EEM 486: Computer Architecture

Transcription

1 EEM 486: Computer Architecture Lecture 1 Course Introduction and the Five Components of a Computer EEM 486 Course Information Instructor: Atakan Doğan (atdogan@anadolu.edu.tr) Office Hours: Anytime Materials: Text: Patterson and Hennessy, Computer Organization and Design: The Hardware/Software Interface, 3rd Edition. Lec 1.2

2 Grading Grading Midterm I: 20% Midterm II: 20% Homeworks+Labs 20% Final: 40% (30%Exam + 10%Labs) HW policy: return in 1 week; no late HW; no cheating Grading Guidelines AA: Others: FF: 0-40 Lec 1.3 What You Need to Know Logic design (EEM 232) Logical equations, schematic diagrams, components VHDL for Labs (EEM 334) Processor, memory, I/O Read and write in an assembly language (EEM 336) Lec 1.4

3 Introduction This course is all about how computers work But what do we mean by a computer? Different types: desktop, servers, embedded devices Different uses: automobiles, graphics, finance, genomics Different manufacturers: Intel, Apple, IBM, Microsoft, 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 perspective Lec 1.5 Why learn this stuff? You want to call yourself a computer scientist You want to build software that people use (need performance) You need to make a purchasing decision or offer expert advice Both Hardware and Software affect performance: Algorithm determines number of source-level statements Language/Compiler/Architecture determine machine instruction (Chapter 2 and 3) Processor/Memory determine how fast instructions are executed (Chapter 5, 6, and 7) Assessing and Understanding Performance in Chapter 4 Lec 1.6

4 Historical Perspective ENIAC built in World War II was the first general purpose computer Used for computing artillery firing tables 80 feet long by 8.5 feet high and several feet wide Each of the twenty 10 digit registers was 2 feet long Used 18,000 vacuum tubes Performed 1900 additions per second Lec 1.7 Technology Rapidly changing field: Moore s Law transistor capacity doubles every months Lec 1.8

5 Moore s Law IBM latest POWER5 has 276 million transistors Intel Dual-Core Xeon (P4- based Tulsa) w/ 16MB unified L3: billion, 2006 P4 Extreme Ed. 178 millions w/ 2MB L3 42 millions Core 2 Duo (Conroe) 291 millions, July ,25 0 Exponential growth Transistor count will be doubled every 18 months Lec 1.9 Integrated Circuits Capacity Lec 1.10

6 Feature Size We are currently at 0.09µm and moving towards 0.065µm Lec 1.11 Average Transistor Cost Per Year Lec 1.12

7 What is Computer Architecture? Computer Architecture = Instruction Set Architecture + Machine Organization Lec 1.13 A View of Computer Architecture Application Compiler Instr. Set Proc. Operating System Firmware I/O system Datapath & Control Digital Design Circuit Design Layout Instruction Set Architecture Coordination of many levels of abstraction Under a rapidly changing set of forces; technology, applications, OS, programming languages, etc. Design, Measurement, and Evaluation Lec 1.14

8 Processor Organization Capabilities & performance characteristics of principal functional units, e.g., Registers, ALU, Shifters, Logic Units,... Ways in which these components are interconnected Information flows between components Logic and means by which such information flow is controlled Choreography of FUs to realize the ISA Register Transfer Level (RTL) Description Lec 1.15 The Instruction Set: a Critical Interface software instruction set hardware Lec 1.16

9 Instruction Set Architecture High Level Language main() { int i,b,c,a[10]; for (i=0; i<10; i++) a[2] = b + c*i; } Compiler ISA lw r2, mem[r7] add r3, r4, r2 st r3, mem[r8] Assembler Lec 1.17 Instruction Set Architecture A very important abstraction interface between hardware and low-level software standardizes instructions, machine language bit patterns, etc. 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 Lec 1.18

10 Machine Organization: The Big Picture Since 1946 all computers have had 5 components Processor Control Memory Input Datapath Output Lec 1.19 Machine Organization Components: input (mouse, keyboard) output (display, printer) memory (disk drives, DRAM, SRAM, CD) network Our primary focus: the processor (datapath and control) implemented using millions of transistors impossible to understand by looking at each transisto Lec 1.20

11 A Typical PC System Architecture 21 Lec 1.21 A Typical PC Motherboard (D975XBX) 22 Lec 1.22

12 A Typical PC Motherboard (D975XBX) 23 Lec 1.23 How do computers work? Need to understand abstractions such as: Applications software Systems software Assembly Language Machine Language Architectural Issues: i.e., Caches, Virtual Memory, Pipelining Sequential logic, finite state machines Combinational logic, arithmetic circuits Boolean logic, 1s and 0s Transistors used to build logic gates (CMOS) Semiconductors/Silicon used to build transistors Properties of atoms, electrons, and quantum dynamics So much to learn! Lec 1.24

13 32 32=>34 signex bit ALU HI register (16x2 bits) Result[HI] 32 Multiplicand Register 32=>34 signex <<1 34 Arithmetic x2 MUX 34 Sub/Add 2 34 LoadMp Multi x2/x1 LO register (16x2 bits) Result[LO] ShiftAll 2 32 LO[1:0] ENC[2] ENC[1] ENC[0] Control Logic Where are We Going?? Input Multiplicand Input Multiplier Single/multicycle Datapaths Extra 2 bits LoadHI ClearHI LoadLO Prev LO[1] Booth Encoder "LO[0]" IFetch Dcd Exec Mem WB IFetch Dcd Exec Mem WB IFetch Dcd Exec Mem WB EEM 486 Performance 1000! 100! 10! 1! DRAM ! 1! ! 3! ! 5! 198 6! 198 7! 198 8! 198 9! 199 0! ! 2! ! 4! 199 5! ! 7! 199 8! 199 9! 200 0! Time Moore s Law CPU! Processor-Memory Performance Gap: (grows 50% / year) µproc 60%/yr. (2X/1.5yr) DRAM 9%/yr. (2X/10 yrs) Pipelining IFetch Dcd Exec Mem WB Memory Systems I/O Lec 1.25 Summary All computers consist of five components Processor: (1) datapath and (2) control (3) Memory (4) Input devices and (5) Output devices Not all memory are created equally Cache: fast (expensive) memory are placed closer to the processor Main memory: less expensive memory--we can have more Need to design against constraints of performance, power, area and cost Lec 1.26