2 CS Architecture

Computer System
Architecture & Environments

Computer System Architecture
Dual-Core Design with different
Processor chips
 Multi-chip and multicore
 Systems containing all chips
• containing multiple separate systems
Dual-Core Design with single Processor
chip
 Multi-chip and multicore
 Systems containing all chips
Computer-System Architecture
 Most systems use a single general-purpose processor

• Most systems have special-purpose processors as well
 Multiprocessors systems growing in use and importance
• Also known as parallel systems, tightly-coupled systems
• Advantages include:
1. Increased throughput
2. Economy of scale
3. Increased reliability – graceful degradation or fault tolerance
• Two types:
1. Asymmetric Multiprocessing – each processor is assigned
a special task.
2. Symmetric Multiprocessing – each processor performs all
tasks
Symmetric & Asymmetric
Multiprocessing Architecture
 When a computer or device uses more than one CPU or Processor

it is called a Multi-Processing. Multi-processors are classified into
the following two types based on their nature of work.
1. Asymmetric
2. Symmetric
 SMP (symmetric multiprocessing) is computer processing done by

multiple processors that share a common operating system (OS)
and memory.
 In symmetric multiprocessing, the processors share the same
input/output (I/O) bus or data path.
 A single copy of the OS is in charge of all the processors.
 In asymmetric multiprocessing, only a master processor runs the

tasks of the operating system.
 For example, AMP can be used in assigning specific tasks to
the CPU based on the priority and the importance of task
completion
Symmetric vs Asymmetric multiprocessing
 The difference between symmetric and asymmetric multiprocessing is that:
• in symmetric multiprocessing the CPUs are identical and they share the
main memory
• while in asymmetric multiprocessing, the CPUs are not identical and they
follow slave, master relationship
Memory Access System
1. Uniform Memory Access

2. Non - Uniform Memory Access
 Processors of Bus-based multiprocessors that experience the same –

uniform – access time to any memory module in the system are often
referred to as Uniform Memory Access (UMA) systems
 Non-uniform memory access (NUMA) is a kind of memory architecture that

allows a processor faster access to contents of memory than other
traditional techniques.
Uniform Memory Access System
Non-Uniform Memory Access System
PC Motherboard
Distributed Systems
 Collection of separate, possibly heterogeneous, systems networked
together
• Network is a communications path, TCP/IP most common
 Local Area Network (LAN)
 Wide Area Network (WAN)
 Metropolitan Area Network (MAN)
 Personal Area Network (PAN)
 Network Operating System provides features between systems
across network
• Communication scheme allows systems to exchange messages
• Illusion of a single system
Computer System Environments
Computing Environments
 Traditional
 Mobile
 Client Server
 Peer-to-Peer
 Cloud computing
 Real-time Embedded
Traditional
 Stand-alone general-purpose machines

 But blurred as most systems interconnect with others (i.e.,
the Internet)
 Portals provide web access to internal systems
 Network computers (thin clients) are like Web terminals
 Mobile computers interconnect via wireless networks
 Networking becoming universal – even home systems use
firewalls to protect home computers from Internet attacks
Mobile
 Handheld smartphones, tablets, etc.

 What is the functional difference between them and a
“traditional” laptop?
 Extra feature – more OS features (GPS)
 Allows new types of apps like augmented reality
 Use IEEE 802.11 wireless, or cellular data networks for
connectivity
 Leaders are Apple iOS and Google Android
Client Server
 Client-Server Computing
• Dumb terminals supplanted by smart PCs
• Many systems now servers, responding to requests generated by
clients
 Compute-server system provides an interface to client to
request services (i.e., database)
 File-server system provides interface for clients to store and
retrieve files
Peer-to-Peer
 Another model of distributed system
 P2P does not distinguish clients and servers
• Instead all nodes are considered peers
• May each act as client, server or both
• Node must join P2P network
 Registers its service with central
lookup service on network, or
• Examples include Voice over IP (VoIP)
such as Skype
Cloud Computing
 Delivers computing, storage, even apps as a service
across a network
 Logical extension of virtualization because it uses
virtualization as the base for it functionality.
• Amazon EC2 has thousands of servers, millions of
virtual machines, petabytes of storage available
across the Internet, pay based on usage
Cloud Computing (Cont.)
 Many types
• Public cloud – available via Internet to anyone willing to pay
• Private cloud – run by a company for the company’s own use
• Hybrid cloud – includes both public and private cloud components
• Software as a Service (SaaS) – one or more applications available

via the Internet (i.e., word processor, google doc)
• Platform as a Service (PaaS) – software stack ready for
application use via the Internet (i.e., online compiler, a database
server)
• Infrastructure as a Service (IaaS) – servers or storage available
over Internet (i.e., storage available for backup use)
Cloud Computing (cont.)
 Cloud computing environments composed of traditional Operating
Systems, plus Virtual Machines, plus cloud management tools
• Internet connectivity requires security like firewalls
• Load balancers spread traffic across multiple applications
Real-Time Embedded Systems
 A real-time embedded system is a particular version of an

embedded system that works on the basis of real-time computing
represented by a dedicated type of operating system
 Some of the real-time embedded systems examples are: Sound

System of a computer (Soft real-time system) Aircraft control system
(Hard real-time system)
 Real-time embedded systems most established form of computers

• Vary considerable, special purpose, limited purpose OS, real-
time OS

2 CS Architecture

Uploaded by

Copyright:

Available Formats

2 CS Architecture

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

2 CS Architecture

Uploaded by

Copyright:

Available Formats

Computer System

Architecture & Environments

 Most systems use a single general-purpose processor

 When a computer or device uses more than one CPU or Processor

 SMP (symmetric multiprocessing) is computer processing done by

 In asymmetric multiprocessing, only a master processor runs the

1. Uniform Memory Access

 Processors of Bus-based multiprocessors that experience the same –

 Non-uniform memory access (NUMA) is a kind of memory architecture that

 Stand-alone general-purpose machines

 Handheld smartphones, tablets, etc.

• Software as a Service (SaaS) – one or more applications available

 A real-time embedded system is a particular version of an

 Some of the real-time embedded systems examples are: Sound

 Real-time embedded systems most established form of computers

You might also like