Presentation by:

1

CISC / RISC comparisons
for Embedded applications

Presentation by Ragu Jegan
Murugesan Course
Advanced Embedded Systems Design
Instructor Dr.Marvin
Stone
Oklahoma State University
Nov 29, 2004
2
Overview

• CISC
• RISC
• Hybrid CISC-RISC
• Choice for Embedded Processors
• CISC Embedded Processors
• RISC Embedded Processors
• Embedded Market
• Conclusion

3
CISC ?

4
CISC

• CISC is a philosophy for designing chips that are
  easy to program and which make efficient use of
  memory. It stands for - Complex Instruction Set
  Computer
• Each instruction in a CISC instruction set might
  perform a series of operations inside the
  processor.
• This reduces the number of instructions required
  to implement a given program. In general terms,
  the instruction sets are designed for the
  convenience of the assembly-language programmer

5
CISC

• The CISC philosophy made more sense, since the
  earliest machines were programmed in assembly
  language and memory was slow and expensive
• Most common microprocessor designs - including
  the Intel 80x86 and Motorola 68K series - follow
  the CISC philosophy.
• The design constraints that led to the
  development of CISC are
• small amounts of slow memory and
• the fact that most early machines were programmed
  in assembly language

6
CISC Microprogramming

• The earliest processor designs used dedicated
  (hardwire) logic to decode and execute each
  instruction in the processor's instruction set.
• This worked well for simple designs with few
  registers, but made more complex architectures
  hard to build, as control path logic can be hard
  to implement.
• So, designers switched tactics - they built some
  simple logic to control the data paths between
  the various elements of the processor, and used a
  simplified microcode instruction set to control
  the data path logic. Thistype of implementation
  is known as a microprogrammed implementation.

7
CISC Microprogramming

• The principle is based on binary coding an
  instruction such that its binary value forms the
  address of a location in a block of memory built
  within the CPU. 
• The addressed location contains a hard-wired bit
  pattern that corresponds to the necessary control
  signals required to perform the instruction.
• Instruction decode then takes place by gating the
  bit pattern on to the CPU's control bus.
  Effectively the memory acts as a translation
  table from Instruction Codes to the required
  control signals.

8
CISC Microprogramming

• These control signals then activate the various
  parts of the CPU required to perform the
  instruction - e.g. gating data from the data bus
  into the Accumulator, triggering the adder
  circuitry in the ALU etc. 
• These actions are referred as 'Microinstructions'
  and the bit patterns stored in the ROM locations
  are referred as 'Microcode'.

9
CISC Microprogramming

• In a micro-programmed system, the main processor
  has some built-in memory (typically ROM) which
  contains groups of microcode instructions which
  correspond with each machine-language
  instruction.
• When a machine language instruction arrives at
  the central processor, the processor executes the
  corresponding series of microcode instructions.

10
CISC Microprogramming

• Because instructions could be retrieved up to 10
  times faster from a cache memory than from main
  memory, designers began to put as many
  instructions as possible into microcode.
• In fact, some processors could be ordered with
  custom microcode which would replace frequently
  used but slow routines in certain application.

11
CISC Microprogramming

• Advantages of a microcode implementation
• Since the microcode memory can be much faster
  than main memory, an instruction set can be
  implemented in microcode without losing much
  speed over a purely hard-wired implementation.
• New chips are easier to implement and require
  fewer transistors than implementing the same
  instruction set with dedicated logic
• A micro-programmed design can be modified to
  handle entirely new instruction sets quickly.  

12
CISC Flexibility of Microprogramming

• Some machines were optimized for scientific
  computing, while others were optimized for
  business computing.
• Since they all shared the same instruction set,
  programs could be moved from machine to machine
  without re-compilation (but with a possible
  increase or decrease in performance depending on
  the underlying hardware.)
• This kind of flexibility and power made
  microcoding the preferred way to build new
  computers for quite some time.

