Printer Friendly
The Free Library
14,588,062 articles and books
Member login
User name  
Password 
 
Join us Forgot password?

Xilinx and SiberCore Announce High-Performance Network Processing Solution; Virtex II and SiberCAM Combination Quadruples Router/Switch Throughput.


Business Editors/High Tech Writers

OTTAWA, Canada--(BUSINESS WIRE)--March 19, 2001

SiberCore Technologies and Xilinx Inc. (NASDAQ NASDAQ
 in full National Association of Securities Dealers Automated Quotations

U.S. market for over-the-counter securities. Established in 1971 by the National Association of Securities Dealers (NASD), NASDAQ is an automated quotation system that reports on
:XLNX) today jointly introduced the Virtex(R)-II SiberBridge - a register transfer level (RTL (Register Transfer Level) A high-level hardware description language (HDL) for defining digital circuits. The circuits are described as a collection of registers, Boolean equations, control logic such as "if-then-else" statements as well as complex event sequences; ) reference design that provides a high performance interface between a 32-bit host (typically a network processor) and one or more SiberCAM(TM) packet forwarding Forwarding is the relaying of packets from one network segment to another by nodes in a computer network.

The simplest forwarding model - unicasting - involves a packet being relayed from link to link along a chain leading from the packet's source to its destination.
 co-processors. The SiberBridge is fully synthesizable Verilog/VHDL reference code, suitable for implementation in the Xilinx(R) Virtex-II FPGAs. The SiberBridge provides a way to initiate searches, obtain search results, and perform table maintenance operations for the SiberCAM packet forwarding subsystem via a single 32-bit synchronous SRAM See static RAM.

SRAM - static random-access memory
 or ZBT ZBT Zeta Beta Tau (fraternity)
ZBT Zero Bus Turnaround (Integrated Device Technology, Inc.)
ZBT Zildjian Bronze Technology (cymbal)
ZBT Zero Balance Transfer
 SRAM interface.

The SiberBridge reference code is the latest product to emerge from SiberCore's SiberLink(TM) Strategic Partnership Program and was developed jointly by SiberCore and Xilinx engineers. Fully synthesizable Verilog / VHDL (VHSIC Hardware Description Language) A hardware description language (HDL) used to design electronic systems at the component, board and system level. VHDL allows models to be developed at a very high level of abstraction.  code is available for the reference design from Xilinx. Details of the Virtex-II SiberBridge are available at http://www.xilinx.com/xapp/xapp254.pdf, or in the Virtex-II Platform FPGA (Field Programmable Gate Array) A type of gate array that is programmed in the field rather than in a semiconductor fab. Containing up to hundreds of thousands of gates, there are a variety of FPGA architectures on the market.  Handbook.

"The exponential rate of change of system performance is bringing new challenges for designers who are simultaneously facing shrinking time to market requirements. The joint reference design coupling SiberCore's SiberCAM and our leadership Virtex-II family is a major leap forward in solving our customer's time-to-market challenges" said Dennis Segers, senior vice president and general manager of the Xilinx Advanced Products Group. "The combination of these two advanced devices dramatically simplifies board design, maximizes system performance and accelerates time to market for network equipment developers, by providing an off-the-shelf, proven silicon solution."

According to Andrew Sorowka, SiberCore's Vice President of Marketing, "Historically, the network processor has handled all packet classification and packet forwarding functions, as well as header parsing See parse.

parsing - parser
, encryption, compression, traffic queuing, header modification, statistics gathering, and other functions.

"Packet forwarding and classification are the most computationally intensive functions in networking equipment, typically requiring 60 percent to 70 percent of the network processor's cycle capacity. Thus, adding a co-processor, such as the SiberCAM for packet forwarding and classification offers the opportunity for substantial throughput improvement.

"The Virtex-II family is the ideal vehicle for the implementation of the intervening logic between a network processor and co-processor because of its design flexibility, high performance, and extensive support network. With the introduction of the Virtex-II SiberBridge, we expect to see this system solution implemented in a large number of next generation switching and routing sub-systems," Sorowka concluded.

The SiberCAM device is a large capacity packet forwarding and classification co-processor, based on SiberCore's ternary (programming) ternary - A description of an operator taking three arguments. The only common example is C's ?: operator which is used in the form "CONDITION ? EXP1 : EXP2" and returns EXP1 if CONDITION is true else EXP2.  content addressable memory See CAM.

content addressable memory - (CAM, or "associative memory") A kind of storage device which includes comparison logic with each bit of storage. A data value is broadcast to all words of storage and compared with the values there.
 (TCAM (TeleCommunications Access Method) IBM communications software widely used to transfer data between mainframes and 3270 terminals. See access method. ) technology. SiberCAM network co-processors significantly increase switch and router throughput, by off-loading packet forwarding and classification functions from the network processor. In addition, the SiberCAM's 3-port interface allows equipment developers to perform route and policy table management without impacting the search process, providing for sustained performance at up to 100 million searches per second (MSPS MSPS Mega-Samples Per Second
MSPS Million Samples Per Second
MSPS Michigan Society of Professional Surveyors
MSPS Modular Synthesis Plug-In System
MSPS Million Symbols per Second
MSPS mobilization stationing and planning system (US DoD) 
).

