Joined department in 2007

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 finally, designing resource-efficient scheduling algorithms in wireless networks. Many of his 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. Prof. Kompella's past efforts in industry included brief stint at Chelsio Communications Inc. in the design of a high-speed TCP offload engine and a packet-classification co-processor at SwitchOn Networks (acquired later by PMC Sierra).