The International Exascale Software Project roadmap

被引:355
作者
Dongarra, Jack [1 ]
Beckman, Pete [1 ]
Moore, Terry [1 ]
Aerts, Patrick [1 ]
Aloisio, Giovanni [1 ]
Andre, Jean-Claude [1 ]
Barkai, David [1 ]
Berthou, Jean-Yves [1 ]
Boku, Taisuke [1 ]
Braunschweig, Bertrand [1 ]
Cappello, Franck [1 ]
Chapman, Barbara [1 ]
Chi, Xuebin [1 ]
Choudhary, Alok [1 ]
Dosanjh, Sudip [1 ]
Dunning, Thom [1 ]
Fiore, Sandro [1 ]
Geist, Al [1 ]
Gropp, Bill [1 ]
Harrison, Robert [1 ]
Hereld, Mark [1 ]
Heroux, Michael [1 ]
Hoisie, Adolfy [1 ]
Hotta, Koh [1 ]
Jin, Zhong [1 ]
Ishikawa, Yutaka [1 ]
Johnson, Fred [1 ]
Kale, Sanjay [1 ]
Kenway, Richard [1 ]
Keyes, David [1 ]
Kramer, Bill [1 ]
Labarta, Jesus [1 ]
Lichnewsky, Alain [1 ]
Lippert, Thomas [1 ]
Lucas, Bob [1 ]
Maccabe, Barney [1 ]
Matsuoka, Satoshi [1 ]
Messina, Paul [1 ]
Michielse, Peter [1 ]
Mohr, Bernd [1 ]
Mueller, Matthias S. [1 ]
Nagel, Wolfgang E. [1 ]
Nakashima, Hiroshi [1 ]
Papka, Michael E. [1 ]
Reed, Dan [1 ]
Sato, Mitsuhisa [1 ]
Seidel, Ed [1 ]
Shalf, John [1 ]
Skinner, David [1 ]
Snir, Marc [1 ]
机构
[1] Univ Tennessee, Knoxville, TN 37996 USA
基金
美国国家科学基金会; 英国工程与自然科学研究理事会;
关键词
exascale computing; high-performance computing; software stack;
D O I
10.1177/1094342010391989
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Over the last 20 years, the open-source community has provided more and more software on which the world's high-performance computing systems depend for performance and productivity. The community has invested millions of dollars and years of effort to build key components. However, although the investments in these separate software elements have been tremendously valuable, a great deal of productivity has also been lost because of the lack of planning, coordination, and key integration of technologies necessary to make them work together smoothly and efficiently, both within individual petascale systems and between different systems. It seems clear that this completely uncoordinated development model will not provide the software needed to support the unprecedented parallelism required for peta/exascale computation on millions of cores, or the flexibility required to exploit new hardware models and features, such as transactional memory, speculative execution, and graphics processing units. This report describes the work of the community to prepare for the challenges of exascale computing, ultimately combing their efforts in a coordinated International Exascale Software Project.
引用
收藏
页码:3 / 60
页数:58
相关论文
共 17 条
[1]  
*DEP EN, 2008, CHALL CLIM CHANG SCI, P98
[2]  
*DEP EN, 2009, FUS EN SCI ROL COMP, P245
[3]  
*DEP EN, 2009, SCI BAS NUCL EN SYST, P94
[4]  
*DEP EN, 2008, SCI CHALL UND QUANT, P129
[5]  
*DEP EN, 2009, SCI GRAND CHALL NAT, P190
[6]  
*DEP EN, 2009, CROSS CUTT TECHN COM, P99
[7]  
*DEP EN, 2009, FOR QUEST NUCL SCI R
[8]  
*DEP EN, 2009, ARCH TECHN EXTR SCAL
[9]  
*DEP EN, 2009, OPP BIOL EXTR SCAL C, P69
[10]  
*DEP EN, 2009, DISC BAS EN SCI ROL