Title : 
Data manipulator network for WSI designs
         
        
            Author : 
Wills, Jeffrey M. ; Jain, Vijay K.
         
        
            Author_Institution : 
Dept. of Electr. Eng., Univ. of South Florida, Tampa, FL, USA
         
        
        
        
        
        
            Abstract : 
Multiprocessor system architectures require the use of INterconnection NETworks (INNETs) to provide for movement of data or instructions between memory and the processing elements. When an INNET is an integral part of the system, a WSI implementation will generally require a large fraction of the wafer area. This paper presents an area-reducing algorithm for the data manipulator network in silicon implementations where two or more levels of metal are available. The objective of multilevel metalization, i.e., more than the traditional two-level metalization, is two-fold: (a) to reduce the silicon area used by the wiring, and (b) to provide for mask programmability of metal layers. The emphasis of this paper is on the first of these aspects
         
        
            Keywords : 
VLSI; cellular arrays; integrated circuit technology; multiprocessor interconnection networks; INNETs; INterconnection NETworks; WSI designs; WSI implementation; area-reducing algorithm; data manipulator network; mask programmability of metal layers; multilevel metalization; Computer architecture; Geometry; Intelligent networks; Multiprocessing systems; Multiprocessor interconnection networks; Power engineering computing; Routing; Silicon; Wires; Wiring;
         
        
        
        
            Conference_Titel : 
Wafer Scale Integration, 1990. Proceedings., [2nd] International Conference on
         
        
            Conference_Location : 
San Francisco, CA
         
        
            Print_ISBN : 
0-8186-9013-5
         
        
        
            DOI : 
10.1109/ICWSI.1990.63894