Title :
Optimal data reduction on reconfigurable tori
Author :
Zhou, Jipeng ; Lau, Francis C M
Author_Institution :
Dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., China
Abstract :
Data reduction is a fundamental operation of parallel computing. We derive lower bounds on communication latency for global data reduction and multiple global data reduction on reconfigurable tori. We present optimal global data reduction algorithms and multiple global data reduction algorithms on reconfigurable tori of any dimension. The formal reduction algorithms we give can make reduction and broadcast operations easy to implement
Keywords :
data reduction; multiprocessor interconnection networks; parallel architectures; reconfigurable architectures; broadcast operations; communication latency; formal reduction algorithms; global data reduction; lower bounds; multiple global data reduction; optimal data reduction; parallel computing; reconfigurable tori; Assembly; Broadcasting; Computer science; Concurrent computing; Delay; Information systems;
Conference_Titel :
Parallel and Distributed Systems, 2001. ICPADS 2001. Proceedings. Eighth International Conference on
Conference_Location :
Kyongju City
Print_ISBN :
0-7695-1153-8
DOI :
10.1109/ICPADS.2001.934827
