NERSCPowering Scientific Discovery Since 1974

Eric Roman

Eric Roman
HPC Systems Engineer
NERSC, Computational Systems
Phone: (510) 486-6420

Biographical Sketch

Eric Roman is a computer systems engineer at Lawrence Berkeley National Laboratory. He joined LBNL in 1999.

From 2004-2006 he took leave to pursue a Ph.D. In physics at the University of California at Berkeley, where he performed ab initio simulations of nonlinear optical properties of semiconductors, spin transport in metals, and the anomalous Hall effect. He completed his doctoral dissertation entitled “Orientation Dependence of the Anomalous Hall Effect in 3D Ferromagnets” in 2010.

His research at LBNL focuses on operating systems for high-performance computing. He has participated in the development of Berkeley Lab's Checkpoint/Restart (BLCR) since the start of the project in 2001. He wrote the initial re-
quirements and implementation surveys before moving on to implement multithreaded checkpoints and restarts. He later implemented BLCR's support for files, pipes, on-the-fly compression of checkpoint files, and direct I/O. In 2008, he worked with Cluster Resources Inc. to add BLCR support to the Torque batch system. In 2003 he led a seminar on the Linux kernel attended by NERSC and Sandia-Livermore. In 2004 he organized the FastOS project “High-End Computing with K42.” He currently is working to optimize file I/O operations in BLCR, and participates in LBNL's collaboration with the Berkeley ParLab.

Conference Papers

Brian Austin, Eric Roman, Xiaoye Sherry Li, "Resilient Matrix Multiplication of Hierarchical Semi-Separable Matrices", Proceedings of the 5th Workshop on Fault Tolerance for HPC at eXtreme Scale, Portland, OR, June 15, 2015,

Khaled Z. Ibrahim, S. Hofmeyr, Eric Roman, "Optimized Pre-Copy Live Migration for Memory Intensive Applications", The International Conference for High Performance Computing, Networking, Storage, and Analysis, 2011,


Massimiliano Albanese, Michael Berry, David Brown, Scott Campbell, Stephen Crago, George Cybenko, Jon DeLapp, Christopher L. DeMarco, Jeff Draper, Manuel Egele, Stephan Eidenbenz, Tina Eliassi-Rad, Vergle Gipson, Ryan Goodfellow, Paul Hovland, Sushil Jajodia, Cliff Joslyn, Alex Kent, Sandy Landsberg, Larry Lanes, Carolyn Lauzon, Steven Lee, Sven Leyffer, Robert Lucas, David Manz, Celeste Matarazzo, Jackson R. Mayo, Anita Nikolich, Masood Parvania, Garrett Payer, Sean Peisert, Ali Pinar, Thomas Potok, Stacy Prowell, Eric Roman, David Sarmanian, Dylan Schmorrow, Chris Strasburg, V.S. Subrahmanian, Vipin Swarup, Brian Tierney, Von Welch, "ASCR Cybersecurity for Scientific Computing Integrity", DOE Workshop Report, January 7, 2015,

At the request of the U.S. Department of Energy’s (DOE) Advanced Scientific Computing Research (ASCR) program, a workshop was held January 7–9, 2015, in Rockville, Md., to examine computer security research gaps and approaches for assuring scientific computing integrity specific to the mission of the DOE Office of Science. Issues included research computation and simulation that takes place on ASCR computing facilities and networks, as well as network-connected scientific instruments, such as those run by other DOE Office of Science programs. Workshop participants included researchers and operational staff from DOE national laboratories, as well as academic researchers and industry experts. Participants were selected based on the prior submission of abstracts relating to the topic. Additional input came from previous DOE workshop reports [DOE08,BB09] relating to security. Several observers from DOE and the National Science Foundation also attended.


Alex Druinsky, Brian Austin, Xiaoye Sherry Li, Osni Marques, Eric Roman, Samuel Williams, "A Roofline Performance Analysis of an Algebraic Multigrid PDE Solver", SC14, November 2014,