Computer Architecture and Organization • The key is to recognize the hierarchical nature of

History and Overview of Computer Architecture most complex systems, including the computer. A
ORGANIZATION AND STRUCTURE hierarchical system is a set of interrelated
• Computer architecture refers to those attributes of subsystems, each of the latter, in turn, hierarchical in
a system visible to a programmer or, put another structure until we reach some lowest level of
way, those attributes that have a direct impact on the elementary subsystem.
logical execution of a program. A term that is often • The hierarchical nature of complex systems is
used interchangeably with computer architecture is essential to both their design and their description.
Instruction Set Architecture (ISA).
• ISA defines instruction formats, instruction
opcodes, registers, instruction and data • In terms of description, we have two choices:
memory; the effect of executed instructions • starting at the bottom and building up to a
on the registers and memory; and an complete description, or
algorithm for controlling instruction • beginning with a top view and decomposing
execution. the system into its subparts.

• Computer organization refers to the operational • Which is more effective?

units and their interconnections that realize the
architectural specifications. • Evidence from a number of fields suggests that the
• Examples of architectural attributes include: top- down approach is the clearest and most
• the instruction set, effective.
• the number of bits used to represent
various data types (e.g., numbers, • The computer system will be described from the top
characters), down. We begin with the major components of a
• I/O mechanisms, and techniques for computer, describing their structure and function,
addressing memory. and proceed to successively lower layers of the
• Organizational attributes include those hierarchy.
hardware details transparent to the Function:
programmer, such as: The operation of each individual component as part of
• control signals; the structure
• interfaces between the computer and Four basic functions that a computer can perform:
peripherals; and ∙ Data processing: Data may take a wide variety of
• the memory technology used. forms, and the range of processing requirements is
IMPORTANCE: broad. However, we shall see that there are only a
Difference between architecture and organization few fundamental methods or types of data
• Many computer manufacturers offer a family of processing.
computer models, all with the same architecture but ∙ Data storage: Even if the computer is processing
with differences in organization. data on the fly (i.e., data come in and get
• The different models in the family have different processed, and the results go out immediately), the
price and performance characteristics. computer must temporarily store at least those
• A particular architecture may span many years and pieces of data that are being worked on at any
encompass a number of different computer models, given moment. Thus, there is at least a short-
its organization changing with changing technology. term data storage function. Equally important, the
• A prominent example of both these computer performs a long- term data storage
phenomena is the IBM System/370 function. Files of data are stored on the computer
architecture. This architecture was first for subsequent retrieval and update.
introduced in 1970 and included a number ∙ Data movement: The computer’s operating
of models. environment consists of devices that serve as
• The customer with modest requirements could buy a either sources or destinations of data. When data
cheaper, slower model and, if demand increased, are received from or delivered to a device that is
later upgrade to a more expensive, faster model directly connected to the computer, the process is
without having to abandon software that had already known as input– output (I/O), and the device is
been developed. referred to as a peripheral. When data are moved
• Over the years, IBM has introduced many new over longer distances, to or from a remote device,
models with improved technology to replace older the process is known as data communications.
models, offering the customer greater speed, lower ∙ Control: Within the computer, a control unit
cost, or both. These newer models retained the same manages the computer’s resources and
architecture so that the customer’s software orchestrates the performance of its functional parts
investment was protected. Remarkably, the in response to instructions.
System/370 architecture, with a few enhancements,
has survived to this day as the architecture of IBM’s
mainframe product line. There is remarkably little shaping of computer structure
• In a class of computers called microcomputers, the to fit the function to be performed. At the root of this
relationship between architecture and organization is lies the general- purpose nature of computers, in
very close. Changes in technology not only which all the functional specialization occurs at the time
influence organization but also result in the of programming and not at the time of design.
introduction of more powerful and more complex Structure:
architectures. The way in which the components are interrelated.
• We now look in a general way at the internal
STRUCTURE AND FUNCTION structure of a computer. We begin with a traditional
• A computer is a complex system; contemporary computer with a single processor that employs a
computers contain millions of elementary electronic microprogrammed control unit, then examine a
components. typical multicore structure.
