An Assessment of Beowulf-class Computing for NASA Requirements: Initial Findings from the First NASA Workshop on Beowulf-class Clustered Computing

نویسندگان

  • Thomas Sterling
  • Tom Cwik
چکیده

The Beowulf class of parallel computing machine started as a small research project at NASA Goddard Space Flight Center’s Center of Excellence in Space Data and Information Sciences (CESDIS). From that work evolved a new class of scalable machine comprised of mass market common off-the-shelf components (MCOTS) using a freely available operating system and industry-standard software packages. A Beowulf-class system provides extraordinary benefits in price-performance. Beowulf-class systems are in place and doing real work at several NASA research centers, are supporting NASA-funded academic research, and operating at DOE and NIH. The NASA user community conducted an intense two-day workshop in Pasadena, California on October 22-23, 1997. This first workshop on Beowulf-class systems consisted primarily of technical discussions to establish the scope of opportunities, challenges, current research activities, and directions for NASA computing employing Beowulf-class systems. The technical discussions ranged from application research to programming methodologies. This paper provides an overview of the findings and conclusions of the workshop. The workshop determined that Beowulf-class systems can deliver multiGflops performance at unprecedented price-performance but that software environments were not fully functional or robust, especially for larger “dreadnought”-scale systems. It is recommended that the Beowulf community engage in an activity to integrate, port, or develop, where appropriate, necessary components of the software infrastructure to fully realize the potential of Beowulf-class computing to meet NASA and other agency computing requirements.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Beowulf: Harnessing the Power of Parallelism in a Pile-of-PCs

| The rapid increase in performance of mass market commodity microprocessors and signiicant disparity in pricing between PCs and scientiic workstations has provided an opportunity for substantial gains in performance to cost by harnessing PC technology in parallel ensembles to provide high end capability for scien-tiic and engineering applications. The Beowulf project is a NASA initiative spons...

متن کامل

Beowulf Parallel Processing for Dynamic Load-balancing12

1 0-7803-5846-5/00/$10.00 © 2000 IEEE 2 Updated August 31, 1999 Abstract—The Beowulf parallel-processing architecture is a public-domain software technology developed by NASA to link commercial off the shelf (COTS) processors yielding super-computer performance (10 Gflops) very economically (under $150K). It has been used for applications as diverse as scalable hierarchical particle algorithms ...

متن کامل

Beowulf – A New Hope for Parallel Computing?

The Beowulf model for clusters of commodity computers[15, 17, 18] has become very popular over the last year, particularly amongst university research groups and other organisations less able to justify large procurements. The Beowulf concept is usually applied[16] to clusters of Personal Computers running Linux, but other platforms and operating systems can also be considered as providing simi...

متن کامل

Parallel Processing of High-Dimensional Remote Sensing Images Using Cluster Computer Architectures

Hyperspectral sensors represent the most advanced instruments currently available for remote sensing of the Earth. The high spatial and spectral resolution of the images supplied by systems like the Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS), developed by NASA Jet Propulsion Laboratory, allows their exploitation in diverse applications, such as detection and control of wildland fi...

متن کامل

A Beowulf-class computing cluster for the Monte Carlo production of the LHCb experiment

The computing cluster built at Bologna to provide the LHCb Collaboration with a powerful Monte Carlo production tool is presented. It is a performance oriented Beowulf-class cluster, made of rack mounted commodity components, designed to minimize operational support requirements and to provide full and continuous availability of the computing resources. In this paper we describe the architectur...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1998