HomeGate Backplane Solutions Brian Von Herzen, Ph.D. Xilinx Consultant June 21, 2004 ISO/IEC JTC1 SC25/WG1 N1118 23 June 2004 (Von Herzen,

Slides:



Advertisements
Similar presentations
Bus Architecture.
Advertisements

Unit Subtitle: Bus Structures Excerpted from 1.
StreamBlade SOE TM Initial StreamBlade TM Stream Offload Engine (SOE) Single Board Computer SOE-4-PCI Rev 1.2.
BY TONY JIA Mother Board and Buses. What is a Mother Board? The motherboard is the largest piece of internal hardware. All of the other internal.
The TickerTAIP Parallel RAID Architecture P. Cao, S. B. Lim S. Venkatraman, J. Wilkes HP Labs.
ESODAC Study for a new ESO Detector Array Controller.
SFI-4.1 Brian Von Herzen, Ph.D. Xilinx Consultant,
Digital Signal Processing and Field Programmable Gate Arrays By: Peter Holko.
IBM RS6000/SP Overview Advanced IBM Unix computers series Multiple different configurations Available from entry level to high-end machines. POWER (1,2,3,4)
June 2007 RAMP Tutorial BEE3 Update Chuck Thacker John Davis Microsoft Research 10 June, 2007.
Parallel JPEG2000 Compression System Performed by: Dmitry Sezganov, Vitaly Spector Instructor: Stas Lapchev, Artyom Borzin.
Performed by : Rivka Cohen and Sharon Solomon Instructor : Walter Isaschar המעבדה למערכות ספרתיות מהירות High Speed Digital Systems Laboratory הטכניון.
1 Fast Communication for Multi – Core SOPC Technion – Israel Institute of Technology Department of Electrical Engineering High Speed Digital Systems Lab.
Detector Array Controller Based on First Light First Light PICNIC Array Mux PICNIC Array Mux Image of ESO Messenger Front Page M.Meyer June 05 NGC High.
HS/DSL Project Yael GrossmanArik Krantz Implementation and Synthesis of a 3-Port PCI- Express Switch Supervisor: Mony Orbach.
CPU Chips The logical pinout of a generic CPU. The arrows indicate input signals and output signals. The short diagonal lines indicate that multiple pins.
Router Architectures An overview of router architectures.
May 8, Peripheral Design Options For USB 2.0 Solutions Dave Thompson Manager of High Speed I/O Development Agere Systems,
Field Programmable Gate Array (FPGA) Layout An FPGA consists of a large array of Configurable Logic Blocks (CLBs) - typically 1,000 to 8,000 CLBs per chip.
System Architecture A Reconfigurable and Programmable Gigabit Network Interface Card Jeff Shafer, Hyong-Youb Kim, Paul Willmann, Dr. Scott Rixner Rice.
Router Architectures An overview of router architectures.
PHY 201 (Blum) Buses Warning: some of the terminology is used inconsistently within the field.
Juanjo Noguera Xilinx Research Labs Dublin, Ireland Ahmed Al-Wattar Irwin O. Irwin O. Kennedy Alcatel-Lucent Dublin, Ireland.
Peripheral Buses COMP Jamie Curtis. PC Buses ISA is the first generation bus 8 bit on IBM XT 16 bit on 286 or above (16MB/s) Extended through.
Asis AdvancedTCA Class What is a Backplane? A backplane is an electronic circuit board Sometimes called PCB (Printed Circuit Board) containing circuitry.
Xilinx at Work in Hot New Technologies ® Spartan-II 64- and 32-bit PCI Solutions Below ASSP Prices January
Computer Organization CSC 405 Bus Structure. System Bus Functions and Features A bus is a common pathway across which data can travel within a computer.
Chapter 6 High-Speed LANs Chapter 6 High-Speed LANs.
Networking Virtualization Using FPGAs Russell Tessier, Deepak Unnikrishnan, Dong Yin, and Lixin Gao Reconfigurable Computing Group Department of Electrical.
Chapter Five Network Architecture. Chapter Objectives  Describe the basic and hybrid LAN technologies  Describe a variety of enterprise-wide and WAN.
… when you will open a computer We hope you will not look like …
Peripheral Busses COMP Jamie Curtis. PC Busses ISA is the first generation bus 8 bit on IBM XT 16 bit on 286 or above (16MB/s) Extended through.
© Copyright Xilinx 2004 All Rights Reserved 9 November, 2004 XUP Virtex-II Pro Development System.
1 Chapter Overview Understanding Expansion Buses Configuring Expansion Cards Cables and Connectors.
 Fiber optic network in ring topology  Custom software implementing a Time Division Multiplexing (TDM) scheme  Documentation summarizing conclusions.
