In this work, the unique power measurement capabilities of the Cray XT architecture were exploited to gain an understanding of power and energy use, and the effects of tuning both CPU and network bandwidth. Modifications were made to deterministically halt cores when idle. Additionally, capabilities were added to alter operating P-state. At the application level, an understanding of the power requirements of a range of important DOE/NNSA production scientific computing applications running at large scale is gained by simultaneously collecting current and voltage measurements on the hosting nodes. The effects of both CPU and network bandwidth tuning are examined, and energy savings opportunities without impact on run-time performance are demonstrated. This research suggests that next-generation large-scale platforms should not only approach CPU frequency scaling differently, but could also benefit from the capability to tune other platform components to achieve more energy-efficient performance.

High Performance Computing Systems and Applications contains fully refereed papers from the 15th Annual Symposium on High Performance Computing. These papers cover both fundamental and applied topics in HPC: parallel algorithms, distributed systems and architectures, distributed memory and performance, high level applications, tools and solvers, numerical methods and simulation, advanced computing systems, and the emerging area of computational grids. High Performance Computing Systems and Applications is suitable as a secondary text for graduate level courses, and as a reference for researchers and practitioners in industry.

Because hardware technology appears unable to provide continuing speed increases, and because parallel architectures and software are not sufficiently developed to provide the practical solutions that have seemed tantalizingly close for some time, computing as a whole is at a crossroads. Even after more than a decade of commercial development, no standard or widely accepted systems have emerged. However, this text defines practical parallelism tests and suggests how they can be passed by giving specific technical suggestions and outlining policy steps that should be taken. Also suggested are methods for evolving better systems from those already in use and applying the definitions of what is needed as rules of selection.

This is volume 72 of Advances in Computers, a series that began back in 1960 and is the oldest continuing series chronicling the ever-changing landscape of information technology. Each year three volumes are produced, which present approximately 20 chapters that describe the latest technology in the use of computers today. In this volume 72, we present the current status in the development of a new generation of high-performance computers. The computer today has become ubiquitous with millions of machines being sold (and discarded) annually. Powerful machines are produced for only a few hundred U.S. dollars, and one of the problems faced by vendors of these machines is that, due to the continuing adherence to Moore's law, where the speed of such machines doubles about every 18 months, we typically have more than enough computer power for our needs for word processing, surfing the web, or playing video games. However, the same cannot be said for applications that require large powerful machines. Applications such as weather and climate prediction, fluid flow for designing new airplanes or automobiles, or nuclear plasma flow require as much computer power as we can provide, and even that is not enough. Today's machines operate at the teraflop level (trillions of floating point operations per second) and this book describes research into the petaflop region (1,015 FLOPS). The six chapters provide an overview of current activities that will provide for the introduction of these machines in the years 2011 through 2015.

High Performance Computing Demystified provides an overview of high performance resources and their applications across many disciplines. This book is organized into five parts encompassing 16 chapters that cover the principles, mode of operation, and practical aspects of supercomputers. The first and second parts provide a brief history of high performance computing and describe the "basic parts needed to build high performance computers, including high performance microprocessors and network topologies. The third part examines the features of multiprocessor architectures of high performance, such as the large number crunchers, massively parallel processing machines, and networks of workstations. The fourth part deals with the software paradigms for high performance, while the fifth part looks into the high performance computing resources that are available to the public, with some guide to accessing those resources. This book is intended primarily for engineers and business managers who have a basic understanding of computers and would like to learn about high performance computing.

Industrial Applications of High-Performance Computing: Best Global Practices offers a global overview of high-performance computing (HPC) for industrial applications, along with a discussion of software challenges, business models, access models (e.g., cloud computing), public-private partnerships, simulation and modeling, visualization, big data a

Performance Computing: Modern Systems and Practices is a fully comprehensive and easily accessible treatment of high performance computing, covering fundamental concepts and essential knowledge while also providing key skills training. With this book, students will begin their careers with an understanding of possible directions for future research and development in HPC, domain scientists will learn how to use supercomputers as a key tool in their quest for new knowledge, and practicing engineers will discover how supercomputers can employ HPC systems and methods to the design and simulation of innovative products. This new edition has been fully updated, and has been reorganized and restructured to improve accessibility for undergraduate students while also adding trending content such as machine learning and a new chapter on CUDA. - Covers enabling technologies, system architectures and operating systems, parallel programming languages and algorithms, scientific visualization, correctness and performance debugging tools and methods, GPU accelerators, and big data problems - Provides numerous examples that explore the basics of supercomputing while also providing practical training in the real use of high-end computers - Helps users with informative and practical examples that build knowledge and skills through incremental steps - Features sidebars of background and context to present a live history and culture of this unique field

This timely text/reference describes the development and implementation of large-scale distributed processing systems using open source tools and technologies. Comprehensive in scope, the book presents state-of-the-art material on building high performance distributed computing systems, providing practical guidance and best practices as well as describing theoretical software frameworks. Features: describes the fundamentals of building scalable software systems for large-scale data processing in the new paradigm of high performance distributed computing; presents an overview of the Hadoop ecosystem, followed by step-by-step instruction on its installation, programming and execution; Reviews the basics of Spark, including resilient distributed datasets, and examines Hadoop streaming and working with Scalding; Provides detailed case studies on approaches to clustering, data classification and regression analysis; Explains the process of creating a working recommender system using Scalding and Spark.

The hands-on guide to high-performance coding and algorithm optimization. This hands-on guide to software optimization introduces state-of-the-art solutions for every key aspect of software performance - both code-based and algorithm-based. Two leading HP software performance experts offer comparative optimization strategies for RISC and for the new Explicitly Parallel Instruction Computing (EPIC) design used in Intel IA-64 processors. Using many practical examples, they offer specific techniques for: Predicting and measuring performance - and identifying your best optimization opportunities Storage optimization: cache, system memory, virtual memory, and I/0 Parallel processing: distributed-memory and shared-memory (SMP and ccNUMA) Compilers and loop optimization Enhancing parallelism: compiler directives, threads, and message passing Mathematical libraries and algorithms Whether you're a developer, ISV, or technical researcher, if you need to optimize high-performance software on today's leading processors, one book delivers the advanced techniques and code examples you need: Software Optimization for High Performance Computing.

High Performance Computing is an integrated computing environment for solving large-scale computational demanding problems in science, engineering and business. Newly emerging areas of HPC applications include medical sciences, transportation, financial operations and advanced human-computer interface such as virtual reality. High performance computing includes computer hardware, software, algorithms, programming tools and environments, plus visualization. The book addresses several of these key components of high performance technology and contains descriptions of the state-of-the-art computer architectures, programming and software tools and innovative applications of parallel computers. In addition, the book includes papers on heterogeneous network-based computing systems and scalability of parallel systems. The reader will find information and data relative to the two main thrusts of high performance computing: the absolute computational performance and that of providing the most cost effective and affordable computing for science, industry and business. The book is recommended for technical as well as management oriented individuals.