Title | ||
---|---|---|
Robust design methods for hardware accelerators for iterative algorithms in scientific computing |
Abstract | ||
---|---|---|
The ubiquity of embedded systems of increasing complexity in domains like scientific computing requires computation on models whose complexity has grown beyond what is economical to manage purely in software to requiring hardware acceleration - a key part of which is selecting numerical data representations (bit-width allocation). To address the shortcomings of existing techniques when applied to scientific computing dataflows, we propose a methodology for determining custom hybrid fixed/floating-point data representations for iterative scientific computing applications. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1145/1837274.1837339 | Design Automation Conference |
Keywords | Field | DocType |
bit-width allocation,custom hybrid,robust design method,hardware acceleration,scientific computing,iterative algorithm,floating-point data representation,numerical data representation,scientific computing dataflows,hardware accelerator,key part,embedded system,iterative scientific computing application,robustness,convergence,data representation,hardware,embedded software,iterative methods,data structures,embedded systems,ubiquitous computing,computational modeling,design methodology,embedded computing,floating point,acceleration,satisfiability modulo theories,resource management | Data structure,Unconventional computing,Iterative method,Computer science,Robustness (computer science),Software,Computational science,Hardware acceleration,Ubiquitous computing,Distributed computing,Computation | Conference |
ISSN | ISBN | Citations |
0738-100X | 978-1-4244-6677-1 | 4 |
PageRank | References | Authors |
0.42 | 8 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Adam B. Kinsman | 1 | 141 | 10.05 |
Nicola Nicolici | 2 | 807 | 59.91 |