2. Computer Organization Lecture Set – 01 Course Overview & Chapter 1 Huei-Yung Lin

3. CCUEE Computer Organization 2 Textbooks Required:  “Computer Organization and Design”, 3 rd Ed. Patterson & Hennessy  (No translation yet!) References:  “Computer Architecture: A Quantitative Approach”, 3 rd Ed. Hennessy & Patterson  MIPS Assembly Language Programming, http://www.eecs.harvard.edu/~ellard/Courses/cs50-asm.pdf http://www.eecs.harvard.edu/~ellard/Courses/cs50-asm.pdf Chapter 2: MIPS Tutorial Chapter 4: The MIPS R2000 Instruction Set  Programmed Instruction to MIPS Assembly Language, http://chortle.ccsu.edu/AssemblyTutorial/TutorialContents.html http://chortle.ccsu.edu/AssemblyTutorial/TutorialContents.html Chapter 26 — Simple Subroutine Linkage. Chapter 27 — Stack-based Linkage Convention

4. CCUEE Computer Organization 3 Grading Grading Policy (total score : 110):  2 Midterms: 40% (each with 20%)  Final: 30%  Home work 20%: NO LATE home work  Participation & Quiz: 20% Please note if you miss three quizzes, you will get 0 point from this category. Further, you will pay the extra penalty (5 points of the total score) for each missing quiz when you are absent over three quizzes. No makeup exams!

5. CCUEE Computer Organization 4 Course Outline Computer Abstractions and Technology (2 lectures) Instructions: Language of the Computer (6 lectures) Midterm #1 Arithmetic for Computers (6 lectures) Assessing and Understanding Performance (2 lectures) The Processor: Datapath and Control (3 lectures) Midterm #2 Enhancing Performance with Pipelining (5 lectures) Large and Fast: Exploiting Memory Hierarchy (3 lectures) Storage, Networks, and Other Peripherals (1 lectures) Final

6. CCUEE Computer Organization 5 Introduction This course is all about how computers work But what do we mean by a computer?  Different types: desktops, servers, embedded devices  Different uses: automobiles, graphics, finance, genomics, …  Different manufacturers: Intel, Apple, IBM, Sun, …  Different underlying technologies and different costs! Analogy: consider a course on “automotive vehicles”  Many similarities from vehicle to vehicle (e.g., wheels)  Huge differences from vehicle to vehicle (e.g., gas vs. electric) Best way to learn:  Focus on a specific instance and learn how it works  While learning general principles and historical perspectives

7. CCUEE Computer Organization 6 Why Learn This Stuff? You want to call yourself a “computer scientist” You want to build software people use (need performance) You need to make a purchasing decision or offer “expert” advice

8. CCUEE Computer Organization 7 Overview Both hardware and software affect program performance:  Algorithm determines number of source-level statements Determines both the count of source level statements and I/O operations  Language/Compiler/Architecture determine machine instructions (Chapters 2 and 3) Determine the number of machine instructions  Processor/Memory determine how fast instructions are executed (Chapters 5, 6 and 7) Determines how fast instructions are executed  I/O system (hardware and OS) (Chapter 8) Determines how fast I/O operations are executed Accessing and understand performance in Chapter 4

9. CCUEE Computer Organization 8 Computer Systems Overview  Technology Trends Instruction Sets (and Software) Logic and Arithmetic Performance Processor Implementation Memory Systems Input/Output Roadmap for the Term: Major Topics

10. CCUEE Computer Organization 9 Classes of Computer Systems Embedded Desktop Server Image sources: Dell Computer www.dell.com Rackable Systems www.rackablecom Apple Computer www.apple.com

11. CCUEE Computer Organization 10 Desktop Computer Systems For “General-Purpose” Use  Word-Processing, Web surfing, Multimedia, etc.  Computation and Programming What’s in the box  Microprocessor  Memory - Synchronous DRAM  Hard disk(s), CDROM/DVD, etc.  I/O - mouse, keyboard, video card, monitor, network, etc. Important Issues:  Performance - how fast is “fast enough”?  Basic capabilities (and expandability)  Cost