Computer Maintenance Unit Subtitle: Bus Structures Excerpted from Copyright © Texas Education Agency, All rights reserved.
LOGO BUS SYSTEM Members: Bui Thi Diep Nguyen Thi Ngoc Mai Vu Thi Thuy Class: 1c06.
Buses Warning: some of the terminology is used inconsistently within the field.
Spartan-II Memory Controller For QDR SRAMs Lobby Pitch February 2000 ®
Architecture Examples And Hierarchy Samuel Njoroge.
Electronics in High Energy Physics Introduction to Electronics in HEP Field Programmable Gate Arrays Part 1 based on the lecture of S.Haas.
SLAC Particle Physics & Astrophysics The Cluster Interconnect Module (CIM) – Networking RCEs RCE Training Workshop Matt Weaver,
Gigabit Ethernet.
1 Dynamic Interconnection Networks Miodrag Bolic.
LAN Switching and Wireless – Chapter 1
J. Christiansen, CERN - EP/MIC
® SPARTAN Series High Volume System Solution. ® Spartan/XL Estimated design size (system gates) 30K 5K180K XC4000XL/A XC4000XV Virtex S05/XL.
Distributed Processors Allow Revolutionary Hardware & Software Partitioning Version 1.1 –March 2002 – APD / J-L Brelet & P Hardy - All right reserved -
Agata Week – LNL 14 November 2007 Global Readout System for the AGATA experiment M. Bellato a a INFN Sez. di Padova, Padova, Italy.
Computer Architecture Part IV-B: I/O Buses. Chipsets Intelligent bus controller chips found on the motherboard Enable higher speeds on one or more buses.
1 Abstract & Main Goal המעבדה למערכות ספרתיות מהירות High speed digital systems laboratory The focus of this project was the creation of an analyzing device.
EMBEDDED SYSTEMS ON PCI. INTRODUCTION EMBEDDED SYSTEMS PERIPHERAL COMPONENT INTERCONNECT The presentation involves the success of the widely adopted PCI.
Infiniband Bart Taylor. What it is InfiniBand™ Architecture defines a new interconnect technology for servers that changes the way data centers will be.
Design Criteria and Proposal for a CBM Trigger/DAQ Hardware Prototype Joachim Gläß Computer Engineering, University of Mannheim Contents –Requirements.
Senior Design May High Performance Optical Interconnect April 24, 2007.
CS 4396 Computer Networks Lab Router Architectures.
Industrial Controls Engineering Department First CERN PXI Users Group meeting 19 th October 2011 – Hubert REYMOND – EN/ICE 1.
1 Chapter 2 Central Processing Unit. 2 CPU The "brain" of the computer system is called the central processing unit. Everything that a computer does is.
Reconfigurable Computing: HPC Network Aspects Mitch Sukalski (8961) David Thompson (8963) Craig Ulmer (8963) Pete Dean R&D Seminar December.
Input/Output Organization III: Commercial Bus Standards CE 140 A1/A2 20 August 2003.
Local Area Networks: Monil Adhikari. Primary Function of a LAN File serving – large storage disk drive acts as a central storage repository Print serving.
Guide to Networking Essentials Fifth Edition Chapter 2 Network Design Essentials.
Trigger Hardware Development Modular Trigger Processing Architecture Matt Stettler, Magnus Hansen CERN Costas Foudas, Greg Iles, John Jones Imperial College.
Delivered by.. Love Jain p08ec907. Design Styles  Full-custom  Cell-based  Gate array  Programmable logic Field programmable gate array (FPGA)
What is a Bus? A Bus is a communication system that transfers data between components inside a computer or between computers. Collection of wires Data.
ROM. ROM functionalities. ROM boards has to provide data format conversion. – Event fragments, from the FE electronics, enter the ROM as serial data stream;
FPGA Technology Overview Carl Lebsack * Some slides are from the “Programmable Logic” lecture slides by Dr. Morris Chang.
System on a Programmable Chip (System on a Reprogrammable Chip)
Dr. Jeffrey M. Harris Director of Research and System Architecture
I/O BUSES.
Presentation transcript:

HomeGate Backplane Solutions Brian Von Herzen, Ph.D. Xilinx Consultant June 21, 2004 ISO/IEC JTC1 SC25/WG1 N June 2004 (Von Herzen, Chitose)

Problem Statement Homegate needs hardware solutions near-term. Key applications include HDTV input, output and processing elements. Compressed HDTV streams may utilize 25 Mbps bandwidth up to several hundred Mbps bandwidth Uncompressed HDTV streams require bandwidths of 1.5 Gbps How can Homegate handle HDTV streams cost- effectively?

