Near-optimal all-to-all broadcast in multidimensional all-port meshes and tori

IEEE Transactions on Parallel and Distributed Systems

Volumn 13, Issue 2, 2002, Pages 128-141

  Yang, Yuanyuan ^a,b   Wang, Jianchao ^a,c  

^a IEEE

^b Stony Brook University   (United States)

^c DataTreasury Corporation   (United States)

Author keywords

All to all broadcast; All to all communication; Broadcast tree; Collective communication; Gossip; Interprocessor communication; Mesh; Parallel computing; Routing; Torus

Indexed keywords

ALL-TO-ALL BROADCAST; ALL-TO-ALL COMMUNICATION; BROADCAST TREE; COLLECTIVE COMMUNICATION; MESH; TORUS;

COMMUNICATION CHANNELS (INFORMATION THEORY); INTERCONNECTION NETWORKS; PARALLEL ALGORITHMS; TELECOMMUNICATION TRAFFIC; THEOREM PROVING; THREE DIMENSIONAL;

PARALLEL PROCESSING SYSTEMS;

EID: 0036473041     PISSN: 10459219     EISSN: None     Source Type: Journal    
DOI: 10.1109/71.983941     Document Type: Article

References (22)

1. Efficient all-to-all communication patterns in hypercube and mesh topologies
2. All-to-all communication on meshes with wormhole routing
3. All-to-all personalized communication in a wormhole-routed torus
4. Bandwidth-optimal complete exchange on wormhole routed 2d/3d torus networks: A diagonal-propagation approach
5. Total-exchange on wormhole k-ary n-cubes with adaptive routing
6. All-to-all communication with minimum start-up costs in 2d/3d tori and meshes
7. All-to-all personalized communication in multidimensional torus and mesh networks
8. Configurable algorithms for complete exchange in 2d meshes
9. Optimum broadcasting and personalized communication in hypercubes
10. Efficient algorithms for all-to-all communications in multi-port message-passing systems
11. Optimal all-to-all personalized exchange in self-routable multistage networks
12. Optimal all-to-all personalized exchange in a class of optical multistage networks
13. Data communication in parallel architectures
14. All-to-all broadcast in torus with wormhole-like routing
15. Gossiping on Meshes and Tori
16. Time-independent gossiping on full-port tori
17. Time-optimal gossip of large packets in noncombining 2d tori and meshes
18. Pipelined all-to-all broadcast in all-port meshes and tori
19. On the impact of communication complexity in the design of parallel numerical algorithms
20. Communication efficient basic linear algebra computations on hypercube architectures