Space-Efficient TCAM-Based Classification Using Gray Coding

Abstract

Ternary content-addressable memories (TCAMs) are increasingly used for high-speed packet classification. TCAMs compare packet headers against all rules in a classification database in parallel and thus provide high throughput unparalleled by software-based solutions. TCAMs are not well-suited, however, for representing rules that contain range fields. Such rules have to be represented by multiple TCAM entries. The resulting range expansion can dramatically reduce TCAM utilization. The majority of real-life database ranges are short. We present a novel algorithm called short range gray encoding (SRGE) for the efficient representation of short range rules. SRGE encodes range borders as binary reflected gray codes and then represents the resulting range by a minimal set of ternary strings. SRGE is database independent and does not use TCAM extra bits.For the small number of ranges whose expansion is not significantly reduced by SRGE, we use dependent encoding that exploits the extra bits available on today's TCAMs. Our comparative analysis establishes that this hybrid scheme utilizes TCAM more efficiently than previously published solutions.The SRGE algorithm has worst-case expansion ratio of 2W −4, where W is the range-field length . We prove that any TCAM encoding scheme has worst-case expansion ratio W or more.

Ingredients to enhance the performance of two-stage TCAM-based packet classifiers in internet of things: greedy layering, bit auctioning and range encoding

“…In comparison, the SRGE algorithm (short range gray encoding) which was proposed in [20] is an efficient, database-independent encoding scheme. This scheme does not require extra bits.…”

“…This scheme does not require extra bits. Bremler-Barr and Hendler [20,21] proposed SRGE as an independent range encoding algorithm based on their observations. They found that encoding the ranges that are available in queues in real databases would be much more efficient when using the Gray code.…”

“…In TCAM-based methods, performing a parallel search on all the inputs requires high power consumption [14][15][16][17][18][19][20][21][22][23][24][25][26][27]. Therefore, several methods have been proposed based on the categorization of the TCAM inputs to reduce power consumption [10, 14-16, 18, 20-23, 27, 28].…”

Design and Performance Analysis of Low Power High Speed CNTFET Binary Content Addressable Memory Cell for Next Generation Communication Networks

“…Post-layout simulations at 45-nm technology disclosed that the power is decreased substantially up to 93%. Many other techniques are presented to improve the performance of the CAM cells [14][15][16][17][18][19][20][21]. But all methods based on CMOS result in high energy consumption.…”

Content Addressable Memory—Early Predict and Terminate Precharge of Match-Line

“…The parallel hardware search scheme of the CAM outperforms the software-based search algorithms [1]. Thus, CAM is an important lookup table hardware for applications like network routers [2], data compression [3], image processing [4], and data management [5]. The parallel active circuits in CAM make it power hungry.…”