This paper considers the efficiency of packet buffers used in packet switches built using Network Processors (NPs). Packet buffers are typically implemented using DRAM, which provides plentiful buffering at a reasonable cost. The problem addressed in this paper is that a typical NP workload may be unable to utilize the peak DRAM bandwidth. Since the bandwidth of the packet buffer is often the bottleneck in the performance of a shared-memory packet switch, inefficient use of available DRAM bandwidth further reduces the packet throughput. Specialized hardware-based schemes that alleviate the DRAM bandwith problem in high-end routers may be less applicable to NP-based systems, in which cost is an important consideration.
Auf dem Entwicklerkongress präsentiert der weltgrößte Softwarehersteller die neuesten Informationen zum... » mehr
Intels schnellster Core-
Nach Wellen großer Begeisterung war es 2009 ruhig um Second Life geworden -