A publication of the Advanced Simulation & Computing Division, NA-121.2, NNSA Defense Programs
December 2008
NA-ASC-500-08—Issue 9
Return to this issue’s stories
ASC Salutes Paul Henning
If you can imagine how it would be to be faced with demonstrating performance on a radically new computer architecture and to write code without having the real processors, memory, or interconnect, then you can understand how exciting Paul Henning’s life has been while working on the new Roadrunner supercomputer. A technical staff member in the Computing, Computation, and Statistical Sciences Division at Los Alamos National Laboratory (LANL), Paul has been involved with the ASC Program since January 1999.
Paul Henning (left) discussing his approach to put Milagro on Roadrunner with colleague Tim Kelley.
As part of LANL’s Advanced Algorithms and Applications Team, Paul is a key contributor to the Roadrunner project. His implementation of a hybrid radiation transport application was one in a suite of performance demonstrations that changed the course of the Roadrunner project to gain full support for execution of the third phase of the petascale machine last December. He also led the design of a hybrid computing communications API (application program interface) specification.
Paul recalls that designing the communications API was risky, because the hardware design had not yet been finalized. “We drew on the experience that we had with the Cell processors and parallel communications to design a flexible API.” That flexibility was tested almost immediately when LANL and IBM devised a new, more power-efficient architecture. “Although the library implementation had to change, the API accommodated the radical design change.”
Paul is working with NNSA and ASC university alliances to be part of the solution to technical problems surrounding this shift in complexity and technology. According to Paul, “The new computers shift complexity from the hardware to the software, making our codes even more intricate. In order to put these new machines to work for us on scientific computing problems, we will have to develop new programming models and prepare developers to work in new environments.” Paul is enthusiastic about the opportunities that are present with the challenges that must be met to keep one leap ahead of technology. “It is very exciting,” he says, “to be involved in computing at this time of rapid innovation.”
Paul has a Ph.D. in Computer Science from the University of Iowa. Before coming to Los Alamos, Paul worked as a student at NASA Ames Research Center and Sandia National Laboratories. While at NASA Ames, Paul was part of a team that had an instrument on the Mars Pathfinder mission—the first rover on Mars. Recalling the excitement of being at mission control at the Jet Propulsion Laboratory for the touchdown of the rover, Paul expresses how fortunate he feels to be involved in cutting-edge projects. “Whether it’s rovers or supercomputers, the best part is the opportunity to work on great teams. I can’t wait to see what is next.”
To see Paul’s presentation Milagro II, a discussion of a different approach to put Milagro on Roadrunner, what results were obtained, what was learned, and what is next, go to the Roadrunner technical seminars at http://www.lanl.gov/orgs/hpc/roadrunner/rrseminars.shtml
DOE Privacy Disclaimer | Sandia Privacy Disclaimer | 2008-4454 W
Developed and maintained by Sandia National Laboratories for NA-121.2