University of Surrey - Guildford
Registry
  
 

  
 
Registry > Module Catalogue
View Module List by A.O.U. and Level  Alphabetical Module Code List  Alphabetical Module Title List  Alphabetical Old Short Name List  View Menu 
2010/1 Module Catalogue
 Module Code: EEE3004 Module Title: COMPUTER ARCHITECTURES
Module Provider: Electronic Engineering Short Name: EE3.CMA
Level: HE3 Module Co-ordinator: WEBB RP Prof (Elec Eng)
Number of credits: 15 Number of ECTS credits: 7.5
 
Module Availability

Autumn Semester

Assessment Pattern

Unit(s) of Assessment
Weighting Towards Module Mark( %)
Examination: Written
100%

Module Overview
Prerequisites/Co-requisites

None

Module Aims

To provide knowledge about the use of parallelism in computer architectures at various levels in the architectural design.

Learning Outcomes

This course is designed to enable graduating students to be able: (a) to select architectures suitable for a wide range of computing tasks; (b) to track future advances in uni-processor and multiprocessor architectures, operating systems and applications.

Module Content

A:   UNIPROCESSOR ARCHITECTURES

[1-5]         Real Memory topics
                 Static and dynamic memory devices – timing and functionality.
                 Dual–port static memories.
                 Multiplexing of address and data buses, timing considerations, control lines, etc.
                 Memory block mapping and interleaving.
.
[6-10]       Virtual Memory
                 General principles of paging, segmentation and mixed pages & segmented schemes.
                 Hardware support – write through, associative memory, cache, etc.
                 Software Support – page–table maintenance, paging process, etc.
                 Translation look–aside buffers.
                 Microprocessor implementations of virtual memory
[11-16]     Memory Caches
Direct–mapped, set associative and fully–associative caches.
Cache performance-the effects of different cache memory sizes, individual line sizes, bus width and bit rates. 
Cache consistency in a multi-master environment.
[17-25]     Instruction Sets and pipelining
                 General requirements of an instruction set.
                 Comparison of instruction formats on common processors (from 1st-generation microprocessors through to RISC machines).
                 RISC vs CISC architectures.
                 Pipelined processing of instruction streams.
                 The effect of branch instructions.
                 Data hazards and avoidance techniques.
                 Effects of instruction re-ordering and loop unrolling.
                 Introduction to “Very Long Instruction Word” (VLIW) architectures.
B:   PARALLEL ARCHITECTURES
 
[26-30]     Fundamentals
                 Classifications of parallelism; load balancing; Algorithmic, Geometric and Processor Farming techniques.
                 Flynn's classification.
                 Point-to-point interconnection topologies; inter-processor routing schemes.
                Amdahl's Law;  
                 Deadlock, and how to avoid it.
                 Limits to Uniprocessor Performance.
 
[31-36]     Specific Examples
                 Vector Processors; memory interleaving; vector stride
                 Very Long Instruction Word (VLIW) architectures.
                 Beowulf Clusters
                 Active Memory architectures: AMT DAP;   Thinking Machines CM-1, CM-2.
                 Virtual Shared Memory architectures: CM-5; Cray T3D; Kendall Square KSR-1.

                 Quantum Information/Computing

 

Methods of Teaching/Learning

Lectures

Selected Texts/Journals

Behrooz, Parhami
Computer Architecture
 
 Oxford University Press
£28.00
B
Wilkinson, B.
Computer Architecture- Design and Performance 2nd edition
0-13-518200-X  
Prentice-Hall
£21.99
B

Last Updated

12 August 2010