• Simple single- processor computer - Figure 1.1 • A greater performance improvement may be
provides a hierarchical view of the internal structure obtained by using multiple levels of cache,
of a traditional single- processor computer. with level 1 (L1) closest to the core and
additional levels (L2, L3, and so on)
progressively farther from the core.
• Four main structural components: Figure 1.2.
• Central processing unit (CPU): Controls the Simplified View of Major Elements of a Multicore
operation of the computer and performs its data Computer
processing functions; often simply referred to as • Figure 1.2 is a simplified view of the principal
processor. components of a typical multicore computer. Most
• Main memory: Stores data. computers, including embedded computers in
• I/O: Moves data between the computer and its smartphones and tablets, plus personal computers,
external environment. laptops, and workstations, are housed on a
• System interconnection: Some mechanism that motherboard.
provides for communication among CPU, main • A printed circuit board (PCB) is a rigid, flat
memory, and I/O. A common example of system board that holds and interconnects chips and
interconnection is by means of a System bus, other electronic components. The board is
consisting of a number of conducting wires to which made of layers, typically two to ten, that
all the other components attach. interconnect components via copper
pathways that are etched into the board. The
• CPU’s Major structural components are as follows: main printed circuit board in a computer is
• Control unit: Controls the operation of the called a system board or motherboard, while
CPU and hence the computer. smaller ones that plug into the slots in the
• Arithmetic and logic unit (ALU): Performs main board are called expansion boards.
the computer’s data processing functions. • The most prominent elements on the
• Registers: Provides storage internal to the motherboard are the chips. A chip is a single
CPU. piece of semiconducting material, typically
• CPU interconnection: Some mechanism silicon, upon which electronic circuits and
that provides for communication among the logic gates are fabricated. The resulting
control unit, ALU, and registers. product is referred to as an integrated circuit.
• The motherboard contains a slot or socket for the
• It covers these components, where we will see that processor chip, which typically contains multiple
complexity is added by the use of parallel and individual cores, in what is known as a multicore
pipelined organizational techniques. processor. There are also slots for memory chips,
• there are several approaches to the implementation I/O controller chips, and other key computer
of the control unit; one common approach is a components. For desktop computers, expansion slots
microprogrammed implementation. enable the inclusion of more components on
• A microprogrammed control unit operates by expansion boards.
executing microinstructions that define the • Thus, a modern motherboard connects only a few
functionality of the control unit. individual chip components, with each chip
containing from a few thousand up to hundreds of
• Multicore computer structure, contemporary millions of transistors.
computers generally have multiple processors. When
these processors all reside on a single chip, the term
multicore computer is used, and each processing
unit (consisting of a control unit, ALU, registers, • A processor chip contains eight cores and an L3
and perhaps cache) is called a core. cache. Not shown is the logic required to control
operations between the cores and the cache and
• Central processing unit (CPU): That portion of a between the cores and the external circuitry on the
computer that fetches and executes instructions. It motherboard. The figure indicates that the L3 cache
consists of an ALU, a control unit, and registers. In a occupies two distinct portions of the chip surface.
system with a single processing unit, it is often However, typically, all cores have access to the
simply referred to as a processor. entire L3 cache via the aforementioned control
• Core: An individual processing unit on a processor circuits. The processor chip shown in Figure 1.2
chip. A core may be equivalent in functionality to a does not represent any specific product, but provides
CPU on a single- CPU system. Other specialized a general idea of how such chips are laid out.
processing units, such as one optimized for vector
and matrix operations, are also referred to as cores.
