Samar Sharma

Reducing TCAM power consumption and increasing throughput

TCAMs have been an emerging technology for packet forwarding in the networking industry. They are fast and easy to use. However, due to their inherent parallel structure they consume high power - much higher than SRAMs or DRAMs. A system using four TCAMs could consume upto 60 watts. The power issue is one of the chief disadvantages of TCAMs over RAM based methods for forwarding. For a system using multiple TCAMs we present methods to significantly reduce TCAM power consumption for forwarding, making it comparable to RAM based forwarding solutions. Using our techniques one can use a TCAM for forwarding at 3 to 4 watts worst case. Our techniques also have an interesting connotation to TCAM forwarding rates. For a static distribution of requests we present methods that make the forwarding rate of a system proportional to the number of TCAMs. So if a system has four TCAMs, one could achieve a four fold performance of that of a single TCAM for a static distribution of requests.

Sorting and searching using ternary CAMs

Sorting and searching are classic problems in computing and several RAM based solutions exist. We present sorting and searching algorithms using TCAMs. Using these algorithms, one can perform sorting in O(n) memory cycles using a TCAM. Furthermore, inserts and deletes to a sorted list and priority queue operations can be done in O(1) cycles. A searching problem may typically involve finding if a query point is contained in a given set of ranges. We call this the point intersection problem. The ranges may be inserted or deleted from the set dynamically. For these problems, we present several algorithms with different time, space and implementation complexity tradeoffs. One of the algorithms uses only O(1) time for all operations and O(1) space for each range in the set when the ranges are disjoint. More precisely, one can perform disjoint range search in one memory cycle using a 2-stage pipeline. We also provide several solutions in scenarios where the ranges in the set are allowed to overlap.

A TCAM-Based Parallel Architecture for High-Speed Packet Forwarding

A partitioned TCAM-based search engine is presented that increases the packet forwarding rate multiple times over traditional TCAMs. The model works for IPv4 and IPv6 packet forwarding. Unlike the previous art, the improvement is achieved regardless of the incoming traffic pattern. Employing small and private memories that dynamically store popular route prefixes inside the ASIC and taking advantage of the inherent characteristics of Internet traffic to exploit parallelism make this improvement possible. Using four TCAM chips, an embodiment of the proposed model delivered more than six times the throughput of a conventional configuration with equal storage capacity and equal clock rate. Power consumption is also reduced in the new system. Other parameters such as storage density and table update performance are not adversely affected

High-speed and low-power network search engine using adaptive block-selection scheme

A new approach for using block-selection scheme to increase the search throughput of multi-block TCAM-based network search engines is proposed. While the existing methods try to counter and forcibly balance the inherent bias of the Internet traffic, our method takes advantage of it. Our method improves flexibility of table management and gains scalability towards high rates of change in traffic bias. It offers higher throughput than the current art and a very low average power consumption. One of the embodiments of the proposed model, using four TCAM chips, can deliver over six times the throughput of a conventional configuration of the same TCAM chips.