A tabular method for verication of data exchange algorithms on networks which possess a certain symmetry (whose underlying graph is a Cayley graph) is given. The algorithms use no intermediate buering of messages. To illustrate this method, optimal total exchange (i.e., all-to-all personalised) algorithms are given for several much-used processor congurations, such as ring networks, the hypercube and symmetric meshes with wrap-around (two and three-dimensional). To the best of our knowledge the latter are new
Load balancing on parallel computers aims at equilibrating some initial load which is initially diff...
All-to-all personalized communication is a class of permutations in which each processor sends a uni...
This chapter is concerned with designing algorithms for machines constructed from multiple processor...
AbstractStar graphs, as discussed in [1], are considered to be attractive alternatives for hypercube...
AbstractA ‘sandwich graph’ is obtained by connecting the corresponding vertices of two copies of a g...
Many authors have considered the design of complete exchange algorithms for a variety of multicomput...
AbstractÐAll-to-all personalized exchange is one of the most dense collective communication patterns...
The interprocessor complete exchange communication pattern can be found in many important parallel a...
Some generalized communication modes enabling the dissemination of information among processors of i...
AbstractLoad balancing on parallel computers aims at equilibrating some initial load which is differ...
AbstractSome generalized communication modes enabling the dissemination of information among process...
The generalized dimension exchange (GDE) method is a fully distributed load balancing method that op...
AbstractThis paper is a survey of existing methods of communication in usual networks. We particular...
This paper presents a fast algorithm for data exchange in a network of processors organized as a rec...
AbstractAn all-to-all communication algorithm is said to be optimal if it has the smallest communica...
Load balancing on parallel computers aims at equilibrating some initial load which is initially diff...
All-to-all personalized communication is a class of permutations in which each processor sends a uni...
This chapter is concerned with designing algorithms for machines constructed from multiple processor...
AbstractStar graphs, as discussed in [1], are considered to be attractive alternatives for hypercube...
AbstractA ‘sandwich graph’ is obtained by connecting the corresponding vertices of two copies of a g...
Many authors have considered the design of complete exchange algorithms for a variety of multicomput...
AbstractÐAll-to-all personalized exchange is one of the most dense collective communication patterns...
The interprocessor complete exchange communication pattern can be found in many important parallel a...
Some generalized communication modes enabling the dissemination of information among processors of i...
AbstractLoad balancing on parallel computers aims at equilibrating some initial load which is differ...
AbstractSome generalized communication modes enabling the dissemination of information among process...
The generalized dimension exchange (GDE) method is a fully distributed load balancing method that op...
AbstractThis paper is a survey of existing methods of communication in usual networks. We particular...
This paper presents a fast algorithm for data exchange in a network of processors organized as a rec...
AbstractAn all-to-all communication algorithm is said to be optimal if it has the smallest communica...
Load balancing on parallel computers aims at equilibrating some initial load which is initially diff...
All-to-all personalized communication is a class of permutations in which each processor sends a uni...
This chapter is concerned with designing algorithms for machines constructed from multiple processor...