• Processor: A physical piece of silicon containing • A single core, which occupies a portion of the
one or more cores. The processor is the computer processor chip. In general terms, the functional
component that interprets and executes instructions. elements of a core are:
If a processor contains multiple cores, it is referred • Instruction logic: This includes the tasks involved
to as a multicore processor. in fetching instructions, and decoding each
instruction to determine the instruction operation
• Another prominent feature of contemporary and the memory locations of any operands.
computers is the use of multiple layers of memory, • Arithmetic and logic unit (ALU): Performs the
called cache memory, between the processor and operation specified by an instruction.
main memory. • Load/store logic: Manages the transfer of data to
• A cache memory is smaller and faster than and from main memory via cache.
main memory and is used to speed up • The core also contains an L1 cache, split between an
memory access, by placing in the cache data instruction cache ( I- cache) that is used for the
from main memory, that is likely to be used transfer of instructions to and from main memory,
in the near future. and an L1 data cache, for the transfer of operands
 and results. Typically, today’s processor chips also integrated circuit that defines the third generation of
include an L2 cache as part of the core. In many computers.
cases, this cache is also split between instruction and • Microelectronics means, literally, “small
data caches, although a combined, single L2 cache is electronics.” Since the beginnings of digital
also used. electronics and the computer industry, there has
been a persistent and consistent trend toward the
BRIEF HISTORY OF COMPUTERS reduction in size of digital electronic circuits.
The First Generation: Vacuum Tubes • The basic elements of a digital computer, as we
know, must perform data storage, movement,
• The first generation of computers used vacuum tubes processing, and control functions. Only two
for digital logic elements and memory. A number of fundamental types of components are required gates
research and then commercial computers were built and memory cells.
using vacuum tubes. For our purposes, it will be • A gate is a device that implements a simple
instructive to examine perhaps the most famous Boolean or logical function.
first- generation computer, known as the IAS • Memory cell is a device that can store 1 bit
computer. of data; that is, the device can be in one of
• A fundamental design approach first implemented in two stable states at any time.
the IAS computer is known as the stored- program By interconnecting large numbers of these fundamental
concept. This idea is usually attributed to the devices, we can construct a computer. We can relate this
mathematician John von Neumann. Alan Turing to our four basic functions as follows:
developed the idea at about the same time. The first Data storage: Provided by memory cells.
publication of the idea was in a 1945 proposal by Data processing: Provided by gates.
von Neumann for a new computer, the EDVAC Data movement: The paths among components are
(Electronic Discrete Variable Computer). used to move data from memory to memory and from
• In 1946, von Neumann and his colleagues began the memory through gates to memory.
design of a new stored- program computer, referred Control: The paths among components can carry
to as the IAS computer, at the Princeton Institute for control signals.
Advanced Studies. The IAS computer, although not
completed until 1952, is the prototype of all • Initially, only a few gates or memory cells could be
subsequent general- purpose computers. reliably manufactured and packaged together. These
The Second Generation: Transistors early integrated circuits are referred to as small-
• The first major change in the electronic computer scale integration (SSI). As time went on, it became
came with the replacement of the vacuum tube by possible to pack more and more components on the
the transistor. The transistor, which is smaller, same chip.
cheaper, and generates less heat than a vacuum tube,
can be used in the same way as a vacuum tube to • This figure reflects the famous Moore’s law, which
construct computers. Unlike the vacuum tube, which was propounded by Gordon Moore, cofounder of
requires wires, metal plates, a glass capsule, and a Intel, in 1965. Moore observed that the number of
vacuum, the transistor is a solid- state device, made transistors that could be put on a single chip was
from silicon. doubling every year, and correctly predicted that this
• The transistor was invented at Bell Labs in 1947 and pace would continue into the near future.
by the 1950s had launched an electronic revolution. • To the surprise of many, including Moore, the pace
It was not until the late 1950s, however, that fully continued year after year and decade after decade.
transistorized computers were commercially The pace slowed to a doubling every 18 months in
available. The use of the transistor defines the the 1970s but has sustained that rate ever since.
second generation of computers. It has become
widely accepted to classify computers into
generations based on the fundamental hardware • The consequences of Moore’s law are profound:
technology employed. Each new generation is • The cost of a chip has remained virtually
characterized by greater processing performance, unchanged during this period of rapid
larger memory capacity, and smaller size than the growth in density. This means that the cost
previous one. of computer logic and memory circuitry
has fallen at a dramatic rate.