12. CCUEE Computer Organization 11 Server Computer Systems Large-Scale Services  File storage  Computation (e.g., supercomputers)  Transaction Processing, Web What’s in the Box(es)  Microprocessor(s)  Hard disks  Network Interface(s) Important issues:  Performance  Reliability, availability  Cost One Rack-Mount PC Unit (Google uses ~ 10,000)

13. CCUEE Computer Organization 12 Embedded Computer Systems Computer as part of larger system  Consumer electronics, appliances  Networking, telecommunications  Automotive / aircraft control What’s in the box  Microcontroller / Microprocessor  Memory: RAM, ROM; Disk  Special-purpose I/O (including analog stuff) Important issues  Cost, Power Consumption  Performance (against real-time constraints)  Reliability and Safety

14. CCUEE Computer Organization 13 “Five classic components” Processor Computer Control (“brain”) Datapath (“brawn”) Memory (where programs, data live when running) Devices Input Output Keyboard, Mouse Display, Printer Disk (where programs, data live when not running) Computer System Organization

15. CCUEE Computer Organization 14 Executing Programs - the “fetch/execute” cycle  Processor fetches instruction from memory  Processor executes “machine language” instruction Processor Control Datapath 1001010010110000 0010100101010001 1111011101100110 1001010010110000 Memory 1111011101100110 1001010010110000 next instr OK, but how do we write useful programs using these instructions? Load Data Perform Calculation Store Results Address Instruction Computer System Operation

16. CCUEE Computer Organization 15 55EF Abstractions in Computer Systems Designers use abstraction to manage complexity  Focus on pertinent information  Suppress unnecessary detail Example: Auto controls  Well-understood interface (inputs, outputs)  Details suppressed

17. CCUEE Computer Organization 16 Abstractions in Computer Systems Coordination of many levels of abstraction Computer Organization I/O systemProcessor Compiler Operating System (Mac OS X) Application (ex: browser) Digital Design Circuit Design Instruction Set Architecture Datapath & Control transistors Memory Hardware Software Assembler

18. CCUEE Computer Organization 17 Machine Language 00000000001000100100000000100000 High-Level Language (C) c = a + b; Assembly Language add R8,R1,R2 AssemblerCompiler Software Abstractions - Languages

19. CCUEE Computer Organization 18 Operating system  Insulates programmer from low-level details Manages system resources Manages file system  Coordinates operation of multiple programs  Protects from system from damage by user programs (accidental or malicious)  Programs interact with OS through system calls Libraries  Provide programmer access to high-level “primitives”  Programs access through well-defined interface (API) Software Abstractions - System Software

20. CCUEE Computer Organization 19 The most important abstraction of computer design Logic - gates, state machines, etc. Circuit - transistors, etc. Layout - mask patterns, etc. Hardware ProcessorI/O System Software Compiler Application Programs Operating System Application Instruction Set Architecture Interface between SW & HW Instruction Set Architecture (ISA) - The Hardware-Software Interface

21. CCUEE Computer Organization 20 Instruction Set Architecture Also called architecture A very important abstraction  Interface between hardware and low-level software  Includes instructions, registers, memory access, I/O and so on  Advantage: different implementations of the same architecture  Disadvantage: sometimes prevents using new innovations True or False: Binary compatibility is extraordinarily important? Modern instruction set architectures:  IA-32, PowerPC, MIPS, SPARC, ARM, and others

22. CCUEE Computer Organization 21 Architecture: features visible to programmer  Registers and memory model  Data types  Instructions Organization: system implementation  Processor design: Datapath, Control, “microarchitecture”  System design: Processor + Memory, I/O Architecture vs. Organization

23. CCUEE Computer Organization 22 Memory (Max. 4GB) 0x00000000 0x00000004 0x00000008 0x0000000C 0x00000010 0x00000014 0x00000018 0x0000001C 0xfffffffc 32 bits 32 General Purpose Registers R0 R1 R2 R30 R31 PC = 0x0000001C 32 bits Registers 32 oprsrtoffset oprsrtrdfunctshamt opaddress Instruction Formats Example Architecture: MIPS

24. CCUEE Computer Organization 23 Top 5 Reasons to Study MIPS It’s in the book It’s used in many applications Learning its architecture and implementation exposes you to important concepts It’s relatively simple and easy to implement (compared to other architectures) Ideas presented using MIPS generalize to other architectures (even the 80x86!)