Strategic Objectives Designing HomeGate hardware for the HDTV 1.5 Gbps bandwidth requirement is a key step to ensuring its relevance over the coming decade for use in the home. Rapid adoption of Homegate requires having a hardware infrastructure available so that new Homegate card and system vendors can get up to speed quickly and develop new hardware with a minimum of engineering development costs.

Possible Solutions Possible backplane electrical standards include – 100Base-T – MII (100 Mbps) – GMII (1 Gbps) – XGMII (10 Gbps) – 1000-Base-CX (1 Gbps) – Aurora (Single-lane XAUI, Gbaud) – PCI Express – Serial Rapid IO (2.5 Gbaud)

Lesson from the PC Industry Intel has moved from PCI to AGP to PCI-X to PCI- Express. Namely from parallel to serial bus solutions. They have determined that multi-gigabit serial solutions offer better price-performance than parallel backplane solutions. Homegate can ride the current price-performance improvement wave of bit-serial multi-gigabit transceiver solutions and avoid the cost of parallel backplane buses entirely.

Good News A wide variety of FPGA, ASIC, ASSP (application- specific standard products) and processor firms have embraced serial multi-gigabit solutions in their existing product families. These products are now riding a steep cost-reduction curve to enable cost-effective bit-serial solutions in today’s marketplace.

Interconnect For backplane-based Homegate applications, multi- gigabit serial solutions provide maximum data bandwidth using the minimum number of electrical connections For distributed Homegate applications, multi-gigabit cabling such as Serial ATA cables provide cost-effective yet robust interconnect. Full-mesh architectures are available, eliminating the need for a central switch card.

N NN N N NN N Fabric Topologies: Full-Mesh In a Full-Mesh Each Node Has a Direct Connection to Every Other Node Switch Fabric is Distributed Across Line Cards REDUCED cost of entry for a base-level Homegate system No switch-card needed

N NN N N NN N Central Switch Fabric Topologies: Star A Star Uses a Centralized Switch Fabric Redundant Switch Fabrics are Typically Used for Fault Tolerance Switch card is needed even for a 2-slot application. Increased cost of entry

Fabric topology for Homegate If Homegate implements a full-mesh topology, every card has a direct connection to every other card. Entry-level costs of Homegate are lower with a full mesh, since no switch card is needed. Using data forwarding, unoccupied cards can increase effective bandwidth to heavily utilized cards. Full-mesh implementations are available on FPGA’s today. For example, the MTX core is currently shipping from Xilinx and provides a complete switching solution for full-mesh architectures.

FPGA Solutions FPGA’s can help prototype early versions of a new standard like Homegate. They provide essential system elements, such as multi- gigabit transceivers (MGT’s), processor cores, logic capability, and dozen’s of IO standards. Small FPGA’s enable cost-effective nodes for low- bandwidth applications, while large FPGA’s exceeding 10-million-gates provide high-performance capability for intensive HDTV processing.

Virtex-II Pro™ Platform FPGA Virtex®-II Fabric – Upward Compatible – Same Design Tools as other FPGA’s Up to four IBM 405 PowerPCs – Industry standard – 420 DMIPS at 300 MHz Up to 24 Serial Transceivers – 622 Mbps to Gbps 2VP100 Combining Proven Functionalities

Conclusion Homegate needs to aim high enough on the performance curve to provide HDTV solutions for the rest of this decade. Multi-gigabit performance is required to support uncompressed HDTV applications in the home. FPGA’s, ASIC’s and ASSP’s are available today that provide cost- effective multi-gigabit (MGT) serial solutions to the Homegate backplane and cabling requirements. FPGA platform technology, including MGT’s, processors, parallel I/O and logic provide a key building block to bootstrapping new standards initiatives and efforts.