Table 1.1. Computer Generations • Because logic and memory elements are
placed closer together on more densely
The Third Generation: Integrated Circuits packed chips, the electrical path length is
• A single, self- contained transistor is called a shortened, increasing operating speed.
discrete component. Throughout the 1950s and early • The computer becomes smaller, making it
1960s, electronic equipment was composed largely more convenient to place in a variety of
of discrete components— transistors, resistors, environments.
capacitors, and so on. Discrete components were • There is a reduction in power
manufactured separately, packaged in their own requirements.
containers, and soldered or wired together onto • The interconnections on the integrated
Masonite- like circuit boards, which were then circuit are much more reliable than solder
installed in computers, oscilloscopes, and other connections. With more circuitry on each
electronic equipment. The entire manufacturing chip, there are fewer interchip
process, from transistor to circuit board, was connections.
expensive and cumbersome. Later Generations
• Beyond the third generation there is less general
• In 1958 came the achievement that revolutionized agreement on defining generations of computers.
electronics and started the era of microelectronics: Table 1.1 suggests that there have been a number of
the invention of the integrated circuit. It is the later generations, based on advances in integrated
circuit technology. With the introduction of large-
 scale integration (LSI), more than 1,000 components • ■ Pentium 4: The Pentium 4 includes additional
can be placed on a single integrated circuit chip. floating-point and other enhancements for
Very- large- scale integration (VLSI) achieved multimedia.11
more than 10,000 components per chip, while • ■ Core: This is the first Intel x86 microprocessor
current ultra- large- scale integration (ULSI) chips with a dual core, referring to the implementation of
can contain more than one billion components. two cores on a single chip.
• ■ Core 2: The Core 2 extends the Core architecture
to 64 bits. The Core 2 Quad provides four cores on
a single chip. More recent Core offerings have up to
10 cores per chip. An important addition to the
• Semiconductor memory architecture was the Advanced Vector Extensions
• The first application of integrated circuit instruction set that provided a set of 256-bit, and
technology to computers was the then 512- bit, instructions for efficient processing of
construction of the processor (the control vector data.
unit and the arithmetic and logic unit) out of
integrated circuit chips. But it was also
found that this same technology could be • Almost 40 years after its introduction in 1978, the
used to construct memories. x86 architecture continues to dominate the processor
market outside of embedded systems. Although the
MICROPROCESSORS organization and technology of the x86 machines
have changed dramatically over the decades, the
Evolution of the Intel x86 Architecture instruction set architecture has evolved to remain
• It is worthwhile to list some of the highlights of the backward compatible with earlier versions. Thus,
evolution of the Intel product line: any program written on an older version of the x86
• ■ 8080: The world’s first general-purpose architecture
microprocessor. This was an 8-bit machine, with
an 8-bit data path to memory. The 8080 was used Embedded System
in the first personal computer, the Altair. • The term embedded system refers to the use of
• ■ 8086: A far more powerful, 16-bit machine. In electronics and software within a product, as
addition to a wider data path and larger registers, opposed to a general-purpose computer, such as a
the 8086 sported an instruction cache, or queue, laptop or desktop system. Millions of computers are
that prefetches a few instructions before they are sold every year, including laptops, personal
executed. A variant of this pro- cessor, the 8088, computers, workstations, servers, mainframes, and
was used in IBM’s first personal computer, securing supercomputers. In contrast, billions of computer
the suc- cess of Intel. The 8086 is the first systems are produced each year that are embedded
appearance of the x86 architecture. within larger devices.
• ■ 80286: This extension of the 8086 enabled
addressing a 16-MB memory instead of just 1 MB.