25. CCUEE Computer Organization 24 Overview of Physical Implementations The hardware out of which we make systems Integrated Circuits (ICs)  Combinational logic circuits, memory elements, analog interfaces Printed Circuit Boards (PCB)  Substrate for ICs and interconnection, distribution of CLK, Vdd, and GND signals, heat dissipation Power Supplies  Converts line AC voltage to regulated DC low voltage levels. Chassis (rack, card case,...)  Holds boards, power supply, provides physical interface to user or other systems Connectors and Cables

26. CCUEE Computer Organization 25 Under the Hood: A Desktop PC Display (CRT or LCD) Keyboard, Mouse “The Box”  Power Supply  Motherboard (see next slide) Memory Graphics card Standard bus card slots (e.g. PCI) Standard I/O connectors (e.g. USB, Parallel Port, etc) Disks, CDRW, etc.

27. CCUEE Computer Organization 26 Organization of a Desktop PC System Cotroller (North Bridge) DRAM Memory (DIMMs) CPU AGP Graphics Card AGP (Graphics) Bus Memory Bus PCI Backplane Bus Peripheral Bus Cotroller (South Bridge) LANSCSI ISA Bus* USB Dual EIDE BIOS ROM

28. CCUEE Computer Organization 27 Typical Motherboard (Pentium III) Rear Panel Conn. Processor Memory N. Bridge S. Bridge IDE Disk Conn. AGP BIOS ROM Floppy Conn.Power Conn. PCI Cards

29. CCUEE Computer Organization 28 Explanations (I) Northbridge is the chip or chips that connect a CPU to memory, the PCI bus, Level 2 cache and AGP activities. Southbridge is the chip that controls all of the computers I/O functions, such as USB, audio, serial, the system BIOS, the ISA bus, the interrupt controller and the IDE channels. Intelligent Drive Electronics (IDE) interface is an interface for mass storage devices, in which the controller is integrated into the disk or CD-ROM drive.

30. CCUEE Computer Organization 29 Explanations (II) Accelerated Graphics Port: an interface specification developed by Intel Corporation.  AGP is based on PCI, but is designed especially for the throughput demands of 3-D graphics Peripheral Component Interconnect: a local bus standard developed by Intel Corporation.  Most modern PCs include a PCI bus in addition to a more general ISA expansion bus. Industry Standard Architecture bus, the bus architecture used in the IBM PC/XT and PC/AT.

31. CCUEE Computer Organization 30 BIOS (basic input/output system) A built-in software On PCs, the BIOS contains all the code required to control the keyboard, display screen, disk drives, serial communications, and a number of miscellaneous functions. The BIOS is typically placed in a ROM chip that comes with the computer (it is often called a ROM BIOS). This ensures that the BIOS will always be available and will not be damaged by disk failures.

32. CCUEE Computer Organization 31 Source: EE Times, www.eetimes.com Under the Hood: Apple iPod

33. CCUEE Computer Organization 32 Computer Systems Overview Technology Trends Instruction Sets (and Software) Logic and Arithmetic Performance Processor Implementation Memory Systems Input/Output Roadmap for the Term: Major Topics

34. CCUEE Computer Organization 33 Computer Systems Overview Types of Computer Systems Abstractions used in Computer Systems Architecture vs. Organization Common Architectures “Under the Hood” - chips and systems

35. CCUEE Computer Organization 34 Technology Trends Historical Notes Current Technology (CMOS VLSI) Trends (Moore’s Law) Image Source: Intel Corporation www.intel.com

36. CCUEE Computer Organization 35 Instruction Sets (and Software) General principles of instruction set design The MIPS instruction set Software concerns: procedures, stacks, etc. oprsrtoffset oprsrtrdfunctshamt opaddress

