Download Data intensive Computing By Gracio, Deborah K.,Gorton, Ian

Sinopsis

In our world of rapid technological change, occasionally it is instructive to contemplate how much has altered in the last few years. Remembering life without the ability to view the World Wide Web (WWW) through browser windows will be difficult, if not impossible, for less “mature” readers. Is it only seven years since YouTube first appeared, a Web site that is now ingrained in many facets of modern life? How did we survive without Facebook all those (actually, about five) years ago?

In 2010, various estimates put the amount of data stored by consumers and businesses around the world in the vicinity of 13 exabytes, with a growth rate of 20 to 25 percent per annum. That is a lot of data. No wonder IBM is pursuing building a 120-petabyte storage array.1 Obviously there is going to be a market for such devices in the future. As data volumes of all types – from video and photos to text documents and binary files for science – continue to grow in number and resolution, it is clear that we have genuinely entered the realm of data-intensive computing, or as it is often now referred to, big data.2 Interestingly, the term “data-intensive computing” was actually coined by the scientific community. Traditionally, scientific codes have been starved of sufficient compute cycles, a paucity that has driven the creation of ever larger and faster high-performance computing machines, typically known as supercomputers.

The Top 500 Web site3 shows the latest benchmark results that characterize the fastest supercomputers on the planet. While this fascination with compute performance continues, scientific computing has been gradually coming to terms with the challenges brought by ever-increasing data size and complexity. In 1998, William Johnston’s paper at the Seventh IEEE Symposium on High Performance Distributed Computing [1] described the evolution of data-intensive computing over the previous decade. The achievements described in that paper, while state of the art at the time, now seem modest in comparison to the scale of the problems that are routinely tackled in present-day data-intensive computing applications.

More recently, others including Hey and Trefethen [2], Bell et al. [3], and Newman et al. [4] have described the magnitude of the data-intensive problems faced by the e-science community. Their descriptions of the data deluge that future applications must process, in domains ranging from science to business informatics, create a compelling argument for research and development (R&D) to be targeted at discovering scalable hardware and software solutions for dataintensive problems. While multi-petabyte data sets and gigabit data streams are today’s frontier of data-intensive applications, no doubt ten years from now we will fondly reminisce about these problems, and will be concerned about the looming exascale applications we need to address.

Figure 1.1 lists the general features of traditional computational science applications and their data-intensive counterparts. The former focuses more on solving mathematical equations for static data sets, whereas the latter is concerned with more exploratory search and processing of large, dynamic, and complex data collections.

Content

1. Data-Intensive Computing: A Challenge for the 21st Century  Ian Gorton and Deborah K. Gracio
2. Anatomy of Data-Intensive Computing Applications Ian Gorton and Deborah K. Gracio
3. Hardware Architectures for Data-Intensive Computing Problems: A Case Study for String Matching Antonino Tumeo, Oreste Villa, and Daniel Chavarr´ıa-Miranda
4. Data Management Architectures Terence Critchlow, Ghaleb Abdulla, Jacek Becla, Kerstin Kleese-Van Dam, Sam Lang, and Deborah L. McGuinness
5. Large-Scale Data Management Techniques in Cloud Computing Platforms Sherif Sakr and Anna Liu
6. Dimension Reduction for Streaming Data Chandrika Kamath
7. Binary Classification with Support Vector Machines Patrick Nichols, Bobbie-Jo Webb-Robertson, and Christopher Oehmen
8. Beyond MapReduce: New Requirements for Scalable Data Processing Bill Howe and Magdalena Balazinska

Click here to download