Comorg 02

SC 2220 COMPUTER ORGANIZATION
9 of 584
Chapter 2 Computer Evolution & Performance
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
10 of 584
Objectives To know a brief history of the development of computer from their mechanical ancestors to present-day system.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
11 of 584
Computer Generations The first generation: Vacuum Tubes o ENIAC, IAS, UNIVAC The second generation: Transistors The third generation: Integrated Circuits (IC) Later generations: Large Scale Integration (LSI), Very Large Scale Integration (VLSI), and Ultra Large Scale Integration (ULSI)
Generation 1 2 3 4 5 6 Approximate Dates 19461957 19581964 19651971 19721977 19781991 1991Technology Vacuum tube Transistor Small and medium scale integration Large scale integration Very large scale integration Ultra large scale integration Typical Speed (operations per second) 40,000 200,000 1,000,000 10,000,000 100,000,000 1,000,000,000
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
12 of 584
The First Generation: Vacuum Tubes ENIAC stands for Electronic Numerical Integrator and Computer. It is the worlds first general-purpose electronic digital computer. It was designed by Eckert and Mauchly at University of Pennsylvania. It was used to compute range and trajectory tables for ranged weapons.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
13 of 584
ENIAC Eckert (19191995) and Mauchly (1908-1980) developed ENIAC (Electronic Numerical Integrator and Computer) at the Moore school of the University of Pennsylvania. It is the worlds first generalpurpose electronic digital computer. It was used to compute range and trajectory tables for ranged weapons.
PIYABUTE FUANGKHON UPDATE: 5/24/2013
14 of 584
ENIAC It is a decimal system (not binary system). It contains 20 accumulators, each capable of holding 10-digit decimal number. A ring of 10 vacuum tubes represents each digit. It is programmed manually by switches. 0123456789 10-digit decimal number requires 1 accumulator. It contains around 18,000 vacuum tubes. It computes 5,000 additions per second.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
15 of 584
von Neumann / Turing Machine It is a binary system. Von Neumann introduced stored program concept where main memory storing both program and data. Arithmetic and logic unit (ALU) operates on binary data. Control unit interprets and executes the instructions in memory. Input and output (I/O) equipment is operated by the control unit. Von Neumann and his colleagues (Princeton Institute for Advanced Studies) began the design of a new stored program computer referred to as the IAS computer. (Completed 1952)
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
16 of 584
Structure of von Neumann Machine
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
17 of 584
IAS Computer Details 1,000 40-bit words o Binary number o 2 20 bit instructions Set of registers (storage in CPU) o Memory Buffer Register (MBR) o Memory Address Register (MAR) o Instruction Register (IR) o Instruction Buffer Register (IBR) o Program Counter (PC) o Accumulator (AC) o Multiplier Quotient (MQ)
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
18 of 584
IAS Memory Formats
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
19 of 584
IAS Instruction Set Data transfer: moves data between memory and ALU registers or between two ALU registers. Unconditional branch: changes the sequence of instruction execution. Conditional branch: changes the sequence of instruction execution depending on a condition. Arithmetic: performs arithmetic and logic operations. Address modify: permits addresses to be computed in the ALU and then inserted into instructions stored in memory.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
20 of 584
IAS Operation
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
21 of 584
IAS Instruction Set
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
22 of 584
UNIVAC I & II In 1947, Eckert-Mauchly formed Eckert-Mauchly Computer Corporation and designed UNIVAC I (Universal Automatic Computer). It was commissioned by US Bureau of Census. It could compute matrix algebra, statistical problems, and logistical problems. The company finally became part of Sperry-Rand Corporation. Late 1950s, UNIVAC II was developed: o Higher performance (faster) than UNIVAC I. o Greater memory capacity than UNIVAC I.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
23 of 584
UNIVAC I
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
24 of 584
UNIVAC II
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
25 of 584
IBM IBM designed punched-card processing equipment. In 1953 - IBM 701 o IBMs first stored program computer. o Perform a scientific calculation. In 1955 - IBM 702 o Mainly used in business applications. Lead to 700/7000 series
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
26 of 584
Punched Card and Punched Card Reader
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
27 of 584
IBM 701
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
28 of 584
IBM 702
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
29 of 584
Example Members of the IBM700/7000 Series
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
30 of 584
IBM 7094 Configuration
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
31 of 584
The Second Generation: Transistors It was invented in 1947 at Bell Labs. It replaced vacuum tubes. It has smaller size. It has cheaper price. It produces less heat dissipation. It is a solid state device (made from silicon).
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
32 of 584
The Third Generation: Integrated Circuit In 1950s, electronic equipment was composed largely of discrete component (transistors, resistors, and capacitors). Later, more than 10,000 transistors were required! o Very expansive and slow manufacturing process. In 1958, integrated circuit was invented (silicon technology). Fabricate the circuit used in 2nd generation in a tiny piece of silicon rather than assemble discrete components made from separate pieces of silicon into the same circuit. Produce many transistors at the same time on a single wafer of silicon.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
33 of 584
Microelectronics
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
34 of 584
Integrated Circuit Data storage provided by memory cells Data processing provided by gates Data movement the paths among components are used to move data from memory to memory and from memory through gates to memory Control the paths among components can carry control signals A computer consists of gates, memory cells, and interconnections among these elements. The gates and memory cells are constructed of simple digital electronic components. Exploits the fact that such components as transistors, resistors, and conductors can be fabricated from a semiconductor such as silicon. Many transistors can be produced at the same time on a single wafer of silicon. Transistors can be connected with a processor metallization to form circuits.
35 of 584
Wafer, Chip, and Gate
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
36 of 584
Wafer
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
37 of 584
Chip and Package
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
38 of 584
IBM 360 Series In 1964, IBM announced the System/360. It is incompatible with older IBM machines (700/7000). It is the industrys first planned family of computers. o A program written for one model should be capable of being executed by another model in the series, with only difference in the time it takes to execute. The characteristics of a family: o Similar or identical instruction sets o Similar or identical operating system o Increased speed o Increased number of I/O ports o Increased memory size o Increased cost
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
39 of 584
Characteristics of the System/360 Family
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
40 of 584
Evolution of PDP-8
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
41 of 584
PDP-8 Bus Structure
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
42 of 584
