Cloud Benchmarking For Maximising Performance of Scientific Applications

How can applications be deployed on the cloud to achieve maximum performance? This question is challenging to address with the availability of a wide variety of cloud Virtual Machines (VMs) with different performance capabilities. The research reported in this paper addresses the above question by proposing a six step benchmarking methodology in which a user provides a set of weights that indicate how important memory, local communication, computation and storage related operations are to an application. The user can either provide a set of four abstract weights or eight fine grain weights based on the knowledge of the application. The weights along with benchmarking data collected from the cloud are used to generate a set of two rankings - one based only on the performance of the VMs and the other takes both performance and costs into account. The rankings are validated on three case study applications using two validation techniques. The case studies on a set of experimental VMs highlight that maximum performance can be achieved by the three top ranked VMs and maximum performance in a cost-effective manner is achieved by at least one of the top three ranked VMs produced by the methodology.

Multi-Tenant Virtual GPUs for Optimising Performance of a Financial Risk Application

Graphics Processing Units (GPUs) are becoming popular accelerators in modern High-Performance Computing (HPC) clusters. Installing GPUs on each node of the cluster is not efficient resulting in high costs and power consumption as well as underutilisation of the accelerator. The research reported in this paper is motivated towards the use of few physical GPUs by providing cluster nodes access to remote GPUs on-demand for a financial risk application. We hypothesise that sharing GPUs between several nodes, referred to as multi-tenancy, reduces the execution time and energy consumed by an application. Two data transfer modes between the CPU and the GPUs, namely concurrent and sequential, are explored. The key result from the experiments is that multi-tenancy with few physical GPUs using sequential data transfers lowers the execution time and the energy consumed, thereby improving the overall performance of the application.

Improving Smartphones Battery Life by Reducing Energy Waste of Background Applications

Smartphones have undergone a remarkable evolution over the last few years, from simple calling devices to full fledged computing devices where multiple services and applications run concurrently. Unfortunately, battery capacity increases at much slower pace, resulting as a main bottleneck for Internet connected smartphones. Several software-based techniques have been proposed in the literature for improving the battery life. Most common techniques include data compression, packet aggregation or batch scheduling, offloading partial computations to cloud, switching OFF interfaces (e.g., WiFi or 3G/4G) periodically for short intervals etc. However, there has been no focus on eliminating the energy waste of background applications that extensively utilize smartphone resources such as CPU, memory, GPS, WiFi, 3G/4G data connection etc. In this paper, we propose an Application State Proxy (ASP) that suppresses/stops the applications on smartphones and maintains their presence on any other network device. The applications are resumed/restarted on smartphones only in case of any event, such as a new message arrival. In this paper, we present the key requirements for the ASP service and different possible architectural designs. In short, the ASP concept can significantly improve the battery life of smartphones, by reducing to maximum extent the usage of its resources due to background applications.

Challenges and Opportunities in Edge Computing

Many cloud-based applications employ a data centre as a central server to process data that is generated by edge devices, such as smartphones, tablets and wearables. This model places ever increasing demands on communication and computational infrastructure with inevitable adverse effect on Quality-of-Service and Experience. The concept of Edge Computing is predicated on moving some of this computational load towards the edge of the network to harness computational capabilities that are currently untapped in edge nodes, such as base stations, routers and switches. This position paper considers the challenges and opportunities that arise out of this new direction in the computing landscape.