Chapter 5

Hardware and Software Trends

Introduction

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

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

• Moore’s 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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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 %

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

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

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

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

Recording Economics

• At current rates of growth, disk capacities are doubling every six months

• Growth rates are exceeding Moore’s Law kinetics by a factor of three

• Price per megabyte has declined from 4 cents in 1998 to 0.07 cent in 2002

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

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

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

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

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

Other Performance Issues

• Data transfer interfaces are constantly evolving to keep pace with higher drive performance.

• New standards include:– Firewire– USB 2– InfiniBand

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

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

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

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

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

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

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

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

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

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

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

Computer Architecture

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

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

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

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

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

Trends in Systems Architecture

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

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

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

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 Moore’s Law rates for semiconductors

• Fiber-optic capacity doubles every six months

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

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

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

Thin Clients

• Called “thin” because they have minimal local storage, and function primarily as display devices

• Applications are executed locally but reside remotely

Benefits of Thin Clients

• Thin clients allow businesses to have a high degree of control over user’s 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

Programming Technology

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

Operating Systems

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

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

Network Operating Systems

• Operating systems that incorporate network aware hooks so that systems can utilize resources seamlessly across the network infrastructure

• Microsoft’s Windows 2000 and Linux both incorporate these elements directly out of the box

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

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

Implications

• Tomorrow’s managers will have magnitudes greater capability than today’s

• 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

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

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