INTERCONNECTION NETWORKS

Slides:



Advertisements
Similar presentations
Computer Architecture and Organization
Advertisements

Chapter 7: System Buses Dr Mohamed Menacer Taibah University
Chapter Three: Interconnection Structure
Digital Computer Fundamentals
Computer Organization, Bus Structure
Chapter Thirteen Multiprocessors.
1/1/ / faculty of Electrical Engineering eindhoven university of technology Processor support devices Part 1:Interrupts and shared memory dr.ir. A.C. Verschueren.
Chapter 10 Switching Fabrics. Outline Physical Interconnection Physical box with backplane Individual blades plug into backplane slots Each blade contains.
TECH CH03 System Buses Computer Components Computer Function
CSCI 8150 Advanced Computer Architecture Hwang, Chapter 7 Multiprocessors and Multicomputers 7.1 Multiprocessor System Interconnects.
CSE 140 Lecture 15 System Designs Professor CK Cheng CSE Dept. UC San Diego 1.
2. Methods for I/O Operations
Lecture 12 Today’s topics –CPU basics Registers ALU Control Unit –The bus –Clocks –Input/output subsystem 1.
CS-334: Computer Architecture
THE COMPUTER SYSTEM. Lecture Objectives Computer functions – Instruction fetch & execute – Interrupt Handling – I/O functions Interconnections Computer.
ATM SWITCHING. SWITCHING A Switch is a network element that transfer packet from Input port to output port. A Switch is a network element that transfer.
Interconnection networks Characteristic of multiprocessor system – ability of each processor to share a set of main memory modules and I/O devices. This.
CHAPTER 3 TOP LEVEL VIEW OF COMPUTER FUNCTION AND INTERCONNECTION
Top Level View of Computer Function and Interconnection.
CSCI 232© 2005 JW Ryder1 Parallel Processing Large class of techniques used to provide simultaneous data processing tasks Purpose: Increase computational.
Bus Mr. Mukul Varshney. Bus A bus, in computing, is a set of physical connections (cables, printed circuits, etc.) which can be shared by multiple hardware.
COMPUTER ORGANIZATIONS CSNB123. COMPUTER ORGANIZATIONS CSNB123 Expected Course Outcome #Course OutcomeCoverage 1Explain the concepts that underlie modern.
Computer Architecture Lecture 2 System Buses. Program Concept Hardwired systems are inflexible General purpose hardware can do different tasks, given.
EEE440 Computer Architecture
Computer System Architecture Dept. of Info. Of Computer. Chap. 13 Multiprocessors 13-1 Chap. 13 Multiprocessors n 13-1 Characteristics of Multiprocessors.
ECEG-3202 Computer Architecture and Organization Chapter 3 Top Level View of Computer Function and Interconnection.
L/O/G/O Input Output Chapter 4 CS.216 Computer Architecture and Organization.
Lec 6 Chap. 13Multiprocessors
Dr Mohamed Menacer College of Computer Science and Engineering, Taibah University CE-321: Computer.
Chapter 3 System Buses.  Hardwired systems are inflexible  General purpose hardware can do different tasks, given correct control signals  Instead.
1 Device Controller I/O units typically consist of A mechanical component: the device itself An electronic component: the device controller or adapter.
Computer Architecture. Top level of Computer A top level of computer consists of CPU, memory, an I/O components, with one or more modules of each type.
Interconnection Structures
Chapter 6 Input/Output Organization
Interconnection structures
Overview Parallel Processing Pipelining
CSE 140 Lecture 14 System Designs
CSE 140 Lecture 14 System Designs
Dynamic connection system
Operating Systems (CS 340 D)
Refer example 2.4on page 64 ACA(Kai Hwang) And refer another ppt attached for static scheduling example.
CHAPTER 4 TOP LEVEL VIEW OF COMPUTER FUNCTION AND INTERCONNECTION
Overview Parallel Processing Pipelining
Overview Parallel Processing Pipelining
Chapter 3 Top Level View of Computer Function and Interconnection
COMP2121: Microprocessors and Interfacing
Switching A Network Layer Function
CSE 140 Lecture 15 System Designs
Multiprocessor Introduction and Characteristics of Multiprocessor
Computer System Overview
ECEG-3202 Computer Architecture and Organization
Overview of Computer Architecture and Organization
CS 140 Lecture 16 Professor CK Cheng 11/21/02.
Chap. 9 Pipeline and Vector Processing
AN INTRODUCTION ON PARALLEL PROCESSING
High Performance Computing & Bioinformatics Part 2 Dr. Imad Mahgoub
A Top-Level View Of Computer Function And Interconnection
William Stallings Computer Organization and Architecture 7th Edition
CSE 140 Lecture 16 System Designs
William Stallings Computer Organization and Architecture
Multiprocessors and Multi-computers
Presentation transcript:

INTERCONNECTION NETWORKS Prof. Varsha Poddar Department of CSE

Requirement of interconnection structures Connection of CPUs , IOPs to input-output devices and memory modules. Connection between components having distinct physical configurations. Several different forms of interconnects.

Few examples of interconnections Time-shared common bus Multiport memory Crossbar switch Multistage switching network Hypercube system

Time-Shared Common Bus

Time-Shared Common Bus(Contd.) Multiple number of processors connected through a common path to a memory unit. Only one processor can communicate with memory or with any other processor at a given time slot. A processor wishing to initiate a transfer, first needs to determine whether the transfer bus is free or not. Else it has to wait.

Time-Shared Common Bus(Contd.) The processor issues a command to inform the destination unit, what task is to be performed. The receiver recognizes the address in the bus and responds to the control signal from sender, after which the transfer is initiated. Problem – 1. Transfer conflicts. Solution – Bus controller that introduces priorities among the requesting units.

Problem – 2. restricted to only one transfer at a time (overall transfer rate is reduced) Solution – Local buses are introduced for internal system transfer & communication.

Multiport Memory System Employs separate bus system between each memory module and each processor.

Multiport Memory System(Contd.) Each processor bus- Is connected to each memory module. Has address, data and control lines for communication with memory module. Each memory module has 4 ports – each accommodates one processor bus.

Multiport Memory System(Contd.) Memory access conflicts resolved by assigning priorities fixed to each memory port. Priority is assigned with physical positioning of each processor , e.g. CPU1 > CPU2 > CPU3 > CPU4

Multiport Memory System(Contd.) Advantage: 1. High transfer rate as multiple path between processors & memory modules. Disadvantage: 1. Expensive memory control logic. 2. Large number of cables & connectors.

Crossbar Switch A number of cross-points that are placed at the intersection of processor bus and memory module paths.

Crossbar Switch(Contd.) Each cross-point has a switch that determines the path from a processor to a memory module. Each switch has a control logic to set up a transfer path between a processor and a memory. Examines the address placed in the bus to determine its perticular memory being addressed.

Crossbar Switch(Contd.) Resolves multiple requests for access to the same memory module – on a predetermined priority basis.

Crossbar Switch(Contd.) Working principle : Cross-point switch = multiplexer + arbitration logic Arbitration logic => priority encoder Each processor generates REQ to arbitration module, the P.E. selects the processor with highest priority. Arbitration module returns ACK signal to selected processor. Processor initiates memory operation(REQ) after receiving ACK. MUX is used to select one processor out of multiple processors, based on select combination generated by arbitration module.

Detailed version of a crossbar switch

Crossbar Switch(Contd.) Advantage: Simultaneous transfer from all memory modules as there is separate path associated with each module. Disadvantage: The hardware required to implement one switch becomes quite large & complicated.

THANK YOU