Hardware and Software Trends

1
Chapter 5

• Hardware and Software Trends

2
Introduction

• Four key areas have fueled the advances in
  telecommunications and computing
• Semiconductor fabrication
• Magnetic recording
• Networking and communications systems
• Software development

3
Exponential Growth

• Gordon Moore (a founder of Intel) observed a
  trend in semiconductor growth in 1965 that has
  held firm for close to 40 years
• Moores Law states that the number of transistors
  on an integrated circuit doubles every 18 months
• Similar performance curves exist in the
  telecommunication and magnetic recording
  industries

4
Semiconductor Technology

• The transistor was invented at Bell Labs in 1947
  by John Bardeen, Walter Brattain, and William
  Shockley
• Semiconductors form the foundation upon which
  much of the modern information industry is based
• Advances in process have allowed system designers
  to pack more performance into more devices at
  decreased cost

5
Trends in Semiconductor Technology

1. Diminishing device size
2. Increasing density of devices on chips
3. Faster switching speeds
4. Expanded function per chip
5. Increased reliability
6. Rapidly declining unit cost

6
Semiconductor Performance

• Electricity (electrons) moves at speeds close to
  the speed of light (186k miles/sec)
• As switching elements of a semiconductor get
  smaller, they can be placed physically closer
  together
• Since the absolute distance between elements
  shrinks, device speed increases
• Semiconductor manufacturing cost is more related
  to number of chips produced rather than number of
  devices per chip

7
Semiconductor Performance

• As device size shrinks, performance improves and
  capability increases (more logic elements in the
  same size package and those elements operate
  faster)
• During the period from 1960 to 1990 density grew
  by 7 orders of magnitude
• 3 circuits to 3 million
• By 2020, chips will hold between 1 to 10 billion
  circuits

8
(No Transcript)
9
Semiconductor Processes

• Semiconductors are produced in processing plants
  called fabs
• Fabs produce semiconductors on silicon wafers
• The wafers are sliced from extremely pure silicon
  ingots and polished
• These wafers can range in size from 6 to 12
  inches (150 to 300 mm) in diameter
• Newer fabs process larger wafers

10
Semiconductor Processes

• Current state of the art fabs process 300 mm
  wafers
• It costs 1.7 billion dollars and takes 30 months
  to construct and equip a fab
• Fabs are completely obsolete, on average, in
  seven years

11
Semiconductor Processes

• Each wafer holds many identical copies of the
  semiconductor
• The wafer moves from process to process across
  the fab, slowly being built up to create the
  final product
• The last step in the process slices the wafer up
  into the individual chips which are tested and
  packaged

12
Semiconductor Processes

• From early in the design of a fab, the number of
  wafers the plant can process per month is
  determined
• To maximize return on capital investment, the
  process engineers attempt to produce the greatest
  number of the highest value chips
• Decreasing device size increases both the number
  of chips per wafer and the speed of the devices
  produced

13
Semiconductor Processes

• The drive to use larger wafers stems from the
  economies of scale
• 2.5 times as many chips can be cut from a 300 mm
  wafer as compared to a 200 mm wafer
• 300 mm fabs cost 1.7 times as much as 200 mm ones

14
Device Geometries

• Device geometry is defined by minimum feature
  size
• This is the smallest individual feature created
  on the device (line, transistor gate, etc.)
• Current feature size in leading edge fabs is 0.10
  microns
• Human hairs are 80 microns in diameter

15
Roadblocks to Device Shrinkage

• Most common chips are made using the
  Complementary Metal Oxide Semiconductor (CMOS)
  process
• Chips using CMOS only consume power when logic
  states change from 1 to 0 or 0 to 1
• As clock speeds increase the number of logical
  operations increases

16
Roadblocks to Device Shrinkage

• As the minimum feature size decreases, components
  are closer together and the number of components
  per unit area increases
• Both these factors increase the amount of waste
  heat needed to be removed from a device
• Effectively removing this heat is a big challenge