• ■ 80386: Intel’s first 32-bit machine, and a major • Types of devices with embedded systems are
overhaul of the product. With a 32-bit architecture, almost too numerous to list.
the 80386 rivaled the complexity and power of • Examples include cell phones, digital cameras,
minicom- puters and mainframes introduced just a video cameras, calculators, micro- wave ovens,
few years earlier. This was the first Intel processor home security systems, washing machines,
to support multitasking, meaning it could run lighting systems, thermostats, printers, various
multiple pro- grams at the same time. automotive systems (e.g., transmission control,
cruise control, fuel injection, anti-lock brakes, and
• ■ 80486: The 80486 introduced the use of much suspension systems), tennis rackets, toothbrushes,
more sophisticated and power-powerful technology and numerous types of sensors and actuators in
and sophisticated instruction pipelining. The 80486 automated systems.
also offered a built-in math coprocessor, offloading
complex math operations from the main CPU.
• ■ Pentium: With the Pentium, Intel introduced • Figure 1.14 shows in general terms an embedded
the use of superscalar tech- niques, which allow system organization. In addi- tion to the processor
multiple instructions to execute in parallel. and memory, there are a number of elements that
• ■ Pentium Pro: The Pentium Pro continued the differ from the typical desktop or laptop computer:
move into superscalar organiza- tion begun with the • ■ There may be a variety of interfaces that enable
Pentium, with aggressive use of register renaming, the system to measure, manip- ulate, and otherwise
branch prediction, data flow analysis, and interact with the external environment. Embedded
speculative execution. sys- tems often interact (sense, manipulate, and
• ■ Pentium II: The Pentium II incorporated Intel communicate) with external world through sensors
MMX technology, which is designed specifically to and actuators and hence are typically reactive
process video, audio, and graphics data efficiently. systems; a reactive system is in continual interaction
with the environment and executes at a pace
determine by that environment.
• ■ Pentium III: The Pentium III incorporates • ■ The human interface may be as simple as a
additional floating-point instruc- tions: The flashing light or as complicated as real-time robotic
Streaming SIMD Extensions (SSE) instruction set vision. In many cases, there is no human interface.
extension added • ■ The diagnostic port may be used for
• 70 new instructions designed to increase diagnosing the system that is being controlled—
performance when exactly the same operations are not just for diagnosing the computer.
to be performed on multiple data objects. Typical
applications are digital signal processing and • ■ Special-purpose field programmable (FPGA),
graphics processing. application-specific (ASIC), or even nondigital
 hardware may be used to increase performance or Embedded Operating Systems
reliability.
• ■ Software often has a fixed function and is • There are two general approaches to developing an
specific to the application. embedded operating system (OS). The first approach
• ■ Efficiency is of paramount importance for is to take an existing OS and adapt it for the
embedded systems. They are opti- mized for energy, embedded application. For example, there are
code size, execution time, weight and dimensions, embedded versions of Linux, Windows, and Mac, as
and cost. well as other commercial and proprietary operating
systems specialized for embedded systems. The
• There are several noteworthy areas of similarity to other approach is to design and implement an OS
general-purpose computer systems as well: intended solely for embedded use. An example of
• ■ Even with nominally fixed function software, the latter is TinyOS, widely used in wireless sensor
the ability to field upgrade to fix bugs, to improve networks.
security, and to add functionality, has become very Application Processors versus Dedicated Processors
important for embedded systems, and not just in • Application processors are defined by the
consumer devices. processor’s ability to execute complex operating
• ■ One comparatively recent development has been systems, such as Linux, Android, and Chrome. Thus,
of embedded system plat- forms that support a the application processor is general- purpose in
wide variety of apps. Good examples of this are nature.
smart- phones and audio/visual devices, such as • A good example of the use of an embedded
smart TVs. application processor is the smartphone. The
embedded system is designed to support numerous
apps and perform a wide variety of functions.