13
Ideal CISC machine

• CISC processors were designed to execute each
  instruction completely before beginning the next
  instruction. (Similar to Run To Completion (RTC)
  model in Co-operative Schedulers)
• Even so, most processors break the execution of
  an instruction into several definite stages as
  soon as one stage is finished, the processor
  passes the result to the next stage

14
Ideal CISC machine

• Four stages in a typical CISC machine
• An instruction is fetched from main memory.
• The instruction is decoded the controlling code
  from the microprogram identifies the type of
  operation to be performed, where to find the data
  on which to perform the operation, and where to
  put the result. If necessary, the processor reads
  in additional information from memory.
• The instruction is executed the controlling code
  from the microprogram determines the
  circuitry/hardware that will perform the
  operation.
• The results are written to memory.

15
CISC advantages

• As each instruction is more capable, fewer
  instructions could be used to implement a given
  task. This made more efficient use of the
  relatively slow main memory.
• Microprogramming is as easy as assembly language
  to implement, and much less expensive than
  hardwiring a control unit.
• The ease of microcoding new instructions allowed
  designers to make CISC machines upwardly
  compatible a new computer could run the same
  programs as earlier computers because the new
  computer would contain a superset of the
  instructions of the earlier computers.
• Because microprogram instruction sets can be
  written to match the constructs of high-level
  languages, the compiler does not have to be as
  complicated.

16
CISC disadvantages

• Many specialized instructions aren't used
  frequently enough to justify their existence -
  approximately 20 of the available instructions
  are used in a typical program.
• Earlier generations of a processor family
  generally were contained as a subset in every new
  version - this made the machines compatible - but
  the instruction set chip hardware become more
  complex with each generation of computers.
• Different instructions take different amount of
  clock time to execute, due to their variable
  length, slowing down the overall performance of
  the machine.

17
RISC ?

18
RISC

• RISC is a microprocessor that is designed to
  perform a smaller number computer instructions so
  that it can operate at a higher speed. It stands
  for - Reduced Instruction Set Computer
• John Cocke of IBM Research in Yorktown, New York,
  originated the RISC concept in 1974 by proving
  that about 20 of the instructions in a computer
  did 80 of the work. The first computer to
  benefit from this discovery was IBM's PC/XT in
  1980. Later, IBM's RISC System/6000, made use of
  the idea.
• The term itself (RISC) is credited to David
  Patterson, a teacher at the University of
  California in Berkeley. The concept was used in
  Sun Microsystems' SPARC microprocessors and led
  to the founding of what is now MIPS Technologies,
  part of Silicon Graphics.

19
RISC

• Performance and design related improvements of
  RISC
• A new microprocessor can be developed and tested
  more quickly if one of its aims is to be less
  complicated.
• Operating system and application programmers who
  use the microprocessor's instructions will find
  it easier to develop code with a smaller
  instruction set.
• The simplicity of RISC allows more freedom to
  choose how to use the space on a microprocessor.
• Higher-level language compilers produce more
  efficient code than formerly because they have
  always tended to use the smaller set of
  instructions to be found in a RISC computer.

20
RISC characteristics

• Simple instruction set. In a RISC machine, the
  instruction set contains simple, basic
  instructions, from which more complex
  instructions can be composed.
• Same length instructions. Each instruction is
  the same length, so that it may be fetched in a
  single operation.
• 1 machine-cycle instructions. Most instructions
  complete in one machine cycle, which allows the
  processor to handle several instructions at the
  same time. This pipelining is a key technique
  used to speed up RISC machines.

21
Pipelining A key RISC technique

• RISC designers are concerned primarily with
  creating the fastest chip possible, and so they
  use a number of techniques, including pipelining.
  
• Pipelining is a design technique where the
  computer's hardware processes more than one
  instruction at a time, and doesn't wait for one
  instruction to complete before starting the next.
  
• RISC machine has the same four stages as in our
  typical CISC machine fetch, decode, execute, and
  write. But these stages are executed in parallel.
  As soon as one stage completes, it passes on the
  result to the next stage and then begins working
  on another instruction.
• In a typical pipelined RISC design, each
  instruction takes 1 clock cycle for each stage,
  so the processor can accept 1 new instruction per
  clock.

