Communications of the ACM - Special section on computer architecture
A reconfiguration algorithm for fault tolerance in a hypercube multiprocessor
Information Processing Letters
Distributed subcube identification algorithms for reliable hypercubes
Information Processing Letters
Subcube Determination in Faulty Hypercubes
IEEE Transactions on Computers
IEEE Transactions on Parallel and Distributed Systems
Submesh Determination in Faulty Tori and Meshes
IEEE Transactions on Parallel and Distributed Systems
Correct and Almost Complete Diagnosis of Processor Grids
IEEE Transactions on Computers
Reconfiguring Processor Arrays Using Multiple-Track Models: The 3Track-Spare-Approach
IEEE Transactions on Computers
The Rule-Based Approach to Reconfiguration of 2-D Processor Arrays
IEEE Transactions on Computers
Proceedings of the The IEEE International Workshop on Defect and Fault Tolerance in VLSI Systems
An overview of the BlueGene/L Supercomputer
Proceedings of the 2002 ACM/IEEE conference on Supercomputing
Finding Maximal Submeshes in Faulty 2D Mesh in the Presence of Failed Nodes
PAS '97 Proceedings of the 2nd AIZU International Symposium on Parallel Algorithms / Architecture Synthesis
Fault Diagnosis in a Boolean n Cube Array of Microprocessors
IEEE Transactions on Computers
On finding maximal subcubes in residual hypercubes
SPDP '90 Proceedings of the 1990 IEEE Second Symposium on Parallel and Distributed Processing
Hi-index | 0.00 |
In a faulty torus/mesh, finding the maximal fault-free submesh is the main problem of reconfiguration Chen and Hu [1] proposed a distributed method to determine the maximal fault-free submesh in a faulty torus In this paper, we show that it is sufficient to apply the distributed algorithm proposed by Chen and Hu [1] to only few nodes of a torus The time for determination of the maximal fault free submesh/submeshes (MFSS) is considerably reduced, by reduction in the number of messages needed for determination of MFSS In addition, it also reduces the congestion in the network We present an algorithm to determine the smallest submesh containing all faulty nodes in a torus The proposed algorithm has a time complexity of O(n(m + k)) for a k-ary n-cube with m faults Intensive simulation study reveals that number of messages is significantly reduced compared to Chen and Hu's [1] method.