Transition of HPC Towards Exascale Computing ( Advances in Parallel Computing )

Publication series :Advances in Parallel Computing

Author: D'Hollander   E.H.; Dongarra  

Publisher: Ios Press‎

Publication year: 2013

E-ISBN: 9781614993247

P-ISBN(Hardback):  9781614993230

Subject: TP Automation Technology , Computer Technology

Keyword: null 自动化技术、计算机技术Automation Technology , Computer Technology

Language: ENG

Access to resources Favorite

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Description

The US, Europe, Japan and China are racing to develop the next generation of supercomputers – exascale machines capable of 10 to the 18th power calculations a second – by 2020. But the barriers are daunting: the challenge is to change the paradigm of high-performance computing.The 2012 biennial high performance workshop, held in Cetraro, Italy in June 2012, focused on the challenges facing the computing research community to reach exascale performance in the next decade. This book presents papers from this workshop, arranged into four major topics: energy, scalability, new architectural concepts and programming of heterogeneous computing systems.Chapter 1 introduces the status of present supercomputers, which are still about two orders of magnitude separated from the exascale mark. Chapter 2 examines energy demands, a major limiting factor of today's fastest supercomputers; the quantum leap in performance required for exascale computing will require a shift in architectures and technology. In Chapter 3, scalable computer paradigms for dense linear algebra on massive heterogeneous systems are presented, and Chapter 4 discusses architectural concepts. Finally, Chapter 5 addresses the programming of heterogeneous systems.This book will be of interest to all those wishing to understand how the development of modern supercomputers is set to advance in the next decade.

Chapter

Chapter 2. The Energy Challenge

Achieving the 20MW Target: Mobilizing the HPC Community to Accelerate Energy Efficient Computing

Palette: A Cache Leakage Energy Saving Technique for Green Computing

Chapter 3. Scalable Computing

Scalable Dense Linear Algebra on Heterogeneous Hardware

Achieving Scalability in the Presence of Asynchrony for Exascale Computing

Chapter 4. Architectural Concepts

The Role of Non-Strict Fine-Grain Synchronization

On the Role of Co-Design in High Performance Computing

Chapter 5. Programming Heterogeneous Architectures

Uniform High-Level Programming of Many-Core and Multi-GPU Systems

Performance and Programming Environment of a Combined GPU/FPGA Desktop

High Performance Sequence Mining Using Pairwise Statistical Significance

Subject Index

Author Index

The users who browse this book also browse


No browse record.