22
RISCs advantages

• Speed. Since a simplified instruction set
  allows for a pipelined, superscalar design RISC
  processors often achieve 2 to 4 times the
  performance of CISC processors using comparable
  semiconductor technology and the same clock
  rates.
• Simpler hardware. Because the instruction set
  of a RISC processor is so simple, it uses up much
  less chip space extra functions, such as memory
  management units or floating point arithmetic
  units, can also be placed on the same chip.
  Smaller chips allow a semiconductor
  manufacturer to place more parts on a single
  silicon wafer, which can lower the per-chip cost
  dramatically.

23
RISCs advantages

• Shorter design cycle.Since RISC processors are
  simpler than corresponding CISC processors, they
  can be designed more quickly, and can take
  advantage of other technological developments
  sooner than corresponding CISC designs, leading
  to greater leaps in performance between
  generations.

24
RISCs disadvantages

• Code Quality The performance of a RISC processor
  depends greatly on the code that it is executing.
  If the programmer (or compiler) does a poor job
  of instruction scheduling, the processor can
  spend quite a bit stalling waiting for the
  result of one instruction before it can proceed
  with a subsequent instruction. Since the
  scheduling rules can be complicated, most
  programmers use a high level language (such as C
  or C) and leave the instruction scheduling to
  the compiler. This makes the performance of a
  RISC application depend critically on the quality
  of the code generated by the compiler. Therefore,
  developers (and development tool suppliers such
  as Apple) have to choose their compiler carefully
  based on the quality of the generated code.

25
RISCs disadvantages

• Code expansionCode expansion refers to the
  increase in size that you get when you take a
  program that had been compiled for a CISC machine
  and re-compile it for a RISC machine. The exact
  expansion depends primarily on the quality of the
  compiler and the nature of the machine's
  instruction set. Since CISC machines perform
  complex actions with a single instruction, when
  RISC machines may require multiple instructions
  for the same action, code expansion can be a
  problem.

26
RISCs disadvantages

• System Design
• They require more instructions, and hence
  memory, than CISCs to implement applications.
• Another problem the RISC machines faces is
  that they require very fast memory systems to
  feed them instructions. RISC-based systems
  typically contain large memory caches, usually on
  the chip itself. This is known as a
  first-level cache.

27
Classic Performance Equation

• The Performance Equation
• The following equation is commonly used for
  expressing a computer's performance ability

time time
cycles instructions Program
cycle instruction
program
28
CISCs Performance Equation

• CISC approach attempts to minimize the number of
  instructions per program, sacrificing the number
  of cycles per instruction.

time time
cycles instructions Program
cycle instruction
program
29
RISCs Performance Equation

• RISC does the opposite, reducing the cycles per
  instruction at the cost of the number of
  instructions per program.

time time
cycles instructions Program
cycle instruction
program
30

Cisc Instruction example CISC provides a
large and powerful range of instructions, which
is less flexible to implement. For example, the
8086 microprocessor family has these
instructions JA Jump if Above JAE Jump if
Above or Equal JB Jump if Below ... JPO Jump
if Parity Odd JS Jump if Sign JZ Jump if Zero
There are 32 jump instructions in the 8086, and
the 80386 adds more.
31

• Risc Instruction example
• RISC concept is to identify the sub-components
  and use those.
• These are much simpler, they can be implemented
  directly in silicon,
• so will run at the maximum possible speed.
• There are only two Jump instructions in the ARM
  processor
• - Branch and Branch with Link.
• The "if equal, if carry set, if zero" type of
  selection is handled by condition options. For
  example
• BLNV Branch with Link NeVer
• BLEQ Branch with Link if EQual
• BL part is the instruction, and the following
  part is the condition.
• We can test something, then only do the next few
  commands if the criteria
• of the test matched.
• No branching off, we simply add conditional
  flags to the instructions we
• require to be conditional

32
Comparision
Feature RISC CISC
Power One or two mill watts Many watts
Compute Speed Up to a mega-flop Up to several mega-flop
I/O Custom, any sort of hardware PC based options via a BIOS
Cost Dollars Tens to hundreds of Dollars
Environmental High Temp, Low EM Emissions Needs Fans, FCC/CE approval an issue
Operating System Port Difficult, requires low-level BSP. Roughly equivalent to making a Mac OS run on a SPARC Station Load and Go- simplified by an industry standard BIOS
33
Why CISC still lives?

