DocumentCode :
1813028
Title :
HPCS 2013 panel: The era of exascale sciences: Challenges, needs and requirements
Author :
Cappello, Franck ; Gentzsch, Wolfgang ; Valero, Mateo ; Nygard, Mads
Author_Institution :
INRIA-Illinois Joint Laboratory on PetaScale Computing, France
fYear :
2013
fDate :
1-5 July 2013
Firstpage :
1
Lastpage :
12
Abstract :
Computer simulation, or simulation-based engineering and science, is now widely accepted by many companies as a way of testing the product before manufacturing physical prototypes. Using simulation-based engineering design, companies are expected to deliver more business value to their end customers in the dynamic business changing environment by reducing product development cost and time while increasing the performance. There are many similar gains in other fields, such as healthcare, biomedical and biosciences, climate and environmental changes, design and manufacturing of advanced materials, geology, chemistry and physics, and even financial systems. Recent directions in research and technological studies have shown that Exascale computing may provide solutions for some of these issues by leading to advances in several areas of science and technology while allowing more computationally intensive and data intensive problems to be handled successfully. However, several computational and technical challenges, from hardware (e.g., data access/storage hierarchy) to algorithms, to programming models, and applications, must be overcome to make Exascale computing a practical infrastructure for computer-aided engineering applications and simulations. In this panel, we shall discuss the promise of Exascale computing to transform the role of modeling and simulation in science and engineering. Panelists will highlight research directions for developing Exascale computing infrastructures including models to support new emerging architectures, programming models to support exasclae computing, tools to simulate and evaluate these architectures, and programming languages (hybrid or new languages) that are appropriate for these new architectures. The intent is to make future HPC widely accessible to the designers, engineers, and scientists, in order for them to focus on how to design and simulate their systems instead of focusing on the computing systems issues.
fLanguage :
English
Publisher :
ieee
Conference_Titel :
High Performance Computing and Simulation (HPCS), 2013 International Conference on
Conference_Location :
Helsinki, Finland
Print_ISBN :
978-1-4799-0836-3
Type :
conf
DOI :
10.1109/HPCSim.2013.6641380
Filename :
6641380
Link To Document :
بازگشت