|
HPCC Group / Home Scalable and
Dependable Applications and Infrastructure for High-Performance
Computing and Networking
The high-performance computing and communications (HPCC) group primarily focuses upon critical
protocols, architectures, services, and applications for efficient, scalable, and dependable
forms of high-performance computing and networking. Current activities focus upon the Dolphin, Energy-Efficient Internet, iVDGL, and UltraLight projects.
For the past decade, the group has also been working with a variety of cutting-edge
high-performance networking technologies as well such as 10 Gigabit and Gigabit Ethernet,
DDR and SDR Infiniband, RapidIO, Quadrics QsNet, Scalable Coherent Interface (SCI), Myrinet, Fibre Channel, ATM, SuperHIPPI,
Giganet cLAN, Synfinity, etc. A broad range of testbed experiments, coupled with the development
of a number of simulative and analytical models for high-performance networks, have led to new
and better insight about the inherenet performance characteristics and tradeoffs of
high-performance network protocols and technologies for application in general-purpose HPC
systems as well as embedded and real-time systems.
Sponsors:
National Science Foundation,
US Navy
Principal Investigators: Dr. Alan D. George, Dr. Ann Gordon-Ross
Group Members
Karthik Sabhanatarajan, MS student, group leader
Baoke Zhang, MS student
Related Links
Avionics
Fiber-Optics and Photonics Conference (AVFOP)
MILCOM 2006
GEMS web page
UPC@Florida web page
Acknowledgements
We gratefully acknowledge the following vendors for their support of this
group:
MLDesign Technologies for
their donation of software tools.
Dolphin Interconnects for
their donation of SCI equipment and software tools.
Intel for their donation of Xeon
processors and motherboards for Kappa
cluster.
AMD for their donation of Opteron
processors for Lambda cluster.
Scali
for their donation of ScaMPI and other software tools for SCI.
|
 |
![[the lab]](/img/b_lab.gif)
![[projects]](/img/b_projects.gif)
![[people]](/img/b_people.gif)