• Why are there still CISC CPUs being developed?
• Why is Intel spending time and money to
  manufacture the Pentium III and Pentium 4?
• AnswerThe answer is simple, backward
  compatibility. The IBM compatible PC is the most
  common computer in the world. Intel wanted a CPU
  that would run all the applications that are in
  the hands of more than 100 million users.

34
Hybrid CISC-RISC

• Up till the mid 1990s, processor designers were
  split into two opposing camps.
• One side supported CISC designs due to its low
  burden on compiler developers and wide
  availability of existing software.
• The other camp supported RISC designs because of
  its simplicity and efficiency.
• However, the CISC vs. RISC debate has now died
  down as contemporary processor designers realize
  that RISC designs might benefit from the addition
  of some CISC characteristics and vice-versa.

35
Hybrid CISC-RISC

• Today, most CISC processors are based on hybrid
  CISC-RISC architecture.
• These designs use a decoder to convert CISC
  instructions into RISC instructions before
  execution. They are then processed by a RISC
  core, which performs a few basic instructions
  very quickly.
• Having a RISC core is advantageous because it
  allows performance enhancing features, such as
  pipelining and branch prediction.
• Popular examples of hybrid designs include the
  Pentium and Athlon family of processors. These
  processors are compatible with software written
  for their CISC predecessors yet perform
  competitively against processors based on RISC
  designs.

36
Hybrid CISC-RISC
RISC and CISC The Best Of Both Worlds

• (AltiVec unit adds 162 new instructions to
  the existing RISC architecture)

37
RISC becomes CISC-like

• RISC processors, have become more CISC-like by
  supporting more functions.
• In fact, many modern RISC processors support more
  instructions than old CISC designs!
• E.g.Motorola G4 processor used in Power Macs and
  eMacs. Its AltiVec unit adds 162 new instructions
  to the existing RISC architecture.
• By following the CISC philosophy of adding more
  instructions, some applications can be run much
  faster. These include multimedia applications,
  such as telecommunications encoding/decoding,
  image conversions and video processing.

38
CISC becomes RISC-like

• On the other hand, CISC have become like
  RISC.Apart from having a RISC core, the number of
  general-purpose registers in CISC processors has
  also grown. This follows RISC ideals and allows
  more instructions to be processed simultaneously.
• E.g.
• The Intel Pentium III with its SSE technology has
  an additional eight 128-bit vector registers.
• AMD's new x86-64 chips also have an additional 8
  general purpose registers and 8 SSE registers.
• The future successor to the Pentium series, Intel
  Itanium IA-64, will even raise the bar further by
  implementing 128 general purpose registers!

39
Choice for Embedded Processors ?
CISC?
RISC?

40
Choice for Embedded Systems ?

• In favor of RISCCISC (also CISC -RISC hybrids)
  consume a lot of power and are not the best
  candidates for embedded applications.
• RISC were designed analytically to deliver
  the most processing power per instruction
  executed. Based on power consumption feature,
  these RISC systems are the favored choice for
  embedded systems where low power is an issue.

41
Choice for Embedded Systems ?

• In favor of RISCAlmost two-thirds of all the
  microprocessors and microcontrollers sold in 2002
  were 8-bitters, all of which were CISC
  architectures like the 8051 and 6805.
  Practically all 4-bit and 16-bit processors are
  also CISC designs.But to be fair, RISC has
  overtaken CISC in the 32-bit embedded world.
  Until 1999, Motorola's 68k was the best-selling
  32-bit processor since the category was created.
  SPARC, MIPS, AMD's 29000,Intel's i960, ARM, and
  even Motorola's own 88000 challenged that
  business throughout the '90s, but the 68k stood
  firm. ARM shipments finally overtook the 68k in
  1999, and the gap has yawned wider ever since.
  ARM licensees (the company makes no chips of its
  own) now collectively outsell Intel's Pentium
  line by a hefty 31 margin. RISC processors are
  doing well at the sharp end of the market

