Survey on Programming Models and Environments for Cluster, Cloud, and Grid Computing that defends Big Data

摘要

A collection of interlinked stand-alone computers which function together in unity as a single incorporated computing resource is a kind of parallel or distributed processing systems called as the cluster. Clusters and grids are systems which intercommunicate among them and act as a single resource. This type of functionality can be referred to as the multi-computer parallel architecture that runs on certain considerations. Nevertheless cloud computing came forth as a more illustrious programming model to handle large data sets using clusters. A programming model is nothing but how data is carried out for handling the application. Performances, portability, objective architecture, sustainment of code are key measures that have to be commemorated while designing a programming model. Applications which are meant for data analytics generally deal with large data sets that undergo several stages of processing. Some of these stages are performed consecutively, and the others are carried out in parallel on clusters, grids, and cloud. This paper portrays a survey on how programming models which are developed for cluster cloud and grid act as a support for big data analytics. In addition, study on programming models which are currently being employed by leading multinational companies are pictured in the paper.