Java, with its dynamic runtime environment and garbage collected GC memory management, is a very popular choice for big data processing engines. Its runtime provides convenient mechanisms to implement workload distribution without having to worry about direct memory allocation and deallocation. However, efficient memory usage is a recurring issue. In particular, our evaluation shows that garbage collection has huge drawbacks when handling a large number of data objects and more than 60% of execution time can be consumed by garbage collection. We present a set of unconventional strategies to counter this issue that rely on data layout transformations to drastically reduce the number of objects, and on changing the code structure to reduce the lifetime of objects. We encapsulate the implementation in Apache Spark making it transparent for software developers. Our preliminary results show an average speedup of 1.54 and a highest of 8.23 over a range of applications, datasets and GC types. In practice, this can provide a substantial reduction in execution time or allow a sizeable reduction in the amount of compute power needed for the same task.

Stix is a platform managing emerging large-scale broadband wireless access (BWA) networks. It has been developed to make it easy to manage such networks for community deployments and wireless Internet service providers while keeping the network management infrastructure scalable and flexible. Stix is based on the notions of goal-oriented and in-network management. With Stix, administrators graphically specify network management activities as workflows, which are deployed at a distributed set of agents within the network that cooperate in executing those workflows and storing management information. We implement the Stix system on embedded boards and show that the implementation has a low memory footprint. Using real topology and logging data from a large-scale BWA network operator, we show that Stix is significantly more scalable (via reduction in management traffic) compared to the commonly employed centralized management approach. Finally we use two case studies to demonstrate the ease with which Stix platform can be used for carrying out network reconfiguration and performance management tasks, thereby also showing its potential as a flexible platform to realize self-management mechanisms.

Embedded systems have successfully entered a broad variety of application domains such as automotive and industrial control, telecommunications, networking, digital media, consumer equipment, office automation and many more. In this paper we investigate if there exist any fundamental differences between application domains that justify the development and tuning of domain-specific compilers. We develop an automated approach that is capable of identifying domain-specific workload characterizations and presenting them in a readily interpretable format based on decision trees. The generated workload profiles summarize key resource utilization issues and enable compiler engineers to address the highlighted bottlenecks. We have evaluated our methodology against the industrial EEMBC benchmark suite and three popular embedded processors and have found that workload profiles differ significantly between application domains. We demonstrate that these characteristics can be exploited for the development of domain-specific compiler optimizations. In a case study we show average performance improvements of up to 44% for a class of networking applications.