42
Choice for Embedded Systems ?

• In favor of CISCThe Power Angle.
• RISC chips have a reputation for being
  low-power devices able to run on batteries,
  bright sunlight. It's true that most RISC
  processors use less energy than, say, Pentium 4.
  That's largely due to their more modern silicon
  manufacturing, not any inherent power-saving
  characteristic of RISC. MIPS, ARM, and PowerPC
  chips use less power than Pentium and Athlon
  chips because they're willing to give up speed
  for power. Low-power chips are made, not born.

43
Choice for Embedded Systems ?

• In favor of CISCRemember RISC processors are
  chips that failed in the desktop computer market.
  They're overwhelmingly losers.
• They're used in embedded systems by default,
  not by design. Like the early settlers of a
  community, RISC has transformed itself into a
  symbol of new hope and opportunity. But, CISC is
  not dead yet.

44
Choice for Embedded Systems ?

• In favor of CISCProgramming is one area where
  CISC processors shine.CISC chips are by nature
  "mature" architectures that have been in the
  market for a long time.
• They have a long and distinguished list of
  software tools, operating systems, debuggers,
  compilers.

45
Choice for Embedded Systems ?

• In favor of CISC
• Motorola's 68k and Intel's x86 families are the
  two predominant 32-bit CISC architectures, and
  they both enjoy a huge software
  availabities.Nearly any tool, driver, or
  middleware you want to name is available for
  these chips-often for free. And all of the
  bugs, quirks, and idiosyncrasies were discovered
  long ago by the hundreds of programmers who came
  before. If you're looking for stable, solid,
  well-supported, well-documented processors, look
  no further than CISC

46
Embedded Processors examples
CISC RISC
68000 series Sparc
X86 family AMD 29000
PDP-11 MIPS
VAX SuperH
IBM 370 PowerPC
Arm
47
CISC Embedded Processors

48
Motorola's 68000 (68K) family CISC

• It is the old man of the embedded processor
  market, and the most popular 32-bit processor
  family in the world until just a few years ago.
• The whole 68K family is an example of CISC
  architecture that fell out of favor in PCs long
  ago, but still has some strong advantages for
  embedded usages.
• Sun originally used 68K processors in its first
  workstations, and all Macintoshes were 68K-based
  until PowerPC came along.
• Now 68K chips are almost always used for embedded
  systems, and Motorola still sells to the tune of
  about 75 million chips per year.
• The whole 68K family goes strong, mostly because
  designers love it, and because so many of the
  chips are already designed-in to millions of
  existing products.

49
x86 CISC

• Like the 68K family, the x86 family is an example
  of CISC architecture. It is one of the
  longest-lived CPU designs ever.
• The "x86 family" refers to Intel's architecture
  that started with the 8086 through the '286,
  '386, and '486, and continues to this day with
  Pentium 4 and AMD's Athlon
• We all know that x86 processors dominate PC
  systems. But in embedded sales, x86 chips like
  the '486DX rank a distant fifth in sales behind
  the ARM, 68K, MIPS, and SuperH.
• That doesn't make them unsuccessful--there are
  more than a dozen competitors that rank even
  lower
• In almost every measure, x86 chips are the
  slowest, most power-hungry, and hardest to
  program processors around. Almost anything would
  be better, and most of the alternatives are,
  which is why there's so much competition for
  embedded processors.

50
PDP -11 CISC

• The PDP-11 was a 16-bit minicomputer sold by
  Digital Equipment Corp. in the 1970s and 1980s
• It had several uniquely innovative features, and
  was easier to program
• Although the basic architecture was extremely
  good, and the PDP-11 line was continually updated
  to use newer technologies, it finally died off
  for one principal reason the 16-bit address
  space was simply too small.
• When large VLSI memory chips became very cheap,
  the PDP-11 was just not capable of using large
  amounts of memory easily.

