Many applications require wire speed searches of information. The searches normally involve simultaneous comparison of the desired information against the entire list of prestored entries. Image, voice, computer, and communication systems are possible platforms for such applications. My proposed SCAM (Super Content-Addressable Memory) may have great potential in supporting DNS operations, URL filtering, network devices address lookup and translation, and virus signature matching. In the first two articles of this series, I will describe the organization of SCAM and show how it manipulates different data types and queries. The third article will describe some associative logic and mathematical algorithms, and will elaborate on performance issues and calculations relevant to SCAM. The fourth article will be dedicated to the realization of SCAM building blocks using ispLEVER tools. The final article will cover assembling those building blocks into a FPGA device using ABEL hardware description language.
展开▼
