No abstract

Abstract-We present the design and evaluation of the heat recovery system for KTH's Lindgren, Stockholm's fastest supercomputer, a Cray XE6. Lindgren came into service in 2010 and has since been primarily used for complex numeric simulations of fluid mechanics and computational chemistry and biology. The heat exchange system collects the wasted heat from Lindgren's 36,384 CPU cores and transfers it via the standard district heating and cooling system to a neighboring building which houses the Chemistry laboratories. We analyze the impact of Lindgren's heat recycle system as a function of outside temperature and we estimate the system's carbon emission savings. Since the original installation of Lindgren in 2010, it has become common practice to use water cooling systems for supercomputers, as water is a better heat transfer medium than air. We discuss the relevant design lessons from Lindgren as they relate to practical and sustainable waste heat recovery designs for today's platforms. Finally, we estimate that the recovered heat from Lindgren reduced the carbon emissions by nearly 50 tons over the 2012-13 winter, the sample period of our analysis.Index Terms-Supercomputer, data center, waste heat recovery, heat exchanger, waste energy reuse, urban district heating and cooling, high-performance computing.

The use of cloud computing as a new paradigm has become a reality. Cloud computing leverages the use of on-demand CPU power and storage resources while eliminating the cost of commodity hardware ownership. Cloud computing is now gaining popularity among many different organizations and commercial sectors. In this paper, we present the scalable brain image analysis (ScaBIA) architecture, a new model to run statistical parametric analysis (SPM) jobs using cloud computing. SPM is one of the most popular toolkits in neuroscience for running compute-intensive brain image analysis tasks. However, issues such as sharing raw data and results, as well as scalability and performance are major bottlenecks in the "single PC"execution model. In this work, we describe a prototype using the generic worker (GW), an e-Science as a service middleware, on top of Microsoft Azure to run and manage the SPM tasks. The functional prototype shows that ScaBIA provides a scalable framework for multi-job submission and enables users to share data securely using storage access keys across different organizations. 2 BACKGROUND In this section we give an overview of the neuroscience workflow involving SPM and describe the VENUS-C cloud architecture with a focus on the GW component used in our implementation. 2.1 SPM Overview The goal of the functional analysis of brain images is to find the parts of the brain that are activated when people (subjects) perform certain tasks. Since the signals that can be measured from the brain are noisy and there is considerable variation between

An implementation of Ada's tasking facilities, on the LSI-11 microcomputer, is described.The performance and the size of the kernel are compared with those of another language having the same basic characteristics, but with a synchronization mechanism based on shared data.The execution of typical test examples shows that the time spent in the two kernels is more or less the same.

No abstract