Results 1 - 10 of 21,305

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

in Performance Modeling of Distributed Memory Architectures
by S. Lennart Johnsson 1991
Cited by 20

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

in Performance and Scalability of the Parallel Simplex Method for Dense Linear Programming Problems (Extended Abstract)
by George Karypis, Vipin Kumar
"... 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

in A scalable parallel formulation of the backpropagation algorithm for hypercubes and related architectures
by Vipin Kumar Shashi Shekhar, Minesh B. Amin 1994
Cited by 16

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

in A Scalable Parallel Formulation of the Backpropagation Algorithm for Hypercubes and Related Architectures
by Vipin Kumar, Shashi Shekhar, Minesh B. Amin, Cm 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.

in An Efficient 3D Optical Implementation of Binary de Bruijn Networks with Applications to Massively Parallel Computing
by Ahmed Louri, Hongki Sung
Cited by 1

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

in On Configuration of Switch-Based Networks with Wormhole Switching
by Wan Y. Lee, Sung Je Hong, Jong Kim 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.

in Performance Modeling of Distributed Memory Architectures
by S. Lennart Johnsson 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

in Evaluating the Impact of Stale Link State on Quality-of-Service Routing
by Anees Shaikh, Jennifer Rexford, Kang G. Shin 2001
Cited by 30

Table 1 Performance results on nCUBE 2 and Paragon multiprocessors.

in Parallel Algorithms for Dynamically Partitioning Unstructured Grids
by Pedro Diniz, Steve Plimpton, Bruce Hendrickson, Robert Leland
"... 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.... ..."

TABLE III Best FBC graphs and n-cubes

in Task Assignment in Cayley Interconnection Topologies
by W. J. Gutjahr, M. Hitz, T.A. Mueck
Results 1 - 10 of 21,305