### Table 5: Lower bounds for the number of element transfers in broadcasting M elements on Boolean n-cube networks of N = 2n nodes.

1991

Cited by 20

### Table 3: Experimental speedups obtained on nCUBE 2 and a network of SUN workstations, using

"... In PAGE 4: ... We used P4 #5B3#5D to implement the one-dimensional simplex formulations. Some of our preliminary experimental results are shown in Table3 . From this table we see that on nCUBE 2, the cyclic one-dimensional partitioning yields good speedups, and the speedup increases linearly as the number of processors increase particularly for large problem instances.... ..."

### Table 8: Checkerboarding and Hybrid using Non-uniform networks on nCUBE2 and CM5

1994

Cited by 16

### Table 8: Checkerboarding and Hybrid using Non-uniform networks on nCUBE2 and CM5

1994

Cited by 16

### Table 2: Characteristics of the binary n-cube, the two-dimensional mesh, and the n-BdB networks. It is assumed that the mesh network has wraparound connections in the rows and columns. The table shows that the n-BdB network is an attractive alternative over binary n-cube and the mesh network.

Cited by 1

### Table 1: Comparison of ve structures n-cube mesh fat k1-k2 tree metahypercube fractahedral

1998

"... In PAGE 8: ... Diameter is the maximum distance and average distance is the mean of distances between all pairs of nodes. In Table1 , ve structures are compared in terms of deadlock avoidance, scalability, exibility, switch utilization, and network properties. Compared with hypercube or mesh, fat tree structure can support deadlock avoidance and exibility.... ..."

### Table 7: Lower bounds and time estimates for personalized communication of M elements per source-destination pair in a Boolean n-cube with N = 2n processors.

1991

"... In PAGE 18: ... Algorithms for the general case can be found in [33, 7, 40, 13, 12, 21] for mesh, Boolean cube, and hypercube networks. The optimal number of element transfers in a Boolean cube are given in Table7 . The optimal number of block transfers in a packet switched system is equal to the number of cube... ..."

Cited by 20

### TABLE II CHARACTERISTICS OF k-ARY n-CUBES

2001

Cited by 30

### Table 1 Performance results on nCUBE 2 and Paragon multiprocessors.

"... In PAGE 4: ... The Chaco runs were performed on an SGI Onyx with a 125 MHz clock. Table1 presents the results for 64 and 1024 partitions for both grids while Fig. 2 plots the parallel run times for the CVD grid for 64 through 1024 partitions.... ..."