| Professor. Kompella's main
research area is computer networks. Particular
topics of interest include scalable inference mechanisms for fault
localization
in enterprise as well as backbone networks, scalable streaming
algorithms and
architectures for various router functions such as traffic measurement,
attack
detection, packet classification and fair queuing, and designing
resource-efficient scheduling algorithms in wireless networks. Many of Prof. Kompella's past inventions resulted in direct industrial impact. Prof. Kompella's dissertation research resulted in the development of sophisticated fault localization tools that can pin-point the location of the failure in large-scale backbone networks. These tools are used daily by a major Internet service provider in their backbone. Along with collaborators at Stanford, he helped pioneer hybrid SRAM-DRAM memory designs for high-capacity high-speed packet buffers in routers. His past efforts in industry included hardware design of a high-speed TCP offload engine at Chelsio Communications Inc. and a packet-classification co-processor at SwitchOn Networks (acquired later by PMC Sierra). Dr. Kompella joined Purdue in August of 2007 as an Assistant Professor in Computer Science after obtaining his Ph.D. degree from UCSD. He obtained his Masters degree from Stanford University in 2001 and an B.Tech degree from IIT Bombay in 1999, both in Computer Science. |