Trends and Challenges in Large-Scale HPC Network Analysis

Trends and Challenges in Large-Scale HPC Network Analysis

DOI: 10.4018/978-1-5225-3799-1.ch006


Many algorithms in graph analytics can be sped up by using the power of low-cost but massively parallel architectures, such as GPUs. On the other hand, the storage and analysis capabilities needed for large-scale graph analytics have motivated the development of a new wave of HPC technologies, including MapReduce-like BSP distributed analytics, No-SQL data storage and querying, and homogeneous and hybrid multi-core/GPU graph supercomputing. In this chapter, the authors review these trends and current challenges for HPC large-scale graph analysis.
Chapter Preview

Homogeneous Parallel Graph Processing

The first form of parallelism that the data analytics and complex network community exploits is homogeneous computing, i.e. parallel computing where all the processors are of the same-kind.

There is a list of publicly available libraries that exploit homogeneous parallel processing, i.e. the use of a single HPC parallel architecture (e.g. a multicore server or a HPC cluster) to power the processing of large networks modeled after real-world phenomena. The following subsections list works that exploit homogeneous parallel processing for efficient graph algorithm execution. A summary of the reviewed works is shown in Table 1.

Complete Chapter List

Search this Book: