Title :
Maximum Performance Computing with Dataflow Engines
Author :
Pell, O. ; Averbukh, V.
Abstract :
Multidisciplinary dataflow computing is a powerful approach to scientific computing that has led to orders-of-magnitude performance improvements for a wide range of applications.
Keywords :
data flow computing; natural sciences computing; performance evaluation; dataflow engines; maximum performance computing; multidisciplinary dataflow computing; performance improvements; scientific computing; Computational algorithms; Computational modeling; Computer architecture; Data processing; Scientific computing; Computational algorithms; Computational modeling; Computer architecture; Data processing; Scientific computing; computational science; computer architectures; dataflow computing; exascale processing; scientific computing;
Journal_Title :
Computing in Science & Engineering
DOI :
10.1109/MCSE.2012.78