51
VAX CISC

• VAX was originally an acronym for Virtual Address
  eXtension, because the VAX was seen as a 32-bit
  extension of the older 16 bit PDP-11.
• VAX is 32-bit addressing computer architecture
  developed in the mid-1970s by DEC.DEC was later
  purchased by Compaq, which in turn was later
  purchased by Hewlett-Packard.
• Trivia VAX is also a brand of wet-dry vacuum
  cleaners, invented in the 1970s. The advertising
  slogan "Nothing sucks like a Vax" was often
  applied ironically by users of VAX computers.

52
RISC Embedded Processors

53
SPARC RISC

• SPARC is best known as the processor used in Sun
  workstations
• SPARC was one of the first RISC designs to see
  the light of day
• In the early 1990s, embedded SPARC chips were
  actually pretty common. Now they're almost
  nonexistent.
• SPARC, like ARM and MIPS, is a licensed
  architecture. Sun doesn't actually make
  processors, so don't go looking for chips with
  the Sun brand name on them.
• A few years ago there were close to ten companies
  making SPARC processors, all different. Sun was
  really the only big customers for them, though,
  so almost all of the SPARC makers went out of
  business.
• TI and Fujitsu are the only significant SPARC
  chip developers left, and this early pioneering
  architecture has all but disappeared from the
  embedded scene.

54
AMD 29000 RISC

• Similar to SPARC chips in the past, AMD's 29000
  processors were also popular, particularly in the
  first Apple laser printers and in some networking
  equipment.
• The 29K was an exceptionally elegant,
  high-performance RISC design. It was most notable
  for its whopping 192 programmable registers (most
  RISC chips have 32 Pentium has eight), which
  made it a programmer's delight. Alas, despite all
  of the 29K's architectural elegance, it was not
  long for this world.
• Why would AMD abandon an entire product line just
  as it becomes the second-best-selling RISC
  architecture in the world?
• Because its support costs were too high. AMD was
  paying third-party developers of compilers,
  operating systems, and other programming tools to
  support the 29K.

55
AMD 29000 RISC

• The world's second-most-popular RISC architecture
  was losing money, as these yearly subsidies were
  eating up all of the 29K's profits. As word of
  the 29K's demise spread, customers started
  looking for alternatives.
• Even though several 29K chips remained in
  production for a few more years, the writing was
  on the wall and customers fled to a number of
  other alternatives

56
Intel i960 RISC

• The i960 was once the best-selling RISC
  architecture on the planet.
• In the early '90s you could find an i960
  processor in almost every laser printer or
  network router made. The i960 was particularly
  popular in HP's LaserJet series of printers, just
  as LaserJet sales took off.
• Like most embedded chips, and all RISC
  processors, it was originally designed to power
  workstations. It came out of a joint venture
  between Intel and Siemens called BiiN. BiiN was
  supposed to develop fault-tolerant Unix
  workstations
• Intel gained control of the processor it
  developed with Siemens. In fairness, Siemens may
  not have wanted the processor very much. It was
  expensive, slow, and very power-hungry. The
  processor also had complex fault-tolerant
  features that made it difficult to manufacture
  and debug and had no (apparent) use outside of
  the workstation market.

57
Intel i960 RISC

• But somehow Intel tried this cast-off processor,
  now called the 80960 or i960, to rapidly find a
  home in embedded systems.
• The i960 family never did overcome its power-hog
  reputation
• Once again hoping to pull a rabbit out of its
  hat, Intel devised a new market for the i960
  intelligent I/O controllers.
• The I2O standard was born, and it cleverly
  defined requirements that just happened to match
  the characteristics of existing i960 chips. After
  some initial lukewarm success, I2O controllers,
  and the i960 processors, eventually faded away.

