hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.2000.01.05

Polyvalent Parallelizations for Hierarchical Block Matching Motion Estimation

Christos Kaklamanis
Andreas I. Svolos
Charalampos G. Konstantopoulos

Puni tekst: engleski, pdf (417 KB) str. 41-69 preuzimanja: 358* citiraj
APA 6th Edition
Kaklamanis, C., Svolos, A.I. i Konstantopoulos, C.G. (2000). Polyvalent Parallelizations for Hierarchical Block Matching Motion Estimation. Journal of computing and information technology, 8 (1), 41-69. https://doi.org/10.2498/cit.2000.01.05
MLA 8th Edition
Kaklamanis, Christos, et al. "Polyvalent Parallelizations for Hierarchical Block Matching Motion Estimation." Journal of computing and information technology, vol. 8, br. 1, 2000, str. 41-69. https://doi.org/10.2498/cit.2000.01.05. Citirano 27.02.2021.
Chicago 17th Edition
Kaklamanis, Christos, Andreas I. Svolos i Charalampos G. Konstantopoulos. "Polyvalent Parallelizations for Hierarchical Block Matching Motion Estimation." Journal of computing and information technology 8, br. 1 (2000): 41-69. https://doi.org/10.2498/cit.2000.01.05
Harvard
Kaklamanis, C., Svolos, A.I., i Konstantopoulos, C.G. (2000). 'Polyvalent Parallelizations for Hierarchical Block Matching Motion Estimation', Journal of computing and information technology, 8(1), str. 41-69. https://doi.org/10.2498/cit.2000.01.05
Vancouver
Kaklamanis C, Svolos AI, Konstantopoulos CG. Polyvalent Parallelizations for Hierarchical Block Matching Motion Estimation. Journal of computing and information technology [Internet]. 2000 [pristupljeno 27.02.2021.];8(1):41-69. https://doi.org/10.2498/cit.2000.01.05
IEEE
C. Kaklamanis, A.I. Svolos i C.G. Konstantopoulos, "Polyvalent Parallelizations for Hierarchical Block Matching Motion Estimation", Journal of computing and information technology, vol.8, br. 1, str. 41-69, 2000. [Online]. https://doi.org/10.2498/cit.2000.01.05

Sažetak
Block matching motion estimation algorithms are widely used in video coding schemes. In this paper,we design an efficient hierarchical block matching motion estimation (HBMME) algorithm on a hypercube multiprocessor. Unlike systolic array designs, this solution is not tied down to specific values of algorithm parameters and thus offers increased flexibility. Moreover, the hypercube network can efficiently handle the non regular data flow of the HBMME algorithm. Our techniques nearly eliminate the occurrence of “difficult” communication patterns, namely many-to-many personalized communication, by replacing them with simple shift operations. These operations have an efficient implementation on most of interconnection networks and thus our techniques can be adapted to other networks as well. With regard to the employed multiprocessor we make no specific assumption about the amount of local memory residing in each processor. Instead, we introduce a free parameter S and assume that each processor has O(S) local memory. By doing so, we handle all the cases of modern multiprocessors, that is fine-grained, medium-grained and coarse-grained multiprocessors and thus our design is quite general.

Hrčak ID: 44851

URI
https://hrcak.srce.hr/44851

Posjeta: 521 *