March 2, 2017 — ECP has selected its fifth Co-Design Center to focus on Graph Analytics — combinatorial (graph) kernels that play a crucial enabling role in many data analytic computing (DAC) application areas as well as several ECP applications.
The Co-Design Center, titled “ExaGraph: Combinatorial Methods for Enabling Exascale Applications Co-Design Center”, was originally submitted as a proposal in June, 2016. It has been selected for support at the seed level. The new Co-Design Center will be led by Mahantesh Halappanavar, a Senior Research Scientist in the Advanced Computing, Mathematics and Data Division at Pacific Northwest National Laboratory (PNNL).
Initially, the work will be a partnership among PNNL, Lawrence Berkeley National Laboratory, Sandia National Laboratories, and Purdue University.
The ExaGraph Co-Design Center is being established to target a number of key data analytic computational motifs such as graph traversals; graph matching; graph coloring; graph clustering, including clique enumeration, parallel branch-and-bound, and graph partitioning – motifs that are currently not being addressed in existing ECP Co-Design Centers. With this new ExaGraph Co-Design Center, the ECP is now in a better position to ready current and evolving DAC applications for efficient use of capable exascale platforms.
Source: The Exascale Computing Project