DocumentCode
1796335
Title
Data locality-based mesh partitioning methods for dataflow machines
Author
Hiba, Antal ; Nagy, Zsolt ; Ruszinko, Miklos ; Szolgay, Peter
Author_Institution
Fac. of Inf. Technol., Peter Pazmany Catholic Univ., Budapest, Hungary
fYear
2014
fDate
29-31 July 2014
Firstpage
1
Lastpage
2
Abstract
Power efficiency became an important factor in High Performance Computing (HPC). FPGA-based dataflow machines are the best candidates for power efficient computing, because of the maximized memory bandwidth utilization, and user-defined optimal caching. However, input data streams are required with optimized data locality. This paper focuses on the possibilities of novel mesh partitioning techniques, which provide partitions with better data locality.
Keywords
data flow computing; field programmable gate arrays; mesh generation; FPGA-based dataflow machines; data locality-based mesh partitioning methods; high performance computing; maximized memory bandwidth utilization; novel mesh partitioning techniques; power efficient computing; user-defined optimal caching; Bandwidth; Electronic mail; Memory management; Minimization; Optimization; Power demand; System-on-chip;
fLanguage
English
Publisher
ieee
Conference_Titel
Cellular Nanoscale Networks and their Applications (CNNA), 2014 14th International Workshop on
Conference_Location
Notre Dame, IN
Type
conf
DOI
10.1109/CNNA.2014.6888599
Filename
6888599
Link To Document