Abstract | ||
---|---|---|
Extends our prior results [Raghavendra & Sridhar (1992, 1993), Sengupta & Raghavendra (1994)] to obtain algorithms for performing all-to-all broadcast, global sum and broadcast operation in an N-node (N=2n), n-dimensional faulty SIMD hypercube, Qn (n⩾9), with the number of faults n-1<f⩽2n-3. We also discuss optimal algorithms for one-to-all personalized broadcasting and all-to-one personalized broadcasting in a Qn with the number of faults f⩽n-1. Our broadcasting and global sum algorithms require 2n+19 steps and n+O(log n) steps, whereas the all-to-all broadcast algorithm requires 10N+15 steps |
Year | DOI | Venue |
---|---|---|
1996 | 10.1109/IPPS.1996.508115 | Honolulu, HI |
Keywords | Field | DocType |
all-to-all broadcast,dimensional faulty simd hypercube,faulty simd hypercubes,broadcast operation,prior result,global operations,faults n,global sum,computer science,fault tolerance,parallel algorithms,robustness,hypercubes,broadcasting,network topology,routing,concurrent computing,emulation,casting,computational complexity | Binary logarithm,Broadcasting,Computer science,Parallel algorithm,Parallel computing,SIMD,Network topology,Concurrent computing,Hypercube,Distributed computing,Computational complexity theory | Conference |
ISBN | Citations | PageRank |
0-8186-7255-2 | 2 | 0.37 |
References | Authors | |
10 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Amit Sengupta | 1 | 8 | 1.72 |
C. S. Raghavendra | 2 | 2 | 0.37 |