Moores Law Gordon Moore - cofounder of Intel. A number of transistors on a chip will double every year. Since 1970s, a number of transistors doubles every 18 months. Cost of a chip has remained unchanged but the cost of computer logic and memory circuitry has fallen at a dramatic rate. Higher packing density means shorter electrical paths, increasing operating speed. Smaller size computer increases flexibility. There is a reduction in power and cooling requirements. Fewer inter-chip connections increases reliability.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
43 of 584
Growth in CPU Transistor Count
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
44 of 584
Later Generations: Semiconductor Memory Microprocessors
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
45 of 584
Semiconductor Memory Semiconductor memory is an electronic data storage device implemented on a semiconductor-based integrated circuit. In 1950s and 1960s, computer memory was constructed from tiny rings of ferromagnetic material. Each ring (called a core) represented either one or zero. Below figure is a core memory.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
46 of 584
Semiconductor Memory In 1970s, Fairchild produced the first relatively capacious semiconductor memory. A chip is smaller size, more reliable, and much faster than a core. Each chip could hold 256 bits of memory.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
47 of 584
Semiconductor Memory If the memory address consists of M bits, the address area consists of 2M addresses per chip. The possible amount of data stored in each chip is 1, 2, 4, 8, 16, 32, 64, 128, 256 and 512 bit, Kbit, Mbit, Gbit and Tbit.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
48 of 584
Microprocessors The density of elements on processor chips continued to rise o More and more elements were placed on each chip so that fewer and fewer chips were needed to construct a single computer processor 1971 Intel developed 4004 o First chip to contain all of the components of a CPU on a single chip o Birth of microprocessor 1972 Intel developed 8008 o First 8-bit microprocessor 1974 Intel developed 8080 o First general purpose microprocessor o Faster, has a richer instruction set, has a large addressing capability
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
49 of 584
1970s and 1980s Microprocessors
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
50 of 584
1990s and 2000s Microprocessors
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
51 of 584
Designing for Performance Pipelining: Processor moves data or instructions into a conceptual pipe with all stages of the pipe processing simultaneously Branch prediction: Processor looks a head in the software and predicts which branches are likely to be processed next. Data flow analysis: Processor analyzes which instructions are dependent on each others results, or data, to create an optimized schedule of instruction. Speculative execution: Processor executes instructions ahead of their actual appearance in the program execution, holding the result in temporary locations (keeping CPU busy).
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
52 of 584
Performance Balance Processor speed has been increased very quickly. Memory capacity has been increased very quickly. Memory speed lags behind processor speed!
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
53 of 584
Evolution of DRAM and Processor Characteristics
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
54 of 584
Typical I/O Device Data Rates
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
55 of 584
Solutions Increase number of bits retrieved at one time (data bus width). o Make DRAM wider rather than deeper Reduce frequency of memory access o Install multi-level cache memory Increase interconnection bandwidth o Front side bus speed: 66-400 MHz o Hierarchy of buses: System Bus/AGP/PCI/PCI-Express
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
56 of 584
Improvements in Chip Organization and Architecture Increase hardware speed of processor o Fundamentally due to shrinking logic gate size More gates, packed more tightly, increasing clock rate Propagation time for signals reduced Increase size and speed of caches o Dedicating part of processor chip Cache access times drop significantly Change processor organization and architecture o Increase effective speed of instruction execution o Parallelism
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
57 of 584
Problems with Clock Speed and Logic Density Power o Power density increases with density of logic and clock speed o Dissipating heat RC delay o Speed at which electrons flow limited by resistance and capacitance of metal wires connecting them o Delay increases as RC product increases o Wire interconnects thinner, increasing resistance o Wires closer together, increasing capacitance Memory latency o Memory speeds lag processor speeds
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
58 of 584
Processor Trends
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
59 of 584
Multicore The use of multiple processors on the same chip provides the potential to increase performance without increasing the clock rate. Strategy is to use two simpler processors on the chip rather than one more complex processor. With two processors, larger caches are justified. As caches became larger, it made performance sense to create two and then three levels of cache on a chip.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
60 of 584
Layout of the Quad Core i7 (i7-3770K) Microprocessor Chip
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
61 of 584
Many Integrated Core (MIC) Leap in performance as well as the challenges in developing software to exploit such a large number of cores The multicore and MIC strategy involves a homogeneous collection of general purpose processors on a single chip Graphics Processing Unit (GPU) Core designed to perform parallel operations on graphics data Traditionally found on a plug-in graphics card, it is used to encode and render 2D and 3D graphics as well as process video Used as vector processors for a variety of applications that require repetitive computations
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
62 of 584
x86 Evolution 8080 o First general purpose microprocessor o 8-bit machine with an 8-bit data path to memory o Used in the first personal computer (Altair) 8086 o 16-bit machine o Used an instruction cache, or queue o First appearance of the x86 architecture 8088 o used in IBMs first personal computer 80286 o Enabled addressing a 16-MByte memory instead of just 1 MByte 80386 o Intels first 32-bit machine o First Intel processor to support multitasking
63 of 584
x86 Evolution (continue) 80486 o More sophisticated cache technology and instruction pipelining o Built-in math coprocessor Pentium o Superscalar o Multiple instructions executed in parallel Pentium Pro o Increased superscalar organization o Aggressive register renaming o Branch prediction o Data flow analysis o Speculative execution Pentium II o MMX technology o Designed specifically to process video, audio, and graphics data
64 of 584
x86 Evolution (continue) Pentium III o Additional floating-point instructions to support 3D graphics software Pentium 4 o Includes additional floating-point and other enhancements for multimedia Core o First Intel x86 microprocessor with a dual core, referring to the implementation of two processors on a single chip Core 2 o Extends the architecture to 64 bits o Recent Core offerings have up to 10 processors per chip
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
65 of 584
8080
8086
8088
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
66 of 584
80286
80386 DX
80386 SX
80486 SX
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
67 of 584
80486DX
Pentium
Pentium Pro
Pentium II
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
68 of 584
Pentium III
Pentium 4
Core 2 Duo
Core i3
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
69 of 584
Core i5
Core i7
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
70 of 584
Embedded Systems A combination of computer hardware and software, and perhaps additional mechanical or other parts, designed to perform a dedicated function. In many cases, embedded systems are part of a larger system or product, as in the case of an antilock braking system in a car.
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
71 of 584
Examples of Embedded Systems and Their Markets

