Advances in sustainable computing towards Big data and HPC convergence

https://doi.org/10.1016/j.suscom.2018.10.007Get rights and content

Introduction

Developing modern computing systems and system software that can scale to massive amounts of data becomes a key challenge to both researchers and practitioners. Scalability in distributed system usually means that the performance of a system should increase proportionally with the increase of resources. However, this is not sufficient in the big data era. Big data and HPC are converging in terms of hardware and software. As a consequence, the system should be designed in a way so that all the five Vs of big data can be tackled. Driven by this insight, this special issue aims at presenting the current state-of-the-art research and future trends on various aspects of big data programming and system software techniques for big data processing and attempts towards building highly adaptive big data systems that can automatically adapt their behaviors to the amount of available resources. The major subjects cover methodologies, modeling, analysis and newly introduced applications. Besides the latest research achievements, this special issue also covers innovative commercial data management systems, innovative commercial applications of big data technology, and experience in applying recent research advances to real-world problems.

Papers selected for this special issue represent recent progresses in the field, including works on big data systems, information security, optimizations for big data analytics, sustainable architectures and applications, etc. All of these papers not only provide novel ideas and state-of-the-art techniques in the field, but also stimulate future research in the sustainable computing towards big data and HPC convergence.

Section snippets

System optimizations for big data and HPC convergence

Cloud is an emerging multi-disciplinary research area with the aim of analyzing the vast amount of data and user requests to extract actionable information. The paper by Sambit Kumar Mishra, Deepak Puthal, Bibhudatta Sahoo, Prem Prakash Jayaraman,Song Jun, Albert Y. Zomaya and Rajiv Ranjan entitled “Energy-efficient VM-placement in cloud data center” proposes a complete mapping algorithm of tasks to virtual machines (VMs) and VMs to physical machines for advancing energy consumption and

Technologies and algorithms for big data processing

In-memory database system is suitable for real-time pro-cessing because it puts all the intermediate data that the program needs in memory and obtains a fast response by minimizing hard disk access time. But the small memory capacity is a bottleneck in processing data using the performance of the actual memory speed. The paper by Xian-Shu Li, Su-Kyung Yoon, Jung-Geun Kim and Shin-Dug Kim entitled “A self-learning pattern adaptive prefetching method for big data applications” proposes a

Sustainable architectures and applications for big data and HPC

Over the frontier computing era, the HPC community has analyzed a wide range of applications of virtually every computational field, identifying pros and cons to be efficiently mapped onto GPU devices. The paper by J. Péreza, A. Rodríguez, J.F. Chico, D. López-Rodríguez and M. Ujaldón entitled “Energy-aware acceleration on GPUs: Findings on a bioinformatics benchmark” performs a complete study on performance and energy efficiency of biomedical codes when accelerated on GPUs. The authors explore

Conclusions

All of the above papers address either technical issues in Big Data platforms or information security or propose novel application models in the various big data and HPC fields. They also trigger further related research and technology improvements in application of sustainable computing. Honourably, this special issue serves as a landmark source for education, information, and reference to professors, researchers and graduate students interested in updating their knowledge about or active in

References (0)

Cited by (0)

View full text