The Internet of Things
• Most embedded systems employ a dedicated
• It is worthwhile to separately callout one of the processor, which, as the name implies, is dedicated
major drivers in the proliferation of embedded to one or a small number of specific tasks required
systems. The Internet of things (IoT) is a term that by the host device. Because such an embedded
refers to the expanding interconnection of smart system is dedicated to a specific task or tasks, the
devices, ranging from appliances to tiny sensors. A processor and associated components can be
domi- nant theme is the embedding of short-range engineered to reduce size and cost.
mobile transceivers into a wide array of gadgets and Microprocessors versus Microcontrollers
everyday items, enabling new forms of As we have seen, early microprocessor chips included
communication between people and things, and registers, an ALU, and some sort of control unit or
between things themselves. The Internet now instruction processing logic. As transistor density
supports the intercon- nection of billions of increased, it became possible to increase the
industrial and personal objects, usually through complexity of the instruction set architecture, and
cloud systems. The objects deliver sensor ultimately to add memory and more than one
information, act on their environment, and, in some processor.
cases, modify themselves, to create overall A microcontroller chip makes a substantially different
management of a larger system, like a factory or use of the logic space available. Also called a “computer
city. on a chip,” billions of microcontroller units are
embedded each year in myriad products from toys to
With reference to the end systems supported, the Internet appliances to automobiles.
has gone through roughly four generations of Embedded versus Deeply Embedded Systems
deployment culminating in the IoT:
• We have, in this section, defined the concept of an
• 1. Information technology (IT): PCs, servers, embedded system. A subset of embedded systems,
routers, firewalls, and so on, bought as IT devices by and a quite numerous subset, is referred to as
enterprise IT people and primarily using wired deeply embedded systems.
connectivity. • A deeply embedded system:
• 2. Operational technology (OT): • uses a microcontroller rather than a microprocessor,
Machines/appliances with embedded IT built by is not programmable once the program logic for the
non-IT companies, such as medical machinery, device has been burned into ROM (read-only
SCADA (supervisory con- trol and data acquisition), memory), and has no interaction with a user.
process control, and kiosks, bought as appliances • are dedicated, single-purpose devices that detect
by enterprise OT people and primarily using wired something in the environment, perform a basic level
connectivity. of processing, and then do some- thing with the
• 3. Personal technology: Smartphones, tablets, and results.
eBook readers bought as IT devices by consumers • often have wireless capability and appear in
(employees) exclusively using wireless connectivity networked configurations, such as networks of
and often multiple forms of wireless connectivity. sensors deployed over a large area (e.g., factory,
• 4. Sensor/actuator technology: Single-purpose agricultural field).
devices bought by consumers, IT, and OT people
exclusively using wireless connectivity, generally of • The Internet of things depends heavily on deeply
a single form, as part of larger systems. embedded systems. Typically, deeply embedded
systems have extreme resource constraints in terms
of memory, processor size, time, and power
consumption.
• It is the fourth generation that is usually thought of
as the IoT, and it is marked by the use of billions of
embedded devices. Cloud Computing
• The general concepts for cloud computing go high-reliability networking between the
back to the 1950s, cloud computing services first provider and subscriber. In this case, some
became available in the early 2000s, particularly
targeted at large enterprises. Since then, cloud • Cloud storage consists of database storage and
computing has spread to small and medium size database applications hosted remotely on cloud
businesses, and most recently to consumers. servers.
Apple’s iCloud was launched in 2012 and had 20 • Cloud Services
million users within a week of launch. Evernote, the • The essential purpose of cloud computing is to
cloud-based notetaking and archiving service, provide for the convenient rental of computing
launched in 2008, approached 100 million users in resources. A cloud service provider (CSP) maintains
less than 6 years. In this section, we provide a brief computing and data storage resources that are
overview. Cloud computing is available over the Internet or private networks.
Customers can rent a portion of these resources as
• There is an increasingly prominent trend in many needed.
organizations to move a substantial portion or even Virtually all cloud service is provided using one of three
all information technology (IT) operations to an models: SaaS, PaaS, and IaaS
Internet-connected infrastructure known as
enterprise cloud computing. At the same time, • Software as a service (SaaS)
individual users of PCs and mobile devices are • SaaS cloud provides service to customers
relying more and more on cloud computing in the form of software, specifically
services to backup data, synch devices, and share, application software, running on and
using personal cloud computing. NIST defines cloud accessible in the cloud. SaaS follows the
computing, in NIST SP-800-145 (The NIST familiar model of Web services, in this
Definition of Cloud Computing), as follows: case applied to cloud resources.
