1 / 100

KT 4054

KT 4054. Computer Systems Organization and Architecture. Topic 1: Design Method. DR. NASHARUDDIN ZAINAL. What is a system?. What do the following systems have in common? __________ system Solar system Home __________ system __________ control system. Plumbing System. Solar System.

denise
Download Presentation

KT 4054

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. KT 4054 Computer Systems Organization and Architecture Topic 1: Design Method DR. NASHARUDDIN ZAINAL

  2. What is a system? • What do the following systems have in common? • __________ system • Solar system • Home __________ system • __________ control system

  3. Plumbing System

  4. Solar System

  5. Home Network System

  6. Inventory Control System

  7. Definition of a System • “A systems is a collection of __________ linked together and __________ in such a way as to be __________ as a single unit.” • Linked components of a system also define the __________ for the system • The __________ is anything outside of the system

  8. General Representation of a System

  9. System Decomposition • Components • May be __________ or • May be __________ • Decomposition • The division of a system into its __________ and __________ • __________

  10. System Architecture “The fundamental properties, and the patterns of relationships, connections, constraints, and linkages among the __________ and between the __________ and its __________ are known collectively as the architecture of the system”

  11. Abstractions of Systems • How are the following two __________ of a business system different from one another? • How are these __________ different from the real business system?

  12. Business Organization Chart

  13. Business Application Architecture

  14. IT System Architectures • __________ processing systems • Client-Server Computing • 2-tier architecture • 3-tier architecture • N-tier architecture • Web-Based Computing • __________Computing

  15. Client-Server Computing • A program on a __________ computer requests services from a program on a __________ computer • Examples: • Email services, file services, print services, directory services, Web services, database services, application services, remote access services

  16. Basic Client-Server Architecture

  17. Advantages of Client-Server Architecture • __________ of services permits • easier administration of services by IT professionals • easier availability and location by users • consistency of resources, such as files and data, can be managed and assured • more efficient and cost-effective hardware procurement through purchasing a small number of very powerful computers

  18. Clients and Servers on a Network

  19. Basic Personal Computer System

  20. Mainframe Computer System

  21. Major PC System Components

  22. Typical Desktop PC

  23. Basic CPU-Memory-I/O Pathway*

  24. Bus • Connect CPU and __________ • _______________: on same bus as CPU/memory or separate bus • Physical packaging commonly called __________ • Also called system bus or external bus • Example of a broadcast bus

  25. Modern Personal Computer General Bus Interface Configuration

  26. Motherboard • Printed circuit board that holds CPU and related components including backplane

  27. Bus Hierarchy • __________ bus: on-chip • __________ bus (backside bus) • __________ bus (front-side bus) • connects the memory subsystem and processor • __________ bus • Connects I/O to the CPU and memory • Connects all peripheral cards and connectors • Examples: PCI-Express, PCI

  28. PCI Bus Connections

  29. I/O Bus Architecture • Consists of an I/O device, I/O device __________, system bus, and a device __________ • Device driver • __________ that controls the I/O devices • Common interface buses • USB – Universal Serial Bus • SCSI – Small Computer System Interface • SATA – Serial Advanced Technology Attachment • IEEE 1394 - Firewire

  30. Root Hub Hub Hub USB • Multipoint bus • __________ provide multiple connection points for I/O devices • Supports up to __________ devices • USB-2 data transfer rate up to 480 Mbits per second Topology Example Hub

  31. SCSI Bus • ANSI standard but multiple variations • Really an I/O bus rather than simple interface • Supports multiple devices from a single SCSI port

  32. USB and FireWire (IEEE 1394) • Both __________, multipoint bus specifications • _______________ devices w/o powering down • Packet protocol for isochronous data transfer • Isochronous: delivery at regular time intervals • Guarantee specified throughput

  33. USB vs. FireWire • __________: high-speed data transfer • 480Mbits/sec • __________: proposed standard • Data transfer up to 4.8 Gbits per second • __________: high-speed data transfer, i.e., full motion video with sound • 400 Mbits/sec to 3.2 Gbits/sec

