Toward Speed and Simplicity: Creating a Software Library for Graph Analytics
August 2015 • Podcast
In this podcast, Scott McMillan and Eric Werner of the SEI's Emerging Technology Center discuss work to create a software library for graph analytics that would take advantage of more powerful heterogeneous supercomputers.
Software Engineering Institute
“In a supercomputer, you generally have lots of compute nodes, each with the dedicated memory bank. The graph analytics problem comes down to dividing the data across these nodes. It doesn’t prevent traversal from one node to the next.”
High performance computing is now central to the federal government and industry as evidenced by the shift from single-core and multi-core or homogeneous central processing units, also known as CPUs, to many core and heterogeneous systems that also include other types of processors like graphics processing units, also known as GPUs.
In this podcast, Scott McMillan and Eric Werner of the SEI’s Emerging Technology Center discuss work to create a software library for graph analytics that would take advantage of these more powerful heterogeneous supercomputers to perform graph analytics at larger scales and more quickly, while making them simpler to program. Graph analytics are more complex, and thus, more difficult to program. These algorithms are used in the DoD-mission applications including intelligence analysis, knowledge representation and reasoning in autonomous systems, cyber intelligence and security, routing planning, and logistics optimization.
About the Speaker
Scott McMillan joined the SEI Emerging Technology Center in May 2013 as a senior software developer, bringing with him more than 20 years of experience in high-performance computing across a wide range of application areas including scientific computing, 2D/3D geographic information systems, and very large-scale database systems. Previously he worked at Raytheon where he contributed to a wide range of projects from cybersecurity, wireless communications, embedded systems, and Windows-device drivers research. Prior to that he worked at General Dynamics Advanced Information Systems where he led the design and development of database systems.
Eric Werner is the technical director and chief architect for the SEI Emerging Technology Center where he sets the technical direction of the center in the areas of software development, high-performance computing, cloud computing, and data analytics. Werner has more than 15 years of professional software development experience, primarily focused on delivering global, mission-critical software systems. Prior to joining the SEI, he was the lead architect and systems engineer for the United States Army’s Command and Control System with General Dynamics C4 Systems.