Title :
Neural computing for built-in self-repair of embedded memory arrays
Author :
Mazumder, P. ; Yih, J.-S.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Michigan Univ., Ann Arbor, MI, USA
Abstract :
A demonstration is presented of how to represent the objective function of the memory repair problem as a neural network energy function, and how to utilize the neural net´s convergence property to find near-optimal solutions. Two algorithms have been developed using a neural network, and their performance is compared with the ´repair most´ algorithm that is used commercially. For randomly generated defect patterns, the proposed algorithm with a hill-climbing capability has been found to be successful in repairing memory arrays in 98% of the cases, as opposed to the repair most algorithm´s 20% of cases.<>
Keywords :
computer maintenance; digital storage; fault location; fault tolerant computing; neural nets; built-in self-repair; convergence property; embedded memory arrays; hill-climbing capability; memory repair problem; near-optimal solutions; neural computing; neural network energy function; objective function; performance; randomly generated defect patterns; reconfiguration; repair most algorithm; Approximation algorithms; Built-in self-test; Circuit faults; Circuit testing; Embedded computing; Intelligent networks; Neural networks; Optical arrays; Software algorithms; Very large scale integration;
Conference_Titel :
Fault-Tolerant Computing, 1989. FTCS-19. Digest of Papers., Nineteenth International Symposium on
Conference_Location :
Chicago, IL, USA
Print_ISBN :
0-8186-1959-7
DOI :
10.1109/FTCS.1989.105623
