HOLMS John F. Snowdon February 20th 2004.

Slides:



Advertisements
Similar presentations
Assembly and Packaging TWG
Advertisements

Electrical and Computer Engineering UAH System Level Optical Interconnect Optical Fiber Computer Interconnect: The Simultaneous Multiprocessor Exchange.
EEE226 MICROPROCESSORBY DR. ZAINI ABDUL HALIM School of Electrical & Electronic Engineering USM.
Khaled A. Al-Utaibi  Computers are Every Where  What is Computer Engineering?  Design Levels  Computer Engineering Fields  What.
GPGPU Introduction Alan Gray EPCC The University of Edinburgh.
Mohammed Yousef Abd El ghany, Faculty of Eng., Comm. Dep., 3rd year. Digital Signal Processor The Heart of Modern Real-Time Control Systems.
Cache Coherent Distributed Shared Memory. Motivations Small processor count –SMP machines –Single shared memory with multiple processors interconnected.
Chapter 8 Hardware Conventional Computer Hardware Architecture.
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)
Some Thoughts on Technology and Strategies for Petaflops.
11/14/05ELEC Fall Multi-processor SoCs Yijing Chen.
© intec 2000 Reasons for parallel optical interconnects Roel Baets Ghent University - IMEC Department of Information Technology (INTEC)
1 6/22/ :39 Chapter 9Fiber Channel1 Rivier College CS575: Advanced LANs Chapter 9: Fibre Channel.
Optoelectronic Multi-Chip Module Demonstrator System Jason D. Bakos Donald M. Chiarulli, Steven P. Levitan University of Pittsburgh, USA.
IBM RS/6000 SP POWER3 SMP Jari Jokinen Pekka Laurila.
University of Kansas Research Interests David Andrews Rm. 324 Nichols
UCB November 8, 2001 Krishna V Palem Proceler Inc. Customization Using Variable Instruction Sets Krishna V Palem CTO Proceler Inc.
Introduction to Metropolitan Area Networks and Wide Area Networks TDC 362 / TDC 460.
SET TOP BOX What is set-top box ? An interactive device which integrates the video and audio decoding capabilities of television with a multimedia application.
Module I Overview of Computer Architecture and Organization.
Chapter 1: Overview Lecturer: Alias Mohd Telecommunications Department Faculty of Electrical Engineering UTM SET 4573: Data Communication and Switching.
Computer performance.
Xilinx at Work in Hot New Technologies ® Spartan-II 64- and 32-bit PCI Solutions Below ASSP Prices January
Computer Architecture and Organization
SARAN THAMPY D SARAN THAMPY D S7 CSE S7 CSE ROLL NO 17 ROLL NO 17 Optical computing.
Computer System Architectures Computer System Software
Chapter 4 Local Area Networks. Layer 2: The Datalink Layer The datalink layer provides point-to- point connectivity between devices over the physical.
ECE 526 – Network Processing Systems Design Network Processor Architecture and Scalability Chapter 13,14: D. E. Comer.
Efficiency and Demand Response NARUC Washington, DC February 14, 2006 Steve Specker President & CEO.
 Fiber optic network in ring topology  Custom software implementing a Time Division Multiplexing (TDM) scheme  Documentation summarizing conclusions.
Silicon Building Blocks for Blade Server Designs accelerate your Innovation.
1 Roland Kersting Department of Physics, Applied Physics, and Astronomy The Science of Information Technology Computing with Light the processing.
Architecture Examples And Hierarchy Samuel Njoroge.
1 Dynamic Interconnection Networks Miodrag Bolic.
Chapter 1 Introduction. Objectives To explain the definition of computer architecture To discuss the history of computers To describe the von-neumann.
F. Gharsalli, S. Meftali, F. Rousseau, A.A. Jerraya TIMA laboratory 46 avenue Felix Viallet Grenoble Cedex - France Embedded Memory Wrapper Generation.
COMPARISON B/W ELECTRICAL AND OPTICAL COMMUNICATION INSIDE CHIP Irfan Ullah Department of Information and Communication Engineering Myongji university,
Patrick R. Haspel, University of Mannheim1 FutureDAQ Kick-off Network Design Space Exploration andAnalysis Computer Architecture Group Prof. Brüning Patrick.
Computer Science 101 Computer Systems Organization.
Scott Ferguson Section 1
CSE 291A Interconnection Networks Instructor: Prof. Chung-Kuan, Cheng CSE Dept. UCSD Winter-2007.
A Systematic Approach to the Design of Distributed Wearable Systems Urs Anliker, Jan Beutel, Matthias Dyer, Rolf Enzler, Paul Lukowicz Computer Engineering.
Future Internet Architecture: The NSF FIND Program Dynamic Optical Circuit Switched (DOCS) Networks for Future Large Scale Dynamic Networking Environments.
Latest ideas in DAQ development for LHC B. Gorini - CERN 1.
Operating System Issues in Multi-Processor Systems John Sung Hardware Engineer Compaq Computer Corporation.
EECB 473 Data Network Architecture and Electronics Lecture 1 Conventional Computer Hardware Architecture
Assaf Shacham, Keren Bergman, Luca P. Carloni Presented for HPCAN Session by: Millad Ghane NOCS’07.
Basic Logic Functions Chapter 2 Subject: Digital System Year: 2009.
16 February 2011Ian Brawn1 The High Speed Demonstrator and Slice Demonstrator Programme The Proposed High-Speed Demonstrator –Overview –Design Methodology.
1 Chapter Overview  Network Cables  Network Interface Adapters  Network Hubs.
Multiprocessor  Use large number of processor design for workstation or PC market  Has an efficient medium for communication among the processor memory.
Motherboard Group 1 1.
ARUN S CS-7 NO:6. HIGH SPEED OPTICAL CABLE TECHNOLOGY HIGH BANDWIDTH UNIVERSAL CONNECTOR SUPPORTS MULTIPLE PROTOCOLS  10Gb/s to 100Gb/s  single universal.
THE COMPUTER MOTHERBOARD AND ITS COMPONENTS Compiled By: Jishnu Pradeep.
Lecture 13 Parallel Processing. 2 What is Parallel Computing? Traditionally software has been written for serial computation. Parallel computing is the.
System on a Programmable Chip (System on a Reprogrammable Chip)
MAHARANA PRATAP COLLEGE OF TECHNOLOGY SEMINAR ON- COMPUTER PROCESSOR SUBJECT CODE: CS-307 Branch-CSE Sem- 3 rd SUBMITTED TO SUBMITTED BY.
Computer Architecture Furkan Rabee
William Stallings Computer Organization and Architecture 6th Edition
Asynchronous Transfer Mode
Microarchitecture.
ERA Broadband Research Network for Radio Astronomy Produced by Ron McArthur September 2002 Tel: +44 (0) Fax: +44 (0) Meet-me:
What is Fibre Channel? What is Fibre Channel? Introduction
Architecture & Organization 1
Architecture & Organization 1
Overview of Computer Architecture and Organization
Introduction to Multiprocessors
ADAS RADAR CO-PROCESSOR
Multiprocessor System Interconnects
Presentation transcript:

