Automatic reconfiguration and yield of the TESH multicomputer network

IEEE Transactions on Computers - Tập 51 Số 8 - Trang 963-972 - 2002
B.M. Maziarz1, V.K. Jain2
1SKF Condition Monitoring, San Diego, CA, USA
2University of South Florida, Tampa, FL, USA

Tóm tắt

This paper considers defect tolerance issues for parallel computing systems based on a new interconnection network, namely "Tori connected mESHes (TESH)". Key features of this network are the following: it is hierarchical, thus allowing exploitation of computation locality and systematic expansion up to a million processors; and it appears to be well-suited for VLSI/ULSI realization, including 3D implementation. The goal here is to present efficient reconfiguration algorithms for such hierarchical parallel computing systems. Despite the dramatic improvement in defect density in recent years, it is still necessary to provide redundancy and defect circumvention to achieve acceptable system-level yields for large multicomputer systems. The TESH-based parallel systems are no exception. Therefore, we develop placement and routing algorithms that assign logical nodes to healthy physical nodes and configure switches to bypass the defective cells, switches and links. Simulations indicate that the placement is nearly 100 percent effective, while the routing performance diminishes with increasing defect density for a given extent of redundancy. The approach scales up well because, in TESH networks, essentially the same kind of sparing is used at all levels.

Từ khóa

#Routing #Parallel processing #Computer networks #Very large scale integration #Ultra large scale integration #Redundancy #Computer aided manufacturing #Multiprocessor interconnection networks #Concurrent computing #Switches

Tài liệu tham khảo

chevalier, 1986, A Programmable Switch Matrix for the Wafer Scale Integration of a Processor Array 10.1109/ICWSI.1995.515450 10.1145/358645.358660 sami, 1983, Reconfigurable Architectures for VLSI Implementation, Proc NCC '83 10.1109/ICWSI.1991.151724 10.1109/12.102840 10.1109/ISCAS.1998.694536 10.1109/71.329667 10.1109/IWRSP.1998.676663 10.1007/BF01660031 10.1109/12.76405 10.1109/PROC.1986.13533 maziarz, 1998, Reconfigurable TESH Connected Parallel Computers 10.1109/71.113081 10.1109/71.372797 10.1109/12.67323 10.1109/71.80187 10.1109/92.711306 jain, 1997, TESH: A New Hierarchical Interconnection Network for Massively Parallel Computing, IEICE Trans Information and Systems (Japan), 80 10.1109/ICISS.1996.552436 10.1109/ICC.1993.397599 10.1109/TC.1987.5009497 10.1109/71.395400