58
MIPS RISC

• MIPS is a prime example of a high-end computer
  architecture that is more successful in toys and
  games than it ever was in engineering
  workstations.
• It got its name from Microprocessor without
  Interlocked Pipeline Stages
• MIPS, the company, originally acquired by Silicon
  Graphics (SGI) in the 1990s started using MIPS
  processors in all its workstations. But,
  weakening profits from workstations couldn't
  support the awesome cost of developing new 32-bit
  and 64-bit microprocessors.
• MIPS/SGI signed up an unusual new customer
  Nintendo. The Japanese game maker wanted to use a
  slightly modified MIPS processor in its upcoming
  N64 video game. This turned out to be MIPS'
  biggest deal ever.The company got two-thirds of
  its money from Nintendo throughout the late
  1990s.

59
MIPS RISC

• Although MIPS doesn't dominate the home
  video-game market like it once did, the
  architecture has comfortably settled into the
  number two RISC position.
• MIPS has extended its family of processors both
  at the high end, with its monstrous 64-bit 20Kc
  family, andat the low end, with SmartMIPS, a
  minimal 32-bit design for smart cards and other
  ultra-low-power systems.
• There's probably no other CPU family that reaches
  so high and so low while remaining software
  compatible throughout the line.

60
SuperH RISC

• Hitachi's SuperH, or SH, processors have been
  around for more than a decade but they were
  almost unknown outside of Japan until recently
• The SuperH family of chips includes some 16-bit
  and some 32-bit processors, most with added
  peripheral I/O and special-purpose controllers.
• SuperH's big hit was with the Sega Saturn video
  game, followed by the Sega Dreamcast. We can also
  find SuperH chips in some of the handheld Windows
  CE computers from Compaq and Casio.
• The SH7750 processor was designed especially for
  Sega and includes some fantastic 3D geometry
  instructions that outstrip anything an x86
  processor can do.

61
PowerPC RISC

• PowerPC started squeaking into the embedded scene
  around 1996. PowerPC design existed in both
  32-bit and 64-bit implementations .
• Within two years, there were more PowerPC chips
  being sold in embedded applications than in
  computers (such as Macintosh), making PowerPC
  "officially" an embedded processor.
• Even so, PowerPC remains a marginal player in the
  overall embedded landscape, selling more than
  SPARC but less than most 32-bit competitors.
• Numerically, the PowerPC is most found in
  controllers in cars.
• Networking is another area where embedded PowerPC
  processors are found in large numbers. PowerQUICC
  MPC860 was a very famous processor used in many
  Cisco edge routers in the late 1990s

62
ARM RISC

• ARM (formerly Advanced RISC Machines) also
  started out as a computer processor, but
  ultimately failed in that market. Now ARM is one
  of the most popular 32-bit embedded designs
  around.
• The English company was originally called Acorn,
  and its older BBC Micro computer was the British
  equivalent to America's Apple II or Commodore 64.
  The BBC Micro was probably the first commercial
  deployment of RISC technology.
• Apple, IBM, Commodore, and other early computer
  vendors ultimately overwhelmed the BBC Micro, but
  its processor design lived on. In recent years,
  the ARM architecture has challenged for, and then
  overtaken, the RISC lead.

63
ARM RISC
64
ARM RISC

• ARM's biggest volume wins have been in a number
  of digital cell phones, particularly those
  manufactured in Europe (ARM is the only European
  entry in this race).
• ARM's simple design gives it small silicon
  footprint, which, in turn, gives it modest power
  consumption. Its comparatively low power combined
  with its ability to be embedded into high-volume
  ASICs gave ARM a leg up in mobile phones.
• Digital Semiconductor (part of DEC) surprised the
  world with StrongARM. Using the same silicon
  technology it used with its phenomenal Alpha
  processors, Digital quadrupled the best speed
  anyone had seen in an ARM-based chip.

65
ARM RISC

• Unfortunately, about that same time, Digital
  suicidally chose to sue Intel over an unrelated
  patent infringement. Intel settled the case
  quickly - by buying Digital Semiconductor rights
  to StrongARM.
• StrongARM now lives on under the new name of
  XScale.
• The first XScale chips are part of Intel's new
  "Personal Internet Client Architecture" (PCA) and
  promise to maintain the high standards set by the
  Digital Semiconductor.