HOLMS John F. Snowdon February 20th 2004

Research

Conjunct Dynamic Serial Optical Interconnect (DSOI) A next generation protocol-agile serial optical interconnect component. New market between telecoms and traditional parallel all electrical transmission. Stepping stone from solely electrical short range interconnects to high bandwidth optical solutions. Uses proven components creating a low cost, tolerance insensitive part. Optoelectronics are used in a manner that is both cost-effective and technologically elegant.

Demonstrator Projects Advanced Modelling of Optical Systems (AMOS) Partners: Leeds University and Silicon Graphics. Neural Optoelectronic Switch Controller (NOSC) Partners: Transtech, BT and NeuScience. High-Speed Optoelectronic Memory (HOLMS) Partners: ETH Zurich, Siemens and Hagen Univeristy et. al. Programmable Optoelectronic Computer Architectures (POCA) Partners: Edinburgh University, Xilinx and BAe Systems. System for Transparent Avionics (STAR) Partners: Imperial College London, BAe Systems and DERA.

Partners BAe Systems, UK British Telecom, UK Ecole Superieure d'Electricite (SUPELEC), France ILFA GmbH, Germany Imperial College London, UK Leeds University, UK Siemens Business Services GmbH & Co. OHG, Germany Silicon Graphics Inc., UK Swiss Federal Institute of Technology (ETHZ), Switzerland Terahertz Photonics, UK THALES Communications (TCFR), France Universität Gesamthochschule Paderborn, Germany University of Hagen, Germany Xilinx, USA

HOLMS High-Speed Optoelectronic Memory Systems To develop optoelectronic packaging technology that allows a seamless integration of complex, parallel optoelectronic interconnection with conventional high performance electronic systems. To construct a demonstrator to prove that the above technology can dramatically increase the performance of real life information systems. The key problem of today’s computer architectures will be addressed: memory latency.

Technical Approach The project aims to integrate: Planar Free Space Optics Opto-Electronic MCM Opto-Electronic PCB

Aims and Advantages The project aims to develop an opto-mechanical interface between OE-MCM components and the waveguides integrated in an OE-PCB system. The three types of communication do not require different drivers and I/O devices. Regardless of the type of communication, latency and bandwidth can become virtually identical. The integration of OE-MCM, OE-PCB and fiber is a key enabling technology for the replacement of high latency multistage networks with low latency direct optical interconnections in information systems.

Memory Architecture A Mephisto (ARM) processor is connected both optically and electronically. Custom memory controllers manage multiple RAM chips in what are known as memory banks. Memory banks are logically grouped. The architecture has a low memory latency. Multicast support makes this system well suited to multiprocessor applications. The proposed example application is a real-time JPEG 2000 decoder. Optoelectronics enables the construction of this innovative memory architecture.

Memory Architecture Optoelectronics enables the construction of this innovative memory architecture. A processor is connected both optically and electronically. Custom memory controllers manage multiple RAM chips in what are known as memory banks. Memory banks are logically grouped. The architecture has a low memory latency. Multicast support makes this system well suited to multiprocessor applications. The proposed example application is a real-time JPEG 2000 decoder A sample application is include real-time satellite image decoding.

Memory Architecture

Architectural Overview

System Segmentation

PCB Segmentation

PIFSO Interface

PIFSO and Fibre Interface

Assembly (PCB-MCM-OE)

Assembly (PIFSO-MCM-PCB)

Assembly – Optical Path