DESIGN VIEW is the summary of the complete DESIGN SOLUTION contributed article, which begins on Page 2.
When software-implemented compression schemes run out of steam, give your CPU a break by employing these speedy hardware-based techniques.
Companies want to reduce their WAN bandwidth requirements to minimize cost and reduce network congestion. As a result of these forces, considerable interest is bubbling up in the area of data compression as a way to reduce the number of packets that must be transmitted across networks.
Two broad categories of compression are currently in use. In lossy compression, data is intentionally discarded. As a result, the decompression of the data doesn't exactly match the original data. This method will allow for higher compression ratios and is useful if the lost data has minimal effect on the decompressed output. Typical applications for lossy compression include audio and video compression.
Lossless compression is used for applications where the original data must be fully restored following decompression. Examples of applications requiring lossless compression include network data, medical and satellite imaging, and military traffic.
Until now, compression algorithms such as the Lempel-Ziv-Welch (LZW) have been implemented in software. This provided acceptable compression performance in many older systems. But with today's increasing numbers of connections, Web servers are now a bottleneck. CPU-intensive compression algorithms can no longer scale to meet next-generation requirements. Plus, as more and more content is served up dynamically, the CPU load increases significantly.
As with many such examples that predate compression, the limitations of software-based implementations are now creating an interest in the migration of this compression technology to hardware—offloading the CPU to perform higher-level functions. However, very little dedicated compression hardware currently exists. But content-addressable memories (CAMs), traditionally targeted at high-speed lookups for packet classification, can represent a key element in the acceleration of lossless compression.
Full article begins on Page 2