66
Who is in the lead?

• The list of vendors described is by no means
  complete.
• We could fill 100 more slides on the other
  choices available just among 32-bit embedded
  processors. There are more than 115 different
  32-bit embedded chips in production right now,
  all of them with happy, healthy users who love
  them.
• History shows that no company holds the lead for
  long in the embedded market. Maybe in a few years
  one of these players will be sitting at the top
  of the heap.

67
Embedded Processors An Analogy
Viruses- PentiumProcessors Insects- Embedded
Processors
68
Embedded Processors An Analogy

• Statistically speaking, all life on earth is just
  insects
• If we round off the fractions, there are no
  trees, no bacteria, no fish, viruses, birds,
  plants or mammals of any kind.
• If we need help feeling humble, mammals make up
  just 0.03 of the total number of species on the
  planet.
• Ask a friend what's the most popular
  microprocessor chip in the world. Chances are
  they'll answer "Pentium."
• The fact is, Pentium accounts for only about 2
  of the microprocessors sold around the world.
  Pentium is to microprocessors what viruses are to
  life on earth.
• The insects-the overwhelmingly dominant
  species--are the embedded microprocessors.
  They're the forgotten phylum that controls
  (approximately) 100 of the microprocessor
  kingdom.

69
Embedded market

• On a product dollar basis,
• Embedded microprocessor - Second largest
  functionStatic RAM - First largest function
• Unlike the standard processor, its embedded
  cousin is available from a wide variety of
  suppliers, with most architectures tailored to
  specific applications.

70
Embedded Processors

• The number of different embedded processors is
  growing, not shrinking.
• There are lots of embedded processors on the
  market because there needs to be a lot of
  embedded processors on the market.
• Intel dominates the desktop only because all
  computers are more or less the same. One
  processor can serve them all. That's not true of
  embedded systems at all.
• Lots of today's embedded microprocessors started
  out as high-end computer processors that didn't
  make it. MIPS, 68K, SPARC, ARM, PowerPC--they're
  all failed desktop processors that have wound up
  as embedded processors by default. None of these
  popular chip families started out as embedded
  processors.

71
In future

• Embedded processor technology, like many other
  functions, will find use in the
  Application-Specific Standard Product (ASSP)
  applications, as well as in customer-specific
  product designs.
• Embedded processor technology a represents the
  single most important function relative to
  next-generation product technology development.
• The most commonly embedded processor core will be
  the ARM architecture, which, product shipment
  wise, will account for almost two out of every
  three dollars. Other major embedded processor
  architectures include MIPS, ARC, and PowerPC,
  with the PowerPC sustaining the highest
  percentage revenue growth through 2006.Courtesy
  In-Stat/MDR -The high-tech market research firm

72
In future

• The communications segment will accounting for
  nearly three out of every four product dollars
  consumed through 2006.
• On the geographic side, it will be The Americas,
  followed by Europe, which will dominate future
  product consumption, accounting for an average of
  70 product dollar consumption through 2006.  

73
Conclusion

• CISC has
• a large, complex instruction set,
• variable-length instructions,
• a small number of general-purpose registers.
• RISC has
• a reduced instruction set
• fixed-length instructions,
• many general-purpose registers.
• Today, designers are producing a hybrid of the
  two design philosophies known as a
  complex/reduced instruction set computer. These
  computers combine characteristics such as
  variable-length instructions, few general-purpose
  registers, pipelining, and floating-point units.

74
Conclusion

• CISC Embedded Processors
• 68K
• X86
• PDP-11
• VAX
• RISC Embedded Processors
• Sparc
• AMD 29K
• MIPS
• SuperH
• PowerPC
• ARM

75
Conclusion

• CISC or RISC?
• Which is really appropriate for embedded systems?
  It depends on what characteristics you're
  shopping for.
• There are many hundreds of Embedded chips in
  production right now. Regardless of them being
  CISC or RISC, all of them have happy, healthy
  users who love them.

76
Thank you for your attention !

• Courtesy Jim Turley, editor in chief of
  Embedded Systems Programming