37. CCUEE Computer Organization 36 Logic & Arithmetic Quick review: binary numbers and arithmetic Adder & ALUs; multiplication & division Floating Point A B F(A,B) Operation Select ALU

38. CCUEE Computer Organization 37 Performance Response Time vs. Throughput Measuring performance using individual programs Combining measurements Benchmarks

39. CCUEE Computer Organization 38 Processor Implementation Basic implementation  Single-Cycle  Multicycle Pipelined implementation Advanced techniques

40. CCUEE Computer Organization 39 Memory Systems Memory Technology Overview Memory Hierarchy  Cache Memories - making access faster  Virtual Memory - making memory larger using disk RegistersCache Memory ProcessorDisk

41. CCUEE Computer Organization 40 Input/Output I/O Overview Impact of I/O on Performance Buses Interfacing Image Source: Seagate Technolgy LLC www.seagate.com

42. CCUEE Computer Organization 41 Roadmap for the Term: Major Topics Computer Systems Overview Technology Trends  Instruction Sets (and Software) Logic and Arithmetic Performance Processor Implementation Memory Systems Input/Output

43. CCUEE Computer Organization 42 Outline - Technology Trends Brief History of Computer Technology  Today’s Technology: VLSI CMOS VLSI Technology Trends

44. CCUEE Computer Organization 43 1940s-50s - Vacuum Tubes 1950s-60s - Discrete Transistors 1960s-70s - Discrete ICs (e.g., TTL) 1970s-present - LSI and VLSI microprocessors A Brief History of Computer Technology

45. CCUEE Computer Organization 44 Computer History - 1940s-1960s ENIAC - 1940s (Vacuum Tubes) IBM 360 - 1960s (Transistors)

46. CCUEE Computer Organization 45 Computer History - 1970s DEC VAX 11/780 - 1970s (Discrete IC’s) Intel 4004 - 1970s (First Microprocessor)

47. CCUEE Computer Organization 46 Computer History - 1970s MOS Technology 6502 Apple II Computer

48. CCUEE Computer Organization 47 Computer History - 1980s Intel 8088 (LSI Microprocessor) Original IBM PC Images: Intel Corporation www.intel.com pcbiography members.tripod.com/pcmuseum

49. CCUEE Computer Organization 48 Outline - Technology Trends Brief History of Computer Technology Today’s Technology: VLSI  VLSI Technology Trends

50. CCUEE Computer Organization 49 Today: VLSI Microprocessors PowerPC 7400 (G4) 6.5M transistors / 450MHz / 8-10W L=0.15µm Pentium® III 28M transistors / 733MHz-1Gz / 13-26W L=0.25µm shrunk to L=0.18µm

51. CCUEE Computer Organization 50 Today: VLSI Microprocessors Pentium® 4 42M transistors / 1.3-1.8GHz 49-55W L=180nm Pentium® 4 “Northwood” 55M transistors / 2-2.5GHz 55W L=130nm Area=131mm 2 Process Shrinks Pentium® 4 “Prescott” 125M transistors / 2.8-3.4GHz 115W L=90nm Area=112mm 2

52. CCUEE Computer Organization 51 Today: VLSI Microprocessors PowerPC® 940 (G5) 58M transistors / 2GHz / 97W L=130nm Area=118mm 2 Image courtesy International Business Machines All Rights Reserved Intel Itanium® 2 410M transistors / 1.3GHz / 130W L=130nm Area=374mm 2 Image source: Intel Corporation www.intel.com

53. CCUEE Computer Organization 52 VLSI Technology Overview Fabrication of multiple transistors on a chip Dominant technology: CMOS Other technologies:  Bipolar (e.g., TTL)  Bi-CMOS - hybrid Bipolar, CMOS  GaAs - Gallium Arsenide (for high speed)  Si-Ge - Silicon Germanium (for high speed, RF)

54. CCUEE Computer Organization 53 2002: L=130nm 2003: L=90nm 2005: L=65nm? Transistor length L shrinks over time! VLSI Technology - CMOS Transistors

55. CCUEE Computer Organization 54 NAND NOR What logic functions do these gates perform? VLSI Technology - CMOS Logic Gates