• Cloud computing: A model for enabling • SaaS enables the customer to use the cloud
ubiquitous, convenient, on-demand network provider’s applications running on the
access to a shared pool of configurable provider’s cloud infrastructure. The
computing resources (e.g., networks, applications are accessible from various
servers, storage, applications, and services) client devices through a simple interface
that can be rapidly provisioned and such as a Web browser. Instead of
released with minimal management effort or obtaining desktop and server licenses for
service provider interaction. software products it uses, an enterprise
obtains the same functions from the cloud
• Advantages of Cloud Computing service.
• You get economies of scale, professional • SaaS saves the complexity of software
network management, and professional installation, maintenance, upgrades, and
security management. patches.
• Network management, and • Examples of services at this level are Gmail,
professional security management. Google’s e-mail service, and
These features can be attractive to Salesforce.com, which help firms keep track
companies large and small, of their customers.
government agencies, and
individual PC and mobile users. • Platform as a Service (PaaS)
The individual or company only • A PaaS cloud provides service to customers in the
needs to pay for the storage capacity form of a platform on which the customer’s
and services they need. applications can run.
• The user, be it company or • PaaS enables the customer to deploy onto the cloud
individual, doesn’t have the hassle infrastructure containing customer-created or
of setting up a database system, acquired applications.
acquiring the hardware they need, • A PaaS cloud provides useful software building
doing maintenance, and backing up blocks, plus a number of development tools, such as
the data—all these are part of the programming languages, run-time environments,
cloud service. and other tools that assist in deploying new
applications.
• A big advantage of using cloud computing to store • PaaS is an operating system in the cloud. PaaS is
your data and share it with others is that the cloud useful for an organization that wants to develop new
provider takes care of security. or tailored applications while paying for the needed
• But, customer is not always computing resources only as needed and only for as
protected. There have been a long as needed.
number of security failures among • Google App Engine and the Salesforce1 Platform
cloud providers. Evernote made from Salesforce.com are examples of PaaS.
headlines in early 2013 when it told
all of its users to reset their • Infrastructure as a Service (IaaS)
passwords after an intrusion was • IaaS, the customer has access to the underlying
discovered. cloud infrastructure.
• IaaS provides virtual machines and other abstracted
• Cloud networking refers to the networks and hardware and operating systems, which may be
network management function- ality that must be in controlled through a service application
place to enable cloud computing. Most cloud programming interface (API).
computing solutions rely on the Internet, but that is • IaaS offers the customer processing, storage,
only a piece of the networking infrastructure. networks, and other fundamental computing
• One example of cloud networking is the resources so that the customer is able to deploy and
provisioning of high-performance and/or
 run arbitrary software, which can include operating 5. Computer architecture _____ refers to
systems and applications. those attributes of a system visible to a
• IaaS enables customers to combine basic programmer or, put another way, those
computing services, such as number crunching and attributes that have a direct impact on the
data storage, to build highly adaptable computer
logical execution of a program.
systems.
• Examples of IaaS are Amazon Elastic Compute
Cloud (Amazon EC2) and Windows Azure. 6. True - Changes in technology not only
influence organization but also result in the
introduction of more powerful and more
1. Infrastructure as a Service - It provides complex architectures
virtual machines and other abstracted
hardware and operating systems, which
may be controlled through a service 7. Cloud Service Provider - It maintains
application programming interface. computing and data storage resources that
are available over the Internet or private
2. Generations of deployment culminating networks.
in the IoT 8. A gate is a device that implements a
simple Boolean or logical function.
Operational Machines/appliances with
technology embedded IT built by
(OT) non-IT companies, such
as medical machinery, 9. True - Changes in technology not only
SCADA (supervisory con- influence organization but also result in the
trol and data acquisition), introduction of more powerful and more
process control, and complex architectures.
kiosks, bought as
appliances by enterprise 10. Transistors - These are smaller, cheaper,
OT people and primarily and generates less heat than a vacuum
using wired connectivity. tube, can be used in the same way as a
vacuum tube to construct computers.

