A processor architecture for horizon
Proceedings of the 1988 ACM/IEEE conference on Supercomputing
Connection autonomy in SIMD computers: a VLSI implementation
Journal of Parallel and Distributed Computing
IEEE Transactions on Computers
Adaptive deadlock- and livelock-free routing with all minimal paths in Torus networks
SPAA '92 Proceedings of the fourth annual ACM symposium on Parallel algorithms and architectures
IEEE Transactions on Parallel and Distributed Systems
Modeling parallel bandwidth: local vs. global restrictions
Proceedings of the ninth annual ACM symposium on Parallel algorithms and architectures
A Dilated-Diagonal-Based Scheme for Broadcast in a Wormhole-Routed 2D Torus
IEEE Transactions on Computers
Efficient Broadcasting in Wormhole-Routed Multicomputers: A Network-Partitioning Approach
IEEE Transactions on Parallel and Distributed Systems
Toward Optimal Complete Exchange on Wormhole-Routed Tori
IEEE Transactions on Computers
Efficient Heuristics for All-Port Multicast in Wormhole-Routed Hypercubes
IEEE Transactions on Parallel and Distributed Systems
Algebraic Foundations and Broadcasting Algorithms for Wormhole-Routed All-Port Tori
IEEE Transactions on Computers
Optimal All-to-All Personalized Exchange in Self-Routable Multistage Networks
IEEE Transactions on Parallel and Distributed Systems
Scatter and gather operations on an asynchronous communication model
SAC '00 Proceedings of the 2000 ACM symposium on Applied computing - Volume 2
Communication Reduction in Multiple Multicasts Based on Hybrid Static-Dynamic Scheduling
IEEE Transactions on Parallel and Distributed Systems
All-to-All Personalized Communication in Multidimensional Torus and Mesh Networks
IEEE Transactions on Parallel and Distributed Systems
Optimal All-to-All Personalized Exchange in a Class of Optical Multistage Networks
IEEE Transactions on Parallel and Distributed Systems
Pipelined All-to-All Broadcast in All-Port Meshes and Tori
IEEE Transactions on Computers
Near-Optimal All-to-All Broadcast in Multidimensional All-Port Meshes and Tori
IEEE Transactions on Parallel and Distributed Systems
Efficient Multicast Algorithms in All-Port Wormhole-Routed Hypercubes
ICPP '97 Proceedings of the international Conference on Parallel Processing
Near-Optimal All-to-All Broadcast in Multidimensional All-Port Meshes and Tori
IPDPS '01 Proceedings of the 15th International Parallel & Distributed Processing Symposium
All-to-all personalized communication on multistage interconnection networks
Discrete Applied Mathematics
Nearly Optimal Algorithms for Broadcast on d-Dimensional All-Port and Wormhole-Routed Torus
IPPS '98 Proceedings of the 12th. International Parallel Processing Symposium on International Parallel Processing Symposium
Total-Exchange on Wormhole k-ary n-cubes with Adaptive Routing
IPPS '98 Proceedings of the 12th. International Parallel Processing Symposium on International Parallel Processing Symposium
Contention-Aware Communication Schedule for High-Speed Communication
Cluster Computing
Optimal all-to-all personalised exchange in a novel optical multistage interconnection network
International Journal of High Performance Computing and Networking
A message passing strategy for array redistributions in a torus network
The Journal of Supercomputing
International Journal of Computer Mathematics
Scheduling independent jobs for torus connected networks with/without link contention
Mathematical and Computer Modelling: An International Journal
Hi-index | 0.02 |
All-to-all personalized communication, or complete exchange, is at the heart of numerous applications in parallel computing. It is one of the most dense communication patterns. In this paper, we consider this problem in a torus of any dimension with the wormhole-routing capability. We propose complete exchange algorithms that use optimal numbers of phases (if each side of the tori is a multiple of eight) or asymptotically optimal numbers of phases (otherwise). Interestingly, in order to achieve this, we only make weak assumptions驴that a node is capable of sending and receiving at most one message at a time, and the network is capable of supporting the dimension-ordered (or e-cube) minimum routing.