Title :
Computational Models for Big Data Processing
Author_Institution :
Dept. of Appl. Inf., Hosei Univ., Koganei, Japan
Abstract :
MapReduce framework has emerged as one of the most widely used parallel computing platforms for processing Big Data on tera- and peta-byte scale. In this note, we introduce several theoretical computational models for MapReduce from a standpoint of parallel algorithmic power by comparing MapReduce computation with standard parallel computational models such as PRAMs and/or combinational Boolean circuits.
Keywords :
Big Data; parallel processing; Big Data processing; MapReduce framework; PRAM; combinational Boolean circuits; parallel algorithmic power; parallel computational model; parallel computing platform; petabyte scale processing; probabilistic random access memory; terabyte scale processing; Computational modeling; Integrated circuit modeling; Memory management; Phase change random access memory; Polynomials; Program processors; Tin; Big Data; MapReduce; PRAM; computational model;
Conference_Titel :
Computing and Networking (CANDAR), 2014 Second International Symposium on
DOI :
10.1109/CANDAR.2014.40