  34. Typical FireWire Configuration • Network-like characteristics • Device controllers independent

  35. Channel Architecture • Used in ______________________________ • Channel subsystem • Separate I/O processor that serves as a CPU for I/O operations • Channel control words • Programs that transfer data between memory and an I/O device using DMA • Subchannels • Connected to a control unit module through one or more channel paths • Similar role to a device controller

  36. I/O Channel Architecture

  37. Clusters • ____________________ systems • Loosely-coupled computers • Each system has its own CPU, memory, and I/O facilities • Each system is known as a __________ of the cluster • Two ways to configure • Shared-nothing model • Shared-disk model

  38. Advantages of Clusters • Increased computing power by __________ the power of individual computer systems • Inherently scalable • Cheaper than using a single large computer • Used for high performance computing systems • ____________________ • Failure in one node does not bring down the entire system • Failover - processing by failed node is switched to other nodes • ____________________ • ____________________ • can be attained either through software and/or through geographically distributed location of nodes

  39. Shared-Nothing Model • High speed __________ between nodes • No sharing of __________ • Partitioning of work through division of data • Advantage • Reduced __________ between nodes • Disadvantage • Can result in inefficient division of __________

  40. Shared-Disk Model • High speed link between __________ • Disk __________ are shared between nodes • Advantage • Better load balancing • Disadvantage • Complex software required for transactional processing (lock, commit phases)

  41. Cluster Models

  42. Beowulf Clusters • Simple and highly __________ • Low cost • Networked • Computers connected to one another by a private __________ network • Connection to an external network is through a single gateway computer • Configuration • COTS – Commodity-off-the-shelf components such as inexpensive computers • Blade components – computers mounted on a __________ that are plugged into connectors on a rack • Either shared-disk or shared-nothing model

  43. Blade and Rack of Beowulf Cluster

  44. High Performance Computing • Also called ____________________ • Clusters of power machines or larger Beowulf blade clusters • Well suited for problems that can be broken into subtasks • __________ computing • Supercomputer performance through distributing CPU processing to the spare CPU cycles of personal computers connected to a network

  45. Four Levels of ComputerDescription • Global system structure • Overall system structure is defined • Major components identified • Processors (Pemproses) • Control modules (Modul kawalan) • Memory modules (Modul ingatan) • Interconnection structure (Struktur saling hubungan) • Mostly a static description -- “black box” approach • __________ level (Paras __________) • Architectural features specified • Interfaces (Antaramuka) • Instruction sets (Set arahan) • Data Representation (Perwakilan data) • More detailed individual component specification

  46. Cont. • __________ level (Paras __________) • Specify internal operation of processor-level components at the word level • Primitives: • Registers (Daftar) • Counters (Pembilang) • Memories (Ingatan) • ALUs • Clocks (Jam) • Combinational logic (Gabungan lojik) • __________ level (Paras __________) • Specify operations at the individual bit level • Gates are primitive elements • Very complex to do manually (logic minimization, etc.)

  47. Global Descriptive Tools • ____________________ • The most universally accepted method of classifying computer systems • Relies on a __________ __________ approach • Published in the Proceedings of the IEEE in 1966 • Any computer can be placed in one of 4 broad categories • SISD: Single instruction stream, single data stream • SIMD: Single instruction stream, multiple data streams • MIMD: Multiple instruction streams, multiple data streams • MISD: Multiple instruction streams, single data stream

  48. Cont. • Advantages of Flynn • Universally accepted • Compact Notation • Easy to classify a system • Disadvantages of Flynn • Very coarse-grain differentiation among machine systems • Comparison of different systems is limited • Interconnections, I/O, memory not considered in the scheme • Other global level tools • Tendency to rely on block diagrams and very coarse performance measures • Processor-memory-switch notation uses block diagrams with 7 basic component types

  49. SISD

  50. SIMD system architecture of [Fly66] SIMD

More Related