Fault tolerant methods are very important for multiprocessor systems because the probability of occurrence of a fault is much higher than in a single processor system. Therefore, in case of long calculations, backward recovery is frequently applied. The reliable storing of temporary results (recovery points) is of high importance. Each recovery point has to be stored unchanged for a possibly long time. For this purpose a 'stable storage' has to be used. A stable storage was designed and implemented for the multiprocessor system MEMSY that was built within the scope of the special research project called 'multiprocessor and network configuration' at the Friedrich-Alexander-University of Erlangen-Nuernberg. MEMSY is characterized by its memor...
With a need to deliver highest quality products operating in all environments, cope with small and u...
In this paper an innovative fault tolerant solid state mass memory (FTSSMM) architecture is describe...
One of the fastest expanding areas of computer exploitation is in embedded systems, whose prime func...
[[abstract]]© 1997 Institute of Electrical and Electronics Engineers - Highly reliable interleaved m...
Applications of computers have extended to almost every field of human activity including some life-...
Traditionally, tightly coupled multiprocessors allow data sharing between multiple caches by keeping...
Checkpointing and rollback recovery is a very effective technique to tolerate the occurrence of fail...
[[abstract]]A highly reliable interleaved memory system for uniprocessor and multiprocessor computer...
This report describes an experiment in the design of a general purpose fault tolerant system, FTM. T...
—This paper describes a novel architecture of fault tolerant Solid State Mass Memory (SSMM) for sat...
The concept of backward recovery is now well established as a means of restoring a consistent state ...
Memory system design is important for providing high reliability and availability. This dissertation...
International audienceScalable shared memory multiprocessors are promising architectures to achieve ...
One of the fundamental limits to high-performance, high-reliability applications is memory's vulnera...
With a need to deliver highest quality products operating in all environments, cope with small and u...
In this paper an innovative fault tolerant solid state mass memory (FTSSMM) architecture is describe...
One of the fastest expanding areas of computer exploitation is in embedded systems, whose prime func...
[[abstract]]© 1997 Institute of Electrical and Electronics Engineers - Highly reliable interleaved m...
Applications of computers have extended to almost every field of human activity including some life-...
Traditionally, tightly coupled multiprocessors allow data sharing between multiple caches by keeping...
Checkpointing and rollback recovery is a very effective technique to tolerate the occurrence of fail...
[[abstract]]A highly reliable interleaved memory system for uniprocessor and multiprocessor computer...
This report describes an experiment in the design of a general purpose fault tolerant system, FTM. T...
—This paper describes a novel architecture of fault tolerant Solid State Mass Memory (SSMM) for sat...
The concept of backward recovery is now well established as a means of restoring a consistent state ...
Memory system design is important for providing high reliability and availability. This dissertation...
International audienceScalable shared memory multiprocessors are promising architectures to achieve ...
One of the fundamental limits to high-performance, high-reliability applications is memory's vulnera...
With a need to deliver highest quality products operating in all environments, cope with small and u...
In this paper an innovative fault tolerant solid state mass memory (FTSSMM) architecture is describe...
One of the fastest expanding areas of computer exploitation is in embedded systems, whose prime func...