In this paper we compare the k-ary n-cube network with its dual. The dual is obtained by interchanging the role of nodes and channels. The resulting nodes in the dual network are connected to two channels only and the resulting channels are multi-way. One of the major topological advantages that can be observed in the dual network is the fixed node degree that is always equal to two irrespective of the network topology or dimension. This property enables the dual network to have wider channels. This comparative study includes the network properties, the cost, and the performance. The network performance is evaluated through simulation. The simulation results show that the dual network has a lower latency and is more efficient (makes better ...
Consider the K-arry n-cube network is the most significant network structure in parallel computer ar...
This paper proposes a new cube based topology called the Folded Metacube (FMC). The new topology has...
This paper analyzes a new multiprocessor interconnection network - the folded cube-connected cycles ...
The performance of k-ary n-cube interconnection networks is analyzed under the assumption of constan...
Abstmct-VLSI communication networks are wire-limited. The cost of a network is not a function of the...
We define an interconnection network AQn,k which we call the augmented k-ary n-cube by extending a k...
The topology of interconnection networks the stage a key role in the performance of all general purp...
We define an interconnection network AQn,k which we call the augmented k-ary n-cube by extending a k...
In this paper, a method for constructing node-disjoint (parallel) paths in k-ary n-cube interconnect...
K-ary n-cubes have been one of the most popular interconnection networks for practical multicomputer...
AbstractIn this paper, we propose and analyze a new interconnection network, the k-ary hypercube. Th...
K-ary n-cubes have been one of the most popular interconnection networks for practical multicomputer...
The performance of an interconnection network is measured by two metrics: average latency and peak n...
. This paper presents the derivation and performance results of several new three-dimensional topolo...
Mass data processing and complex problem solving have higher and higher demands for performance of m...
Consider the K-arry n-cube network is the most significant network structure in parallel computer ar...
This paper proposes a new cube based topology called the Folded Metacube (FMC). The new topology has...
This paper analyzes a new multiprocessor interconnection network - the folded cube-connected cycles ...
The performance of k-ary n-cube interconnection networks is analyzed under the assumption of constan...
Abstmct-VLSI communication networks are wire-limited. The cost of a network is not a function of the...
We define an interconnection network AQn,k which we call the augmented k-ary n-cube by extending a k...
The topology of interconnection networks the stage a key role in the performance of all general purp...
We define an interconnection network AQn,k which we call the augmented k-ary n-cube by extending a k...
In this paper, a method for constructing node-disjoint (parallel) paths in k-ary n-cube interconnect...
K-ary n-cubes have been one of the most popular interconnection networks for practical multicomputer...
AbstractIn this paper, we propose and analyze a new interconnection network, the k-ary hypercube. Th...
K-ary n-cubes have been one of the most popular interconnection networks for practical multicomputer...
The performance of an interconnection network is measured by two metrics: average latency and peak n...
. This paper presents the derivation and performance results of several new three-dimensional topolo...
Mass data processing and complex problem solving have higher and higher demands for performance of m...
Consider the K-arry n-cube network is the most significant network structure in parallel computer ar...
This paper proposes a new cube based topology called the Folded Metacube (FMC). The new topology has...
This paper analyzes a new multiprocessor interconnection network - the folded cube-connected cycles ...