当前位置:
X-MOL 学术
›
arXiv.cs.PF
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Leveraging Transprecision Computing for Machine Vision Applications at the Edge
arXiv - CS - Performance Pub Date : 2021-08-29 , DOI: arxiv-2108.12914 Umar Ibrahim Minhas, Lev Mukhanov, Georgios Karakonstantis, Hans Vandierendonck, Roger Woods
arXiv - CS - Performance Pub Date : 2021-08-29 , DOI: arxiv-2108.12914 Umar Ibrahim Minhas, Lev Mukhanov, Georgios Karakonstantis, Hans Vandierendonck, Roger Woods
Machine vision tasks present challenges for resource constrained edge
devices, particularly as they execute multiple tasks with variable workloads. A
robust approach that can dynamically adapt in runtime while maintaining the
maximum quality of service (QoS) within resource constraints, is needed. The
paper presents a lightweight approach that monitors the runtime workload
constraint and leverages accuracy-throughput trade-off. Optimisation techniques
are included which find the configurations for each task for optimal accuracy,
energy and memory and manages transparent switching between configurations. For
an accuracy drop of 1%, we show a 1.6x higher achieved frame processing rate
with further improvements possible at lower accuracy.
中文翻译:
在边缘机器视觉应用中利用超精密计算
机器视觉任务对资源受限的边缘设备提出了挑战,特别是当它们执行具有可变工作负载的多个任务时。需要一种可以在运行时动态适应同时在资源限制内保持最高服务质量 (QoS) 的稳健方法。该论文提出了一种轻量级方法,可监控运行时工作负载约束并利用准确性与吞吐量的权衡。优化技术包括为每个任务寻找配置以获得最佳精度、能量和内存,并管理配置之间的透明切换。对于 1% 的精度下降,我们显示实现的帧处理速率提高了 1.6 倍,并且可能在较低精度下进一步改进。
更新日期:2021-08-31
中文翻译:
在边缘机器视觉应用中利用超精密计算
机器视觉任务对资源受限的边缘设备提出了挑战,特别是当它们执行具有可变工作负载的多个任务时。需要一种可以在运行时动态适应同时在资源限制内保持最高服务质量 (QoS) 的稳健方法。该论文提出了一种轻量级方法,可监控运行时工作负载约束并利用准确性与吞吐量的权衡。优化技术包括为每个任务寻找配置以获得最佳精度、能量和内存,并管理配置之间的透明切换。对于 1% 的精度下降,我们显示实现的帧处理速率提高了 1.6 倍,并且可能在较低精度下进一步改进。