A survey of high-performance computing scaling challenges. (January 2017)

• Record Type: Journal Article
• Authors: Geist, Al; Reed, Daniel A
• Is Part Of: International journal of high performance computing applications. Volume 31:Number 1(2017)
• Page Start: 104
• Page End: 113
• Publication Date: 2017-01
• Subjects: Reliability -- exascale systems -- cloud computing -- energy efficiency -- data center; High performance computing -- Periodicals; Supercomputers -- Periodicals; 004.1105
• DOI: 10.1177/1094342015597083
• Languages: English
• ISSNs: 1094-3420

Abstract

Commodity clusters revolutionized high-performance computing when they first appeared two decades ago. As scale and complexity have grown, new challenges in reliability and systemic resilience, energy efficiency and optimization and software complexity have emerged that suggest the need for re-evaluation of current approaches. This paper reviews the state of the art and reflects on some of the challenges likely to be faced when building trans-petascale computing systems, using insights and perspectives drawn from operational experience and community debates.