Home // FUTURE COMPUTING 2016, The Eighth International Conference on Future Computational Technologies and Applications // View article

Benchmarking Big Data Applications: A Review

Authors:
Sayaka Akioka

Keywords: big data, benchmark, stream mining

Abstract:
Big data applications have become one of the non-negligible applications in recent years. These big data applications are supposed to investigate gigantic amount of data from various data sources from several points of view, uncover new findings, and then deliver totally new values. As big data applications handle extremely huge amount of data compared with conventional applications, there is a high, and increasing demand for the computational environment, which accelerates and scales out big data applications. The serious problem here, however, is that the behaviors, or characteristics of big data applications are not clearly defined yet. Modern computational environment has been and is evolving mainly for speed-up of benchmarks, such as LINPACK, or SPEC. These benchmarks are relatively scalable according to the number of CPUs. Big data applications are not scalable to the contrary, and the current computational environment is not necessarily ideal for big data applications. This paper primarily intends to provide a comprehensive survey on modeling, and benchmarking big data applications. The appropriate modeling, and benchmarking are indispensable for the development, or design of the adequate computational environment targeting on big data applications.

Pages: 59 to 64

Copyright: Copyright (c) IARIA, 2016

Publication date: March 20, 2016

Published in: conference

ISSN: 2308-3735

ISBN: 978-1-61208-461-9

Location: Rome, Italy

Dates: from March 20, 2016 to March 24, 2016