The Continuing Education Program of the Gerontological Society, through its grant and contract from Branch NIMH, is pleased to present following paper. We believe this compilation a broad range mental health treatment modalities will be useful aid in-service education staff development programs.1

We explore the advantages of using Erasure Codes (ECs) in a very challenging sensor networking scenario, namely, monitoring and tracking bats wild. The mobile bat nodes collect contact information that needs to be transmitted stationary base stations whenever they are communication range. particularly interested improving overall reliability wireless communication. capable storing few 100kB data exchange aggregated form. Due continuous flight forest environment, channel quality varies...

The carbon footprint of software activities is determined by embodied and operational emissions hardware resources. This paper presents cMemento, a concept that enables operating systems to make carbon-aware memory placement decisions. Main has become heterogeneous in today's computer systems. In addition traditional (and volatile) main (e.g. DRAM), novel technologies with persistent properties are often also available PRAM, FRAM, MRAM). Complementary, there large number new interfaces...

The need for high performance in embedded devices grows at a breathtaking pace. Embedded processors that satisfy the hunger superlative processing power share common issue: increasing leads to growing energy demands during operation. As remains limited resource devices, it is critical optimise software components low power. Low-power needs models which, however, are increasingly difficult create as complexity of today's devices.

The carbon footprint of software activities is determined by embodied and operational emissions hardware resources. This paper presents cMemento, a concept that enables operating systems to make carbon-aware memory placement decisions.

For the design and operation of today's computer systems, power energy requirements are highest priorities. Unlike performance analyses, however, measurements heterogeneous systems difficult to conduct. Especially at system-software level, performing remains challenging. Yet, such essential improve software components for low high energy-efficiency.In this paper, we analyze discuss characteristics several with up 20 cores (160 hardware threads) 1 TB main memory. analyzed outline challenges...

Edge computing systems need to use their available resources efficiently. Operating and run-time offer numerous configuration parameters fine-tune behaviour, which are adjustable balance the execution time energy demand of applications. However, number produces a vast space possible configurations exact consequences on non-functional properties often poorly documented. Thus, identifying efficient proves challenging.

The Meltdown and Spectre hardware vulnerabilities shocked manufacturers system users upon discovery. Numerous attack vectors mitigations have been developed deployed. However, due to the deep entanglement in core CPU components they will be an important topic for years. Although performance overhead of software has examined closely, energy experienced little attention---even though demand is a critical cost factor data centres.

Operating systems rely on system calls to allow the controlled communication of isolated processes with kernel and other processes. Every call includes a processor mode switch from unprivileged user privileged mode. Although switches are essential isolation mechanism guarantee system's integrity, they induce direct indirect performance costs as invalidate parts state. In recent years, high-performance networks storage hardware has made user/kernel transition overhead bottleneck for IO-heavy...

To reduce the carbon footprint of software, it is imperative that systems first become aware their footprint. Despite various proposals to make software via application-level development kits, we believe awareness and adjustment carbon-emission information an operating-system duty---similar how manages time today. In this paper, motivate envision carbond, a Linux-based service mediate between hardware (including power supply) software. Following recently established Software Carbon Intensity...

Interrupt handling with predictably low latency is a must for systems to respond external events. System designers of tiny embedded computers large-scale distributed face the challenge ever-increasing hardware and software complexity. In absence precise timing models, measurement-based approaches are required achieve latency. this paper, we present INTspect, tool that systematically evaluates interrupt latency, at run-time, in Linux operating system kernel. We apply INTspect on two distinct...

Machine learning has shown tremendous success in a large variety of applications. The evolution machine-learning applications from cloud-based systems to mobile and embedded devices shifted the focus only quality-related aspects towards resource demand machine learning. For systems, dedicated accelerator hardware promises energy-efficient execution neural network inferences. Their precise terms time power demand, however, is undocumented. Developers, therefore, face challenge fine-tune their...

To reduce the carbon footprint of software, it is imperative that systems first become aware their footprint. Despite various proposals to make software via application-level development kits, we believe awareness and adjustment carbon-emission information an operating-system duty---similar how manages time today. In this paper, motivate envision carbond, a Linux-based service mediate between hardware (including power supply) software. Following recently established Software Carbon Intensity...

The recent restructuring of the electricity grid (i.e., smart grid) introduces a number challenges for today's large-scale computing systems. To operate reliable and efficient, systems must adhere not only to technical limits thermal constraints) but they also reduce operating costs, example, by increasing their energy efficiency. Efforts improve efficiency, however, are often hampered inflexible software components that hardly adapt underlying hardware characteristics. In this paper, we...

Artificial Intelligence (AI) has changed our daily lives. The evolution from centralised cloud-hosted services towards embedded and mobile devices shifted the focus quality-related aspects resource demand of machine learning. Its pervasiveness demands for "green" AI---both development operation AI models still include significant investments in terms processing time power demand. In order to prevent such Waste, this paper presents Precious, an approach, as well practical implementation, that...

Edge systems enable large numbers of embedded nodes to communicate in order cooperate towards achieving a shared goal. However, such operate under both timeliness and energy-efficiency constraints. This paper proposes X-Leep, run-time system that detects the pace system, supporting Internet-of-Things scenarios. X-Leep adapts local processing speed accordingly, considering time-related energy-related Our evaluation shows increases energy efficiency compared state art with only minor effect on...

Excessive energy consumption is a critical problem for mobile computing systems due to their limited battery capacity. Software developers aim improve efficiency by monitoring and profiling the of in order discover resolve hot-spots. However, measurement often tedious since it involves hardware setup as well software integration. To support accurate but also convenient measurements, we propose inclusion external devices into existing performance subsystems. This approach allows...

Energy has emerged to be the most important resource for computing systems. Despite exceptional importance of energy, reducing its demand at application and system level remains a challenging task programmers engineers. This is aggravated by fact that traditional energy-saving approaches are not only error-prone but even lead adverse consequences (i.e. increased energy consumption). To address this concern, we present FigarOS operating fine-grained system-level optimizations. The evaluation...

Energy efficiency has developed to one of the most important non-functional system properties. One keystone building an energy-efficient is right configuration, which tailored currently running application and hardware. Finding such a configuration manually, however, complex often unfeasible task due vast space on side required hardware knowledge other side. This paper presents refines approach automatically identify select configurations in re-configurable systems. The relies different...

Modern computing systems need to execute applications in an energy-efficient manner. To this end, operating systems, middleware, and run-time offer plenty of parameters that support fine-tuning their behaviour. However, individual combined impact on performance power draw is so complex optimisation potential often ignored practice. This paper therefore discusses a cross-layer system design uses machine learning internally enable current workload. Our approach includes all layers, from the...

Multi-core processors are commonplace and continue to require rethinking (not only) in system software development. It is still difficult operate several functionally identical computing cores efficiently. One misconception assume that of a multi-core processor will behave non-functionally alike, especially at the speed which they execute same non-sequential program. We show considerable deviations non-functional behaviour otherwise anything but unusual, can be expected vary by more than...