17
Industry Success

• Success of the semiconductor industry is driven
  by huge budgets for scientific research, process
  design, and innovation
• Since the semiconductor was invented, the
  industry has experienced a growth rate of 100
  times per decade

18
Industry Innovation

• Increases in device processing power comes not
  only from increased clock rates and decreased
  device sizes
• Innovation in physical computer architecture also
  drives performance
• Bus widths have increased from 8 to 16 to 32 and
  now are growing to 64-bit wide
• With wider busses, more data can be transferred
  from place to place on the chip simultaneously,
  increasing performance

19
Industry Innovation

• Cache Memory Fast, high speed memory used to
  buffer program data near the processor to avoid
  data access delays
• Super scalar designs designs that allow more
  than one instruction to be executed at a time
• Hyperthreading adding a small amount of extra
  on-chip hardware that allows one processor to
  efficiently act as two, boosting performance by
  25

20
(No Transcript)
21
Semiconductor Content

• Microprocessors comprise less than 50 of total
  chip production
• Memory, application-specific integrated circuits
  (ASICs), and custom silicon make up the bulk of
  production
• The telecommunications industry is a huge driver
  worldwide as cell phone penetration increases

22
Summary

• The invention and innovation of the semiconductor
  industry has been enormously important
• Chip densities will continue to increase due to
  innovation in physics, metallurgy, chemistry, and
  manufacturing tools and processes
• Semiconductors will continue to be cheaper,
  faster, and more capable

23
Recording Technologies

• As dramatic as the progress in semiconductor
  development is, progress in recording
  technologies is even more rapid
• Disk-based magnetic storage grew at a compounded
  rate of 25 through the 1980s but then
  accelerated to 60 in the early 1990s and further
  increased to in excess of 100 by the turn of the
  century

24
Exploding Demand

• As personal computers have grown in computing
  power, storage demands have also accelerated
• Operating systems and common application suites
  consume several gigabytes of storage to start
  with
• The World Wide Web requires vast amounts of
  online storage of information
• Disk storage is being integrated into consumer
  electronics

25
Recording Economics

• At current rates of growth, disk capacities are
  doubling every six months
• Growth rates are exceeding Moores Law kinetics
  by a factor of three
• Price per megabyte has declined from 4 cents in
  1998 to 0.07 cent in 2002

26
(No Transcript)
27
Bit Density

• Data density for disk drives is measured in bits
  per square inch called areal density
• Current areal density is 70 gigabits per square
  inch and is expected to climb to 100 gigabits per
  square inch by the end of 2003
• By 2007, areal densities are expected to exceed
  1000 gigabits per square inch

28
Hard Drive Anatomy

• Data is stored on hard drives in concentric
  circles called Tracks
• Each track is divided into segments called
  Sectors
• A drive may contain multiple disks called
  Platters
• Writing or reading data is done by small
  recording heads supported by a mobile arm

29
Hard Drive Performance

• Drive performance is commonly measured by how
  quickly data can be retrieved and written
• Two common measures are used
• Seek Time
• Rotational Delay

30
Hard Drive Performance

• Seek Time is the amount of time it takes the
  heads to move from one track to another
• This time is commonly measured in milliseconds
  (ms or thousandths of a second)
• For a processor operating at 1 Ghz, 1 ms is
  enough time to execute one million instructions
• Common seek times of inexpensive drives are from
  7 to 9 ms

31
Rotational Delay

• The delay imposed by waiting for the correct
  sector of data to move under the read / write
  heads
• Current drives spin at 7200 RPM.
• Faster rotational speeds decrease rotational
  delay
• High end server drives spin at 15000 RPM, with
  surface speeds exceeding 100 MPH
• Heads float on a cushion of air 3 millionths of
  an inch thick

32
Other Performance Issues

• Data transfer interfaces are constantly evolving
  to keep pace with higher drive performance.
• New standards include
• Firewire
• USB 2
• InfiniBand

