DocumentCode :
1985962
Title :
Fabric-Based Systems: model, tools, applications
Author :
Wolinski, Christophe ; Gokhale, Maya ; McCabe, Kevin
Author_Institution :
Los Alamos Nat. Lab., NM, USA
fYear :
2003
fDate :
9-11 April 2003
Firstpage :
288
Lastpage :
289
Abstract :
A Fabric-Based System (FBS) is a parameterized cellular architecture in which an array of computing cells communicates with an embedded processor through a global memory. This architecture is customizable to different classes of applications by functional unit, interconnect, and memory parameters, and can be instantiated efficiently on platform FPGAs (field programmable gate array). In previous work (Bellows et al., 2002), we have demonstrated the advantage of reconfigurable fabrics for image and signal processing applications. Recently, we have built a Fabric Generator (FG), a Java-based toolset that greatly accelerates construction of the fabrics. A module-generation library is used to define, instantiate, and interconnect cells´ datapaths. FG also generates customized sequencers for individual cells or collections of cells. We describe the Fabric-Based System model, the FG toolset, and concrete realizations of fabric architectures generated by FG on the Altera Excalibur ARM that can deliver 4.5 GigaMACs/s (8/16 bit data, multiply-accumulate).
Keywords :
formal specification; logic CAD; memory architecture; reconfigurable architectures; Altera Excalibur ARM; FBS; FG; FPGA; Fabric Generator; Java-based toolset; computing cell; embedded processor; fabric architecture; fabric-based system; field programmable gate array; functional unit; global memory; image processing; memory parameter; module-generation library; parameterized cellular architecture; reconfigurable fabric; signal processing; Acceleration; Array signal processing; Bellows; Computer architecture; Embedded computing; Fabrics; Field programmable gate arrays; Java; Libraries; Memory architecture;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Field-Programmable Custom Computing Machines, 2003. FCCM 2003. 11th Annual IEEE Symposium on
Print_ISBN :
0-7695-1979-2
Type :
conf
DOI :
10.1109/FPGA.2003.1227274
Filename :
1227274
Link To Document :
بازگشت