DK Panda, Ohio State University
A broad array of HPC enthusiasts have gathered at the Ohio Supercomputer Center this week for the sixth meeting of the MVAPICH Users Group (MUG).
The Network-Based Computing Research Group is lead by DK Panda, a professor and university distinguished scholar of computer science at The Ohio State University, created and enhances the popular MVAPICH HPC system software package. Panda is a longtime user of OSC services and partners closely with the center’s staff on several research projects.
Dr. Panda’s software is foundational for supercomputers around the world, including OSC’s systems and many of the Top 500,” said David Hudak, Ph.D., executive director of OSC. “Beyond just the software, the partnership with DK and his research group has provided OSC with a great deal of insight and expertise over the years.”
The MUG meeting provides an open forum for all attendees to discuss and share their knowledge on using the MVAPICH2 libraries on large-scale systems and a diverse set of applications.
In addition to demos, hands-on, one-on-one and open-mic sessions, thethree-day event will feature keynote addresses from Martin Schulz, professor and chair for Computer Architecture and Computer Organization at Technical University of Munich, and Amitava Majumdar, director of the Data Enabled Scientific Computing division at San Diego Supercomputing Center.
The conference also will include tutorials from ARM, Mellanox and Panda’s Network-Based Computing Research Group, focusing on upcoming developments, as well as invited talks from many organizations (Lawrence Livermore National Laboratory, Texas Advanced Computing Center, Jülich Supercomputing Center, Intel, ARM, Huawei, San Diego Supercomputing Center, Northeastern University, University of Texas-Austin, Rutgers University, National Science Foundation, University of Oregon, National Center for Atmospheric Research, University of Tokyo, University of Luxembourg, Tsinghua University and The Ohio State University.).
MVAPICH2 is a popular open-source implementation of the MPI-3.1 standard prevalent on systems with InfiniBand, Omni-Path, iWARP or RoCE interconnects. Message Passing Interface (MPI), the lingua franca of scientific parallel computing, is a standard for the communications library that a parallel application uses to share data among tasks and is available on a variety of parallel computer platforms.
In addition to OSC’s Owens, Ruby and Oakley systems and those at more than 2,925 organizations in 86 countries worldwide, MVAPICH is powering the second fastest supercomputer: The Sunway TaihuLight at the National Supercomputing Center in Wuxi, China, built to process 125 quadrillion calculations per second.
This year’s MUG meeting is sponsored by OSC, Mellanox Technologies, Paratools, X-ScaleSolutions, National Science Foundation, and The Ohio State University.