33
Fault-Tolerant Storage

• Data has become a strategic asset of most
  businesses
• Loss of data can cripple and sometimes kill an
  enterprise
• Fault-tolerant storage systems have become more
  important as data availability has become more
  critical

34
RAID Storage

• RAID is an acronym that stands for Redundant
  Array of Inexpensive Drives
• RAIDs spread data across multiple drives to
  reduce the chance that the failure of one drive
  would result in data loss
• RAID levels commonly range from 0 to 5 with some
  derivative cases

35
RAID Tradeoffs

• Creating data redundancy creates transactional
  overhead and waste of storage capacity
• RAID 1 is also known as disk mirroring where
  every bit on one disk is duplicated on the mirror
• Every transaction takes two reads or two writes,
  and disk space is half of capacity

36
RAID Tradeoffs

• RAID 5 spreads data across multiple disks and
  creates special error-correcting data
• With any drive failure, the lost data can be
  reconstructed from the remaining data and the
  error-correcting codes
• This has less redundancy than a RAID 1 system,
  but delivers better throughput

37
RAID Results

• Mean time before data loss (MTBDL) is a
  calculation that attempts to quantify the
  reliability of a drive
• A four-disk storage system without RAID has a
  MTBDL of 38,600 hours or about once every four
  years
• A five-disk RAID 5 system of equal capacity
  yields a MTBDL of 48.875 million hours

38
CD-ROM Storage

• Five inches in diameter, capable of holding 650
  MB of data
• So inexpensive, powerful, and widespread are
  these disks, that many PC manufacturers are
  discontinuing the sale of 1.44 MB floppy drives
  in new PCs
• CD-R blanks are now costing approximately 5 cents
  each

39
DVD Storage

• DVDs or Digital Versatile Discs
• Store 4.7 GB of digital data
• Can be used to store video, audio, or larger data
  archives

40
Autonomous Storage Systems

• Computers have traditionally been built with
  display, compute, and storage subsystems in close
  physical proximity
• With widespread, high speed digital networks,
  these components no longer need to be in the same
  physical box
• Network Attached Storage and Storage Area
  Networks are storage examples of this trend

41
Network Attached Storage

• A logical extension of the client/server model
• NAS boxes are servers not of applications but of
  storage
• Data storage can be centralized so that the
  disciplines of archiving, security, availability,
  and restoration are handled by computing
  professionals, not desktop users

42
Storage Area Networks

• Commonly referred to as the network behind the
  server
• Create a unified storage architecture that
  supports the storage needs of multiple servers
• Server to storage links are high-speed optical
  connections using network-like protocols complete
  with routers and switches

43
Benefits of Storage Systems

• Data throughput from a server standpoint and from
  a storage standpoint must be balanced
• Fast servers with slow storage or slow servers
  with fast storage do not deliver optimal
  performance
• Decoupling storage from computation allows
  managers to scale each independently

44
Computer Architecture

• Computers include
• Memory
• Mass storage
• Logic
• Peripherals
• Input devices
• Displays

45
Supercomputers

• At the extreme edge of the computing spectrum,
  supercomputers are clusters of individual
  machines lashed together with high-speed network
  connections
• The 50 most powerful supercomputers in existence
  today are built of no less than 64 processors
• The most powerful are composed of close to 10,000
  individual processors

46
Supercomputer Performance

• Current benchmarking for supercomputers is the
  flop or floating-point operations per second
• The most powerful supercomputers in the world
  easily exceed 1 tera-flops
• The most powerful machine can attain 35 Tflops

47
Supercomputer Challenges

• Effectively harnessing thousands of CPUs together
  is a very complex programming challenge
• Massively parallel computing operating systems
  are difficult to design, optimize, and
  troubleshoot

48
Microcomputers

• The first microcomputer was sold by IBM in the
  early 1970s
• With the progress of Moore's Law, PCs have become
  more and more powerful with desktop systems able
  to deliver in excess of 2500 MIPS (millions of
  instructions per second)
• 10000 MIPS systems will be commonplace by the end
  of the decade

