8/21/2011

Computer Architecture

Introduction
Ren Cumplido and Claudia Feregrino CCC INAOE Some material taken from: Vishwani D. Agrawal
Auburn University

Text book: D. A. Patterson and J. L. Hennessy, Computer Organization & Design, the Hardware/Software Interface, Fourth Edition, San Francisco, California: Morgan Kaufman Publishers, Inc., 2008, ISBN 978-0-12374493-7. Instructors: Ren Cumplido, Claudia Feregrino Assistant: Juan Manuel Campos Prerequisites:
Logic Design Basis of Assembly Language Programming

Course Organization

8/21/2011

Student Performance Evaluation

Three exams: 35% Homeworks: 15% (~6) Lab assignments: 15% (~5) CPU Design Project: 15% Class Presentation: 10% Participation: 10%

Class attendance in NOT optional

Course Objective
Learn what a digital computer contains and how it works. Learn design concepts of a modern computer. Gain design experience (through project). You Will Learn: How programs are translated into the machine language
And how the hardware executes them

The hardware/software interface What determines program performance

And how it can be improved

How hardware designers improve performance What is parallel processing

4

8/21/2011

The Concept of a Computer

User

Application software
Systems software Hardware
Operating system compiler assembler Programs user writes and runs

Application software Written in high-level language (HLL) System software Compiler: translates HLL code to machine code Operating System: service code Handling input/output Managing memory and storage Scheduling tasks & sharing resources Hardware Processor, memory, I/O controllers

Software
Compiler
Application software, a program in C:

Assembler
MIPS binary machine code:
00000000101000010000000000011000 00000000000110000001100000100001 10001100011000100000000000000000 10001100111100100000000000000100 10101100111100100000000000000000 10101100011000100000000000000100 00000011111000000000000000001000

MIPS compiler output, assembly language program:

swap (int v[ ], int k) swap; {int temp; temp = v[k]; v[k] = v[k+1]; v[k+1] = temp; }
Application software Systems software Hardware

muli add lw lw sw sw jr

$2, $2, $15, $16, $16, $15, $31

$5, 4 $4, $2 0 ($2) 4 ($2) 0 ($2) 4 ($2)

8/21/2011

Levels of Program Code

High-level language
Level of abstraction closer to problem domain Provides for productivity and portability

Assembly language
Textual representation of instructions

Hardware representation
Binary digits (bits) Encoded instructions and data

Fall 2011

The Hardware of a Computer

Control Datapath
Central Processing Unit (CPU) or processor

Input Memory Output

Application software Systems software Hardware

FIVE EASY PIECES

8

8/21/2011

Instruction Set Architecture (ISA)

A set of assembly language instructions (ISA) provides a link between software and hardware. Given an instruction set, software programmers and hardware engineers work more or less independently. ISA is designed to extract the most performance out of the available hardware technology.
Systems software Hardware

Software

Instruction set

Application software

Hardware

ISA
Defines registers Defines data transfer modes between registers, memory and I/O Types of ISA: RISC, CISC, VLIW, Superscalar Examples:
IBM370/X86/Pentium/K6 (CISC) PowerPC (Superscalar) Alpha (Superscalar) MIPS (RISC and Superscalar) Sparc (RISC), UltraSparc (Superscalar)
10

8/21/2011

Computer Architecture
Architecture: System attributes that have a direct impact on the logical execution of a program Architecture is visible to a programmer:
Instruction set Data representation I/O mechanisms Memory addressing
11

Computer Organization
Organization: Physical details that are transparent to a programmer, such as
Hardware implementation of an instruction Control signals Memory technology used

Example: System/370 architecture has been used in many IBM computers, which widely differ in their organization.
12

8/21/2011

How Do the Pieces Fit Together?

Application Operating System Compiler Memory system Firmware Instruction Set Architecture I/O system

Instr. Set Proc. Datapath & Control Digital Design Circuit Design

Coordination of many levels of abstraction Under a rapidly changing set of forces Design, measurement, and evaluation
Fall 2011 13

Research and Development of Continuing Interest

Instruction level parallelism (ILP) Multi-core processors and Chip multiprocessing (CMP) Energy efficiency and low power design Embedded systems Network processing

14

8/21/2011

The Computer Revolution

Progress in computer technology
Underpinned by Moores Law

Makes novel applications feasible

Computers in automobiles Cell phones Human genome project World Wide Web Search Engines

Computers are everywhere

Fall 2011 15

Classes of Computers
Desktop computers
General purpose, variety of software Subject to cost/performance tradeoff

Server computers
Network based High capacity, performance, reliability Range from small servers to building sized

Embedded computers
Hidden as components of systems Stringent power/performance/cost constraints
Fall 2011 16

8/21/2011

The Computer/Processor Market

Fall 2011

17

In 1965, Gordon Moore predicted that the number of transistors that can be integrated on a die would double every 18 to 24 months (i.e., grow exponentially with time). Amazingly visionary million transistor/chip barrier was crossed in the 1980s.
2300 transistors, 1 MHz clock (Intel 4004) - 1971 16 Million transistors (Ultra Sparc III) 42 Million transistors, 2 GHz clock (Intel Xeon) 2001 55 Million transistors, 3 GHz, 130nm technology, 250mm2 die (Intel Pentium 4) - 2004 140 Million transistor (HP PA-8500) 1000 Million Intel Xeon - 2009
Fall 2011 18

8/21/2011

Understanding Performance
Algorithm
Determines number of operations executed

Programming language, compiler, architecture

Determine number of machine instructions executed per operation

Processor and memory system

Determine how fast instructions are executed

I/O system (including OS)

Determines how fast I/O operations are executed
Fall 2011 19

Impacts of Advancing Technology

Processor
logic capacity: performance: increases about 30% per year 2x every 1.5 years
ClockCycle = 1/ClockRate 500 MHz ClockRate = 2 nsec ClockCycle 1 GHz ClockRate = 1 nsec ClockCycle 4 GHz ClockRate = 250 psec ClockCycle

Memory
DRAM capacity: memory speed: cost per bit: 4x every 3 years, now 2x every 2 years 1.5x every 10 years decreases about 25% per year increases about 60% per year
20

Disk
capacity:
Fall 2011

10

8/21/2011

Inside some embedded systems

Fall 2011

21

DSP Processors

Fall 2011

22

11

8/21/2011

Summary
A computer processes digital data. A user solves a problem by writing and/or running a program written in a high-level programming language like C. Inside computer, system programs called compiler and assembler break the user program down into assembly code (instruction set) and then into binary machine code. The machine code is processed by the 5-piece hardware (control unit, datapath, memory, input and output) to obtain the desired result.
23

12