A Capabilities-Aware Framework for Using Computational Accelerators in Data-Intensive Computing

Multicore computational accelerators such as GPUs are now commodity components for highperformance computing at scale. While such accelerators have been studied in some detail as stand-alone computational engines, their integration in large-scale distributed systems raises new challenges and trade-offs. In this paper, we present an exploration of resource management alternatives for building asymmetric accelerator-based distributed systems. We present these alternatives in the context of a capabilities-aware framework for data-intensive computing, which uses an enhanced implementation of the MapReduce programming model for accelerator-based clusters, compared to the state of the art. The framework can transparently utilize heterogeneous accelerators for deriving high performance with low programming effort. Our work is the first to compare heterogeneous types of accelerators, GPUs and a Cell processors, in the same environment and the first to explore the trade-offs between compute-efficient and control-efficient accelerators on data-intensive systems. Our investigation shows that our framework scales well with the number of different compute nodes. Furthermore, it runs simultaneously on two different types of accelerators, successfully adapts to the resource capabilities, and performs 26.9% better on average than a static execution approach.

Approaches to the Implementation of the Water Framework Directive: Targeting Mitigation Measures at Critical Source Areas of Diffuse Phosphorus in Irish Catchments

The Water Framework Directive (WFD) has initiated a shift towards a targeted approach to implementation through its focus on river basin districts as management units and the natural ecological characteristics of waterbodies. Due to its role in eutrophication, phosphorus (P) has received considerable attention, resulting in a significant body of research, which now forms the evidence base for the programme of measures (POMs) adopted in WFD River Basin Management Plans (RBMP). Targeting POMs at critical sources areas (CSAs) of P could significantly improve environmental efficiency and cost effectiveness of proposed mitigation strategies. This paper summarises the progress made towards targeting mitigation measures at CSAs in Irish catchments. A review of current research highlights that knowledge related to P export at field scale is relatively comprehensive however; the availability of site-specific data and tools limits widespread identification of CSA at this scale. Increasing complexity of hydrological processes at larger scales limits accurate identification of CSA at catchment scale. Implementation of a tiered approach, using catchment scale tools in conjunction with field-by-field surveys could decrease uncertainty and provide a more practical and cost effective method of delineating CSA in a range of catchments. Despite scientific and practical uncertainties, development of a tiered CSA-based approach to assist in the development of supplementary measures would provide a means of developing catchment-specific and cost-effective programmes of measures for diffuse P. The paper presents a conceptual framework for such an approach, which would have particular relevance for the development of supplementary measures in High Status Waterbodies (HSW). The cost and resources necessary for implementation are justified based on HSWs’ value as undisturbed reference condition ecosystems.