Market Embedded Device
Automotive
Consumer electronics
Industrial control
Medical
Office automation
Ignition system Engine control Brake system Digital and analog televisions Set-top boxes (DVDs, VCRs, Cable boxes) Personal digital assistants (PDAs) Kitchen appliances (refrigerators, toasters, microwave ovens) Automobiles Toys/games Telephones/cell phones/pagers Cameras Global positioning systems Robotics and controls systems for manufacturing Sensors Infusion pumps Dialysis machines Prosthetic devices Cardiac monitors Fax machine Photocopier Printers Monitors Scanners
UPDATE: 5/24/2013
PIYABUTE FUANGKHON
72 of 584
Embedded Systems : Requirements and Constraints Small to large systems, implying different cost constraints and different needs for optimization and reuse Relaxed to very strict requirements and combinations of different quality requirements with respect to safety, reliability, real-time and flexibility Short to long life times Different environmental conditions in terms of radiation, vibrations, and humidity Different application characteristics resulting in static versus dynamic loads, slow to fast speed, compute versus interface intensive tasks, and/or combinations thereof Different models of computation ranging from discrete event systems to hybrid systems
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
73 of 584
Possible Organization of an Embedded Systems
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
74 of 584
Acorn RISC Machine (ARM) Family of RISC-based microprocessors and microcontrollers Designs microprocessor and multicore architectures and licenses them to manufacturers Chips are high-speed processors that are known for their small die size and low power requirements Widely used in PDAs and other handheld devices Chips are the processors in iPod and iPhone devices Most widely used embedded processor architecture Most widely used processor architecture of any kind
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
75 of 584
ARM Evolution
Family ARM1 ARM2 Notable Features 32-bit RISC Multiply and swap instructions; Integrated memory management unit, graphics and I/O processor First use of processor cache First to support 32-bit addresses; floatingpoint unit Integrated SoC 5-stage pipeline; static branch prediction Enhanced DSP instructions 6-stage pipeline 9-stage pipeline 13-stage superscalar pipeline Applications processor; 7-stage pipeline None None Cache Typical MIPS @ MHz 7 MIPS @ 12 MHz
ARM3 ARM6 ARM7 ARM8 ARM9 ARM9E ARM10E ARM11 Cortex XScale
4 KB unified 4 KB unified 8 KB unified 8 KB unified 16 KB/16 KB 16 KB/16 KB 32 KB/32 KB Variable Variable 32 KB/32 KB L1 512 KB L2
12 MIPS @ 25 MHz 28 MIPS @ 33 MHz 60 MIPS @ 60 MHz 84 MIPS @ 72 MHz 300 MIPS @ 300 MHz 220 MIPS @ 200 MHz 740 MIPS @ 665 MHz 2000 MIPS @ 1 GHz 1000 MIPS @ 1.25 GHz
DSP = digital signal processor SoC = system on a chip
PIYABUTE FUANGKHON
UPDATE: 5/24/2013
76 of 584
ARM Design Categories ARM processors are designed to meet the needs of three system categories: o Secure applications Smart cards, SIM cards, and payment terminals o Embedded real-time systems Systems for storage, automotive body and power-train, industrial, and networking applications o Application platforms Devices running open operating systems including Linux, Palm OS, Symbian OS, and Windows CE in wireless, consumer entertainment and digital imaging applications
PIYABUTE FUANGKHON
UPDATE: 5/24/2013

