arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.01568cs.LGcs.DC
收藏

DynaMIX:多任务系统上基于DNN的实时的应用的资源优化

DynaMIX: Resource Optimization for DNN-Based Real-Time Applications on a Multi-Tasking System

The University of Michigan(密歇根大学)

Minkyoung Cho, Kang G. Shin

摘要:

随着深度神经网络(DNN)证明其重要性和可行性,越来越多基于DNN的应用程序(如对象的检测和分类)已被开发并部署在自动驾驶汽车(AV)上。为了满足他们不断增长的期望和要求,自动驾驶汽车应该“优化”使用其有限的车载计算资源,用于多个并发的车载应用程序,同时满足他们的时序要求(特别是安全要求)。也就是说,实时的【形】AV应用程序应与其他并发应用程序共享有限的板载资源,而不会错过由生成并向应用程序提供输入图像的相机的帧速率所规定的最后期限。然而,大多数(如果不是全部的话)现有DNN解决方案专注于增强其特定硬件的并发性,而不动态优化/修改DNN应用程序的资源需求,这取决于运行应用程序的数量,这是由于它们的高计算成本。为了缓解这一限制,我们提出了DynaMIX(动态混合精度模型构造),它优化了并发应用程序的资源需求,旨在最大限度地提高执行精度。为了实现实时的【形】的资源优化,我们制定了一个优化问题,使用应用程序的性能配置文件来考虑每个应用程序的准确性和最坏情况下的延迟。我们还提出了动态模型重新配置,通过在运行时延迟加载选定的层,以减少加载整个模型的开销。DynaMIX在多任务系统的约束满足和推理精度方面进行了评估,并与最先进的解决方案进行了比较,证明了其在各种环境/操作条件下的有效性和可行性。

英文摘要:

As deep neural networks (DNNs) prove their importance and feasibility, more and more DNN-based apps, such as detection and classification of objects, have been developed and deployed on autonomous vehicles (AVs). To meet their growing expectations and requirements, AVs should "optimize" use of their limited onboard computing resources for multiple concurrent in-vehicle apps while satisfying their timing requirements (especially for safety). That is, real-time AV apps should share the limited on-board resources with other concurrent apps without missing their deadlines dictated by the frame rate of a camera that generates and provides input images to the apps. However, most, if not all, of existing DNN solutions focus on enhancing the concurrency of their specific hardware without dynamically optimizing/modifying the DNN apps' resource requirements, subject to the number of running apps, owing to their high computational cost. To mitigate this limitation, we propose DynaMIX (Dynamic MIXed-precision model construction), which optimizes the resource requirement of concurrent apps and aims to maximize execution accuracy. To realize a real-time resource optimization, we formulate an optimization problem using app performance profiles to consider both the accuracy and worst-case latency of each app. We also propose dynamic model reconfiguration by lazy loading only the selected layers at runtime to reduce the overhead of loading the entire model. DynaMIX is evaluated in terms of constraint satisfaction and inference accuracy for a multi-tasking system and compared against state-of-the-art solutions, demonstrating its effectiveness and feasibility under various environmental/operating conditions.

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。

↑