56. CCUEE Computer Organization 55 VLSI Processing (Fig. 1-14)

57. CCUEE Computer Organization 56 Integrated Circuits (2003 State-of-the-Art) Primarily Crystalline Silicon 1mm - 25mm on a side 2003 - feature size ~ 0.13 µ m = 0.13 x 10 -6 m 100 - 400M transistors (25 - 100M “ logic gates") 3 - 10 conductive layers “ CMOS ” (complementary metal oxide semiconductor) - most common. Package provides:  spreading of chip-level signal paths to board- level  heat dissipation. Ceramic or plastic with gold wires. Chip in Package Bare Die

58. CCUEE Computer Organization 57 Printed Circuit Boards (PCB) Fiberglass or ceramic 1-20 conductive layers 1-20in on a side IC packages are soldered down

59. CCUEE Computer Organization 58 VLSI Design Tradeoffs Cost - related to chip size  Amount of logic  Current technology  Non recurring engineering (NRE) cost vs. unit cost Performance  Clock speed  Implementation  Application Power consumption  Power supply voltage  Clock speed

60. CCUEE Computer Organization 59 Outline - Technology Trends Brief History of Computer Technology Today’s Technology: VLSI VLSI Technology Trends 

61. CCUEE Computer Organization 60 VLSI Trends: Moore ’ s Law In 1965, Gordon Moore predicted that transistors would continue to shrink, allowing:  Doubled transistor density every 24 months  Doubled performance every 18 months History has proven Moore right But, is the end in sight?  Physical limitations  Economic limitations I’m smiling because I was right! BUT… No exponential is forever! Gordon Moore Intel Co-Founder and Chairmain Emeritus Image source: Intel Corporation www.intel.com

62. CCUEE Computer Organization 61 Source: http://www.intel.com/pressroom/kits/quickreffam.htm, EE Times Microprocessor Trends (Intel)

63. CCUEE Computer Organization 62 Technology Trends: Microprocessor Complexity 2X transistors/Chip Every 1.5 years Called “Moore’s Law” Alpha 21264: 15 million Pentium Pro: 5.5 million PowerPC 620: 6.9 million Alpha 21164: 9.3 million Sparc Ultra: 5.2 million Moore’s Law Athlon (K7): 22 Million Itanium 2: 410 Million

64. CCUEE Computer Organization 63 Technology Trends: Processor Performance 1.54X/yr Intel P4 2000 MHz (Fall 2001) year Performance measure

65. CCUEE Computer Organization 64 Technology Trends: Memory Capacity (Single Chip DRAM) year size (Mbit) 19800.0625 19830.25 19861 19894 199216 199664 1998128 2000256 2002512

66. CCUEE Computer Organization 65 Summary - Technology Trends Processor  Logic capacityincreases ~ 30% per year  Clock frequencyincreases ~ 20% per year  Cost per functiondecreases ~20% per year Memory  DRAM capacity: increases ~ 60% per year (4x every 3 years)  Speed: increases ~ 10% per year  Cost per bit: decreases ~25% per year Disk  Storage capacityincreases ~ 60% per year

67. CCUEE Computer Organization 66 Summary 5 classic components of all computers Control Datapath Memory Input Output processor Two key technologies for modern processors  Compilers  Silicon Two key ideas for  Exploiting parallelism via pipelining  Exploiting locality of access via caches

68. CCUEE Computer Organization 67 Computer Systems Overview Technology Trends Instruction Sets (and Software)  Logic & Arithmetic Performance Processor Implementation Memory systems Input/Output Roadmap for the Term: Major Topics

69. CCUEE Computer Organization 68 References Portions of these slides are derived from:  Textbook figures © 1998 Morgan Kaufmann Publishers all rights reserved  Tod Amon's COD2e Slides © 1998 Morgan Kaufmann Publishers all rights reserved  Dave Patterson’s CS 152 Slides – Fall 1997 © UCB  Rob Rutenbar’s 18-347 Slides – Fall 1999 CMU  John Nestor’s ECE 313 Slides – Fall 2004 LC  T.S. Chang’s DEE 1050 Slides – Fall 2004 NCTU  Other sources as noted