Comorg 02

Transféré par

Informations du document

Titre original

Copyright

Formats disponibles

Partager ce document

Partager ou intégrer le document

Options de partage

Avez-vous trouvé ce document utile ?

Ce contenu est-il inapproprié ?

Droits d'auteur :

Formats disponibles

Comorg 02

Transféré par

Droits d'auteur :

Formats disponibles

SC 2220 COMPUTER ORGANIZATION

Chapter 2 Computer Evolution & Performance

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

Structure of von Neumann Machine

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

IAS Memory Formats

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

IAS Instruction Set

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

Punched Card and Punched Card Reader

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

Example Members of the IBM700/7000 Series

SC 2220 COMPUTER ORGANIZATION

IBM 7094 Configuration

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

Wafer, Chip, and Gate

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

Chip and Package

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

Characteristics of the System/360 Family

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

PDP-8 Bus Structure

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

Growth in CPU Transistor Count

SC 2220 COMPUTER ORGANIZATION

Later Generations: Semiconductor Memory Microprocessors

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

1970s and 1980s Microprocessors

SC 2220 COMPUTER ORGANIZATION

1990s and 2000s Microprocessors

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

SC 2220 COMPUTER ORGANIZATION

Evolution of DRAM and Processor Characteristics

SC 2220 COMPUTER ORGANIZATION

Typical I/O Device Data Rates