULP SoC coupling the RV64 and RV32 cores in a heterogeneous host+accelerator architecture fully based on the RISC-V ISA. We demonstrate the capabilities of the proposed SoC on a wide range of benchmarks relevant to nano-UAV applications. The cluster can deliver up to 90GOp/s and up to 1.8TOp/s/W on 2-bit integer kernels and up to 7.9GFLOp/s and up to 150GFLOp/s/W on 16-bit FP kernels.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