Toward Speed and Simplicity: Creating a Software Library for Graph Analytics

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. Listen on Apple Podcasts.