Analytical Bounds on the Threads in IXP1200 Network Processor

Increasing link speeds have placed enormous burden on the processing requirements and the processors are expected to carry out a variety of tasks. Network Processors (NP) [1] [2] is the blanket name given to the processors, which are traded for flexibility and performance. Network Processors are offered by a number of vendors; to take the main burden of processing requirement of network related operations from the conventional processors. The Network Processors cover a spectrum of design tradeoff, that span in between the custom ASIC and the general-purpose processors. IXP1200 (Intel’s network processor) is one among them. This paper focuses on deriving the analytical bounds on the optimum number of threads in IXP1200 at 1Gbps wire speed. 1