Combining a SiberCAM co-processor with an existing network processor can increase router or switch throughput by as much as four times. For example, an OC-12 router with a processor that is capable of supporting 622 Mbits per second on its own, can increase its throughput to OC-48 (2,488 Mbits per second) by adding a SiberCAM co-processor. The addition of the SiberCAM co-processor essentially allows the equipment developer to upgrade the OC-12 router to an OC-48 router, using the same basic architecture.

Typically the interface between the network processor unit (NPU (Network Processing Unit) Same as network processor. ) and packet forwarding co-processor is implemented within FPGA such as the Virtex-II devices. The SiberBridge is a simple mechanism to allow a network processor to perform searches using different threads of operation. It enables maintenance and search operations to be initiated using 32-bit registers and to organize search results for up to 32 different contexts. To the NPU the SiberBridge appears to be a memory mapped synchronous SRAM or a ZBT SRAM.

Why Virtex-II Works Best - The Virtex-II platform FPGA family allows digital system designers to implement single chip solution with density up to 10 million system gates with an abundance of on-chip memory options and advanced routing resources. Virtex-II features enable system designers to eliminate external termination resistors with on-chip XCITE XCITE Xilinx Controlled Impedance Technology  digitally controlled impedance Digitally Controlled Impedance is a function for controlling impedance (in FPGAs): [1]
  • Series resistance to match line impedance.
  • Parallel resistance to avoid reflection.
See also
  • Transmission line
References

1.
, manage 16 pre engineered low skew (1) The misalignment of a document or punch card in the feed tray or hopper that prohibits it from being scanned or read properly.

(2) In facsimile, the difference in rectangularity between the received and transmitted page.
 clock domains, with on-chip frequency and phase control (Digital Clock Manager). The family delivers complete solutions for networking applications. Designed to be implemented in a Virtex-II FPGA, the SiberBridge demonstrates an interface between a 32-bit host (network processor) and the SiberCAM device, or a cascade of SiberCAM devices. This interface takes advantage of the on-chip DDR (Double Data Rate) Refers to an SDRAM memory chip that increases performance by doubling the effective data rate of the frontside bus. For more details, see SDRAM.

DDR - Double Data Rate Random Access Memory
 registers (input and output) and the 18 Kb dual-port RAM of Virtex-II FPGA to deliver high-performance and flexible interface with SiberCAM and a comprehensive solution for networking applications.

SiberCore established its SiberLink Partnership Program to facilitate the design integration between stand-alone network processors (NPs) and its ternary CAM-based packet forwarding and classification co-processor products.

About SiberCore Technologies

SiberCore Technologies is a fabless communications semiconductor company providing silicon-based packet management products and solutions to the Internet infrastructure market. The Company's initial products are packet forwarding engines, based on ternary Content Addressable Memory (CAM) technology, that are designed to overcome the most onerous performance bottleneck in the data communications market, i.e. packet forwarding and classification. SiberCore's unique architectural and design innovations give the SiberCAM family of products significant advantages in terms of capacity, speed, feature set and power reduction. SiberCore is located in Ottawa, Canada's high technology capital. The company's web site is located at www.sibercore.com.

About Xilinx

Xilinx is the leading supplier of complete programmable logic solutions, including advanced integrated circuits, software design tools, predefined system functions delivered as cores, and unparalleled field engineering support. Founded in 1984 and headquartered in San Jose, Calif., Xilinx invented field programmable gate arrays (FPGAs) and fulfills more than half of the world demand for these devices today. Xilinx solutions enable customers to significantly reduce the time required to develop products for the computer, peripheral, telecommunication, networking, industrial control, instrumentation, aerospace, defense, and consumer markets. For more information, visit the Xilinx web site at www.xilinx.com.
COPYRIGHT 2001 Business Wire
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2001, Gale Group. All rights reserved. Gale Group is a Thomson Corporation Company.

 Reader Opinion

Title:

Comment:



 

Article Details
Printer friendly Cite/link Email Feedback
Publication:Business Wire
Date:Mar 19, 2001
Words:1010
Previous Article:Pratt & Whitney Canada Enhances Aftermarket Service Capabilities Through Acquisition.
Next Article:Nanovation Partners With Turin Networks To Develop Innovative Optical Communications Networks.
Topics:



Related Articles
IBM, XILINX: MULTI $MILLION MANUFACTURING DEAL.
XILINX UNVEILS OPEN PROTOCOL INITIATIVE FOR SCALABLE SERIAL CONNECTIVITY.
Xilinx and Tensilica announce configurable processor support for programmable systems design.
Marconi chooses Xilinx for next-gen synch digital hierarchy products.
Xilinx provides proven XAUI solution for 10 Gigabit Ethernet applications.
Xilinx Virtex-II Pro FPGAs Are 38% Faster Than Competitive Offerings Using ISE 6.1i Design Tools.
Xilinx announces free configurable PCS reference design for use with Virtex-II pro platform FPGAS.(Brief Article)
Xilinx simplifies QDR II SRAM Memory interfacing with new Virtex-II Pro memory tool kit.
Xilinx shatters 2.4 terabit PICMG 3.0 bandwidth barrier by demoing 10Gbps serial signaling over ATCA backplane.(Advanced Telecom and Compute...
Xilinx delivers the industry's fastest high-speed serial transceivers.

Terms of use | Copyright © 2009 Farlex, Inc. | Feedback | For webmasters | Submit articles