Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Fault tolerant VLSI multicomputers

Book ·
OSTI ID:5384601

An approach is presented to increase the reliability of future high-end systems beyond what is possible with technological solutions alone. The system consists of computation nodes and communication nodes, interconnected by high-speed dedicated links. These components are relied upon to detect errors while system level protocols are used for error recovery and reconfiguration. The use of duplication and matching for implementing the self-checking nodes allows us to restrict a detailed analysis of the impact of all possible faults to the comparator, a circuit that can be implemented in a relatively straightforward way in NMOS or CMOS technology.

OSTI ID:
5384601
Country of Publication:
United States
Language:
English