Personal Smartphones, tablets, 11. False, organization - Computer

technology and eBook readers architecture refers to the operational units
bought as IT devices by and their interconnections that realize the
consumers (employees) architectural specifications.
exclusively using wireless
connectivity and often 12. True - The general- purpose nature of
multiple forms of wireless computers, all the functional specialization
connectivity. occurs at the time of programming and not
at the time of design.
Sensor/actuator Single-purpose devices
technology bought by consumers, IT,
and OT people 13. Evolution of the Intel x86 Architecture
exclusively using wireless
connectivity, generally of
a single form, as part of
larger systems. 80286 This extension of the 8086
enabled addressing a 16-MB
Information PCs, servers, routers, memory instead of just 1 MB
technology (IT) firewalls, and so on,
bought as IT devices by Pentium It was introduced the use of
enterprise IT people and superscalar techniques, which
primarily using wired allow multiple instructions to
connectivity. execute in parallel.

8080 The world’s first general-

purpose microprocessor. This
3. Large- scale integration - An integration
was an 8-bit machine, with an
wherein more than 1,000 components can
8-bit data path to memory.
be placed on a single integrated circuit chip.
8086 A far more powerful, 16-bit
4. Software as a Service- It enables the machine. In addition to a wider
customer to use the cloud provider’s data path and larger registers,
applications running on the provider’s cloud sported an instruction cache, or
infrastructure. queue, that prefetches a few
instructions before they are
executed.
 Pentium II It incorporated Intel MMX electronic circuits and logic
technology, which is designed gates are fabricated
specifically to process video,
audio, and graphics data Arithmetic Performs the operation
efficiently. and logic specified by an instruction
unit (ALU)
80486 It introduced the use of much
more sophisticated and printed It is a flat board that holds
powerful cache technology and circuit board and interconnects chips and
sophisticated instruction other electronic components
pipelining.
Instruction This includes the tasks
Pentium It continued the move into logic involved in fetching
Pro superscalar organization begun instructions, and decoding
with the Pentium, with each instruction to determine
aggressive use of register the instruction operation and
renaming, branch prediction, the memory locations of any
data flow analysis, and operands.
speculative execution.
21.  Embedded System - It refers to the use of
14. Memory cell _________ is a device that electronics and software within a product,
can store 1 bit of data; that is, the device as opposed to a general-purpose computer,
can be in one of two stable states at any such as a laptop or desktop system.
time.
22. False, top-down - In the structure and
15. False, vacuum tubes - The first generation function, the bottom-up approach is the
of computers used transistors for digital most effective and clearest method to use
logic elements and memory. in computer system.
16. Von Neumann Architecture - It is a
fundamental design approach first
implemented in the IAS computer. 23. Data movement - The paths among
components are used to move data from
17. Deeply Embedded System - It uses a memory to memory and from memory
microcontroller rather than a through gates to memory
microprocessor, is not programmable once
the program logic for the device has been 24. Moore's Law - It states that the number of
burned into ROM (read-only memory), and transistors that could be put on a single
has no interaction with a user. chip was doubling every year, and correctly
predicted that this pace would continue into
the near future.
18. Internet of things (IoT) -  It is a term that
refers to the expanding interconnection of 25. Cloud networking - It refers to the
smart devices, ranging from appliances to networks and network management
tiny sensors. functionality that must be in place to enable
cloud computing.
19. Dedicated processor - It is dedicated to
one or a small number of specific tasks
required by the host device and the
processor and associated components can
be engineered to reduce size and cost.

20. Major Elements of a Multicore Computer

motherboard It contains a slot or socket

for the processor chip, which
typically contains multiple
individual cores

Load/store Manages the transfer of data

logic to and from main memory
via cache.

chip It is a single piece of

semiconducting material,
typically silicon, upon which