49
Trends in Systems Architecture

• Slowly systems are shifting from being PC focused
  to network focused

50
Client/Server Computing

• With powerful graphical workstations and
  high-speed networking, PCs have become the user
  interface engine, not the application
• The most obvious example is the Web browser. Any
  number of servers using numerous different server
  programs are all accessible by the same Web client

51
Thin Clients

• With the hollowing out of the computer, client
  PCs no longer need to do it all
• Storage can be offloaded to SANs or NAS arrays
• Compute cycles can be located on application
  servers across or even external to the enterprise

52
Communications Technology

• The same semiconductor and switching technologies
  that have driven the computer revolution have
  driven the telecommunications revolution
• Fiber-optic data capacity has increased even
  faster than Moores Law rates for semiconductors
• Fiber-optic capacity doubles every six months

53
Intranets, Extranets, and the WWW

• Intranet Network dedicated to internal
  corporate use
• Extranet Network used to bring partners
  external to the company into the corporate network

54
The World Wide Web

• Invented by Tim Berners-Lee at CERN
• Open standard client/server interface
• Uses open standard HTML for page formatting and
  display
• The Web creates a powerful open access structure
  that everyone can leverage for business needs

55
WWW and Business

• Intranets, extranets, and the Internet all play
  parts in creating an e-enabled business
• Client/server architectures modularize components
  allowing special purpose or custom built systems
  for online business

56
(No Transcript)
57
Thin Clients

• Called thin because they have minimal local
  storage, and function primarily as display
  devices
• Applications are executed locally but reside
  remotely

58
Benefits of Thin Clients

• Thin clients allow businesses to have a high
  degree of control over users desktops
• Central client management eases troubleshooting
  and allows rollout of application upgrades
  without much overhead
• Thin clients commonly lack removable storage so
  data security is enhanced

59
Programming Technology

• As opposed to the exponential rate of growth with
  the previously discussed technologies, software
  has grown at a linear pace

60
Operating Systems

• Current examples are
• Microsoft Windows XP
• Linux (Open source)
• Apple OS X
• Free BSD (Open source)
• Solaris (Sun)
• AIX (IBM)

61
History of Operating Systems

• First programs were called Monitors
• They allowed operators to more easily load
  programs and retrieve output
• Uniprocessing executing one program at a time
• Multiprocessing appearing to execute several
  programs simultaneously by processing a few
  instructions from each in succession

62
Network Operating Systems

• Operating systems that incorporate network aware
  hooks so that systems can utilize resources
  seamlessly across the network infrastructure
• Microsofts Windows 2000 and Linux both
  incorporate these elements directly out of the box

63
Application Programming

• Internet technology requires new tools to exploit
  its full potential
• Markup languages such as SGML, HTML, and XML
• Java is used to code applications that can run on
  a broad range of operating systems and
  microprocessors

64
Recapitulation

• The torrent of innovation of the past 30 years
  will continue
• Technology will open opportunities and foster
  innovation that will continue to change our way
  of life
• It is as important how we use technology as it is
  what technology enables. These innovations are
  tools, and carry the same moral hazards that all
  tools have

65
Implications

• Tomorrows managers will have magnitudes greater
  capability than todays
• Huge data stores will profile customers,
  patients, and employees
• Intranets will begin to break down the barriers
  between levels of management, eliminating
  distance in time and bureaucracy

66
Implications

• Business models are changing with B2B, B2C, and
  ASP models becoming rapidly growing markets
• Information is a strategic asset as well as a
  business tool
• With rapid, granular Internet information
  strategies, information may be shared even with
  competitors if it serves a business purpose at
  the time

67
Summary

• New breakthroughs in information processing
  technology will challenge our ability to harness
  and integrate these advances into society,
  corporations, and governmental organizations
• Rapid organizational changes will be the norm
• Failure to embrace change dooms organizations and
  their leaders to failure