TY - GEN
T1 - Topic 14+16: High-performance and scientific applications and extreme-scale computing (Introduction)
AU - Downes, Turlough P.
AU - Roller, Sabine P.
AU - Seitsonen, Ari Paavo
AU - Valcke, Sophie
AU - Keyes, David E.
AU - Sawley, Marie Christine
AU - Schulthess, Thomas C.
AU - Shalf, John M.
N1 - KAUST Repository Item: Exported on 2020-10-01
PY - 2013
Y1 - 2013
N2 - As our understanding of the world around us increases it becomes more challenging to make use of what we already know, and to increase our understanding still further. Computational modeling and simulation have become critical tools in addressing this challenge. The requirements of high-resolution, accurate modeling have outstripped the ability of desktop computers and even small clusters to provide the necessary compute power. Many applications in the scientific and engineering domains now need very large amounts of compute time, while other applications, particularly in the life sciences, frequently have large data I/O requirements. There is thus a growing need for a range of high performance applications which can utilize parallel compute systems effectively, which have efficient data handling strategies and which have the capacity to utilise current and future systems. The High Performance and Scientific Applications topic aims to highlight recent progress in the use of advanced computing and algorithms to address the varied, complex and increasing challenges of modern research throughout both the "hard" and "soft" sciences. This necessitates being able to use large numbers of compute nodes, many of which are equipped with accelerators, and to deal with difficult I/O requirements. © 2013 Springer-Verlag.
AB - As our understanding of the world around us increases it becomes more challenging to make use of what we already know, and to increase our understanding still further. Computational modeling and simulation have become critical tools in addressing this challenge. The requirements of high-resolution, accurate modeling have outstripped the ability of desktop computers and even small clusters to provide the necessary compute power. Many applications in the scientific and engineering domains now need very large amounts of compute time, while other applications, particularly in the life sciences, frequently have large data I/O requirements. There is thus a growing need for a range of high performance applications which can utilize parallel compute systems effectively, which have efficient data handling strategies and which have the capacity to utilise current and future systems. The High Performance and Scientific Applications topic aims to highlight recent progress in the use of advanced computing and algorithms to address the varied, complex and increasing challenges of modern research throughout both the "hard" and "soft" sciences. This necessitates being able to use large numbers of compute nodes, many of which are equipped with accelerators, and to deal with difficult I/O requirements. © 2013 Springer-Verlag.
UR - http://hdl.handle.net/10754/564660
UR - http://link.springer.com/10.1007/978-3-642-40047-6_73
UR - http://www.scopus.com/inward/record.url?scp=84883149219&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-40047-6_73
DO - 10.1007/978-3-642-40047-6_73
M3 - Conference contribution
SN - 9783642400469
SP - 737
EP - 738
BT - Lecture Notes in Computer Science
PB - Springer Nature
ER -