There are close to five million apps that run on more than a billion smartphones as of 2020 [1] . This number is likely to continue increasing rapidly with the technological advancements in mobile computing, smaller form-factor wearable computers, and the Internet-of-Things (IoT) devices. Although form factors and specific system requirements vary, mobile platforms share common design goals, which include energy-efficiency, competitive performance, battery life, and reliability. Competitive performance requires faster operating frequency and leads to higher power consumption. In turn, power consumption increases the junction and skin temperatures, which have adverse effects on the device reliability and user experience. Therefore, highly heterogeneous systems-on-chips (SoCs) are required to achieve the performance requirements in terms of tight power consumption, energy, and cost. The design of these platforms remains challenging. Moreover, application development, let alone aggressive optimization, is notoriously difficult and time-consuming when utilizing highly specialized accelerators. The optimization problem is exacerbated by dynamic variations of application workloads and operating conditions. As a result, there is a need for novel software- and hardware-based adaptive resource management approaches that consider the platform as a whole, rather than focusing on a subset of the target system.

中文翻译：

---

客座编辑介绍：移动平台的设计和管理：从智能手机到可穿戴设备

有近距离 到2020年，将有500万个应用程序在超过10亿部智能手机上运行 [1] 。随着移动计算，更小尺寸的可穿戴计算机和物联网（IoT）设备的技术进步，该数字可能会继续快速增长。尽管外形尺寸和特定的系统要求各不相同，但移动平台具有共同的设计目标，包括节能，竞争性能，电池寿命和可靠性。竞争性能需要更快的工作频率，并导致更高的功耗。反过来，功耗会增加结点和皮肤的温度，这会对设备的可靠性和用户体验产生不利影响。因此，需要高度异构的片上系统（SoC）来实现严格的功耗，能耗和成本方面的性能要求。这些平台的设计仍然具有挑战性。此外，使用高度专业化的加速器时，应用程序开发（更不用说积极的优化）非常困难且耗时。应用程序工作负载和操作条件的动态变化会加剧优化问题。结果，需要一种新颖的基于软件和硬件的自适应资源管理方法，该方法将平台视为一个整体，而不是关注目标系统的子集。