USRC’s systems software research is related to operating system kernels and middleware for next generation supercomputers.
USRC’s systems software research is lead by Mike Lang.
Below are the staff considered to be in the “Systems Software” group.
Hugh participated in the design and implementation of the Linux Noise Detective. The Linux Noise detective is a Linux kernel module and a GUI to collect process data directly from the kernel (on multiple cluster nodes simultaneously) and analyze the data to determine the sources of system noise. He also participated in the design and the development of the XGet file transfer software. XGet scalably transfers files to nodes within a cluster by building a tree of participants and delegating serving duties to optimal slave nodes. He participated in the development of the XCPU cluster management system. XCPU keeps the state of the cluster distributed across all nodes, allowing easy configuration of hot-spare management nodes and graceful failover that doesn't require canceling the running jobs in case of head node failure.
Dr. Xin Yuan
Professor, Dept of Computer Science, Florida State University
Dr. Xin Yuan is currently a full Professor in the Department of Computer Science at Florida State University. His research interests include parallel and distributed systems, communication optimizations, interconnection networks, and networking. He obtained his B.S. and M.S degrees in Computer Science from Shanghai Jiaotong University in 1989 and 1992, respectively. He earned his Ph.D degree in Computer Science from the University of Pittsburgh in 1998. He has published more than 80 papers in leading journals and conferences. The STAR-MPI software package that he and his students developed has been incorporated in the MPI stack of the IBM Blue Gene/P system. Dr. Yuan is currently serving on the Editorial Boards of several international journals. He has also served as the Program Chairs and vice-Chairs for several international conferences and workshops such as the International Conference on Parallel Processing (ICPP) and the IEEE International Conference on High Performance Computing (HiPC), and as Program Committee Members for many international conferences and workshops. He is a senior member of ACM and IEEE.
Dr. Yuan worked with Mike Lang, Scott Pakin, and the USRC Systems group on interconnection networks research that covers a spectrum of networking issues including topology, routing, switching, flow control, and congestion control. The goal was to identify the appropriate interconnection network technologies for the next generation supercomputers as well as the future generation exascale supercomputing systems.
Dr. Ioan Raicu
Assistant Professor in Computer Science, Illinois Institute of Technology
Dr. Ioan Raicu is an assistant professor in CS at Illinois Institute of Technology, as well as a guest research faculty in MCS at Argonne National Laboratory. He is also the founder (2011) and director of the Data-Intensive Distributed Systems Laboratory at IIT. His research work and interests are in the general area of distributed systems. His work focuses on a relatively new paradigm of Many-Task Computing (MTC), which aims to bridge the gap between two predominant paradigms from distributed systems, High-Throughput Computing (HTC) and High-Performance Computing (HPC). His work has focused on defining and exploring both the theory and practical aspects of realizing MTC across a wide range of large-scale distributed systems. He is particularly interested in resource management in large scale distributed systems with a focus on many-task computing, data intensive computing, cloud computing, grid computing, and many-core computing. Dr. Raicu has been working with Mike Lang for several years co-mentoring graduate students on exploring extreme-scale simulations in distributed services. The projects include exploring the scalability of distributed NoSQL key/value storage systems with different architectures, and distributed job-launch and scheduling through work-stealing for both MTC and HPC workloads.
Dr. Satyajayant Misra
Assist Professor, Computer Science Dept, New Mexico State University
Dr. Carlos Maltzahn
Associate Adjunct Professor Computer Science Dept, UC Santa Cruz
Dr. Patrick Bridges
Assistant Professor in Computer Science, University of New Mexico
Dr. Dorian Arnold
Professor, UNM Dept of Computer Science, University of New Mexico
Dorian is an assistant professor in the Department of Computer Science at the University of New Mexico. His research focuses on the performance and reliability of extremely large scale systems with tens of thousands, hundreds of thousands or even millions of processing elements.
Dorian is working with Mike Lang, Hugh Greenberg and the USRC Systems Group on the Redfish Project. This group investigates the basic, general computation, communication and storage primitives that underlie HPC system services and provide a library of building blocks that provides a flexible, resilient and scalable implementation of these primitives.
Dr. Sean Williams
Postdoctoral Researcher, New Mexico Consortium
PhD Student, Computer Science, Illinois Institute of Technology
PHD Student, Ira A. Fulton School of Engineering, Arizona State University
Doug is a PhD student from Arizona State University's Ira
A. Fulton School of Engineering in Tempe, Arizona. Doug returned
to USRC in the fall of 2015 after a successful summer internship
in 2013. While working at USRC, Doug began working on LANL's
contribution to the UNITY project with mentor Mike Lang, along
with collaborators from GATech and ORNL.
UNITY seeks to 'unify' the application view of memory and
storage, into one clean, simple interface developers can use
without knowledge of a machine's devices. Through UNITY, we hope
to better manage the avalanche of emerging storage and memory
technologies anticipated in future Ultrascale Systems.
During his time at USRC, Doug has published a paper on his first
project "TCASM: An asynchronous shared memory interface for
high-performance application composition" which will be used as
part of UNITY's low level data management mechanism.