Hybrid algorithms for complete exchange in 2D meshes

IEEE Transactions on Parallel and Distributed Systems

Volumn 12, Issue 12, 2001, Pages 1201-1218

  Sundar, N S ^b   Jayasimha, D N ^c   Panda, Dhabaleswar K ^a,d   Sadayappan, P ^d  

^a IEEE   (United States)

^b HEWLETT PACKARD COMPANY   (United States)

^c INTEL CORPORATION   (United States)

^d OHIO STATE UNIVERSITY   (United States)

Author keywords

Barrier synchronization; Collective communication; Combining; Complete exchange; Direct exchange; Hybrid algorithms; Mesh topology; Message contention; Wormhole routing

Indexed keywords

BARRIER SYNCHRONIZATION; COLLECTIVE COMMUNICATION; COMPLETE EXCHANGE; CYCLIC EXCHANGE; DISTRIBUTED MEMORY MULTICOMPUTERS; HYBRID ALGORITHMS; MESH TOPOLOGY; MESSAGE CONTENTION; SCOTTS DIRECT EXCHANGE; WORMHOLE ROUTING;

COMPUTER SIMULATION; DATA STORAGE EQUIPMENT; DISTRIBUTED COMPUTER SYSTEMS; MATHEMATICAL MODELS; PROGRAM PROCESSORS; SORTING; TWO DIMENSIONAL;

PARALLEL ALGORITHMS;

EID: 0035690895     PISSN: 10459219     EISSN: None     Source Type: Journal    
DOI: 10.1109/71.970553     Document Type: Article

References (30)

1. Balanced parallel sort on hypercube multiprocessors
2. Practical parallel algorithms for personalized communication and integer sorting
3. CCL: A portable and tunable collective communication library for scalable parallel computers
4. Building a high-performance collective communication library
5. Optimal communication algorithms for hypercubes
6. Complete exchange on the iPSC-860
7. Multiphase complete exchange on a circuit switched hypercube
8. Multiphase complete exchange on paragon, SP2, and CS-2
9. Complete exchange on a circuit switched mesh
10. How to get good performance from the CM-5 data network
11. Optimal total exchange in linear arrays and rings
12. Optimal matrix transposition and bit reversal on hypercubes: All-to-all personalized communication
13. MPI: A message-passing interface standard
14. A binary interleaved algorithm for complete exchange on a mesh architecture
15. Optimum broadcasting and personalized communication in hypercubes
16. Derandomizing algorithms for routing and sorting on meshes
17. Total exchange on a reconfigurable parallel architecture
18. A survey of collective communication in wormhole-routed massively parallel computers
19. Efficient communication in the folded Petersen interconnection networks
20. A communication model for the intel iPSC/2
21. Introduction to process-oriented simulation and CSIM
22. Efficient all-to-all communication patterns in hypercube and mesh topologies
23. Routing and sorting on meshes with row and column buses
24. Algorithms for all-to-all personalized exchange in 2D and 3D tori
25. Complete exchange in 2D meshes
26. A routing method for all-to-all burst on hypercube networks
27. All-to-all communication on meshes with wormhole routing
28. Complete exchange on a wormhole routed mesh
29. Complete exchange on the CM-5 and touchstone delta