Академический Документы
Профессиональный Документы
Культура Документы
Instructor
Office Times: W, 3-5 pm
Laxmi Narayan Bhuyan
Office: Engg.II Room 351
E-mail: bhuyan@cs.ucr.edu
Tel: (951) 827-2244
TA: Li Yan
Office Hours: Tuesday 1-3 pm
Cell: (951)823-3326
email: lyan@cs.ucr.edu
Grading
Grading: Based on Curve
Test1: 35 points
Test 2: 35 points
Project 1: 15 points
Project 2: 15 points
The project is based on Simple Scalar
simulator. See www.simplesacar.com
software
instruction set
hardware
Computer Architecture
A Quantitative Approach, Fifth Edition
Chapter 1
Fundamentals of Quantitative
Design and Analysis
Performance improvements:
Introduction
Computer Technology
Lightweight computers
Productivity-based managed/interpreted
programming languages
Move to multi-processor
Introduction
RISC
Introduction
Desktop Computing
Emphasis on price-performance
Servers
Classes of Computers
Classes of Computers
Embedded Computers
Emphasis: price
Classes of Computers
Parallelism
10
Vector architectures
Multimedia extensions
Graphics processor units
Classes of Computers
Flynns Taxonomy
No commercial implementation
Tightly-coupled MIMD
Loosely-coupled MIMD
11
12
Trends in Technology
Trends in Technology
13
Bandwidth or throughput
Trends in Technology
14
Trends in Technology
15
Feature size
Trends in Technology
16
Currentstatic x Voltage
Scales with number of transistors
To reduce: power gating
Static Power
17
Dynamic energy
Dynamic power
18
Intel 80386
consumed ~ 2 W
3.3 GHz Intel
Core i7 consumes
130 W
Heat must be
dissipated from
1.5 x 1.5 cm chip
This is the limit of
what can be
cooled by air
Power
19
Speedup of X relative to Y
Execution time
Response time
Throughput
Measuring Performance
Measuring Performance
Benchmarks
20
Principle of Locality
Principles
21
ExTimebefore
ExTimeafter
9/23/2004
F
S
]
1
=
[(1-F) +
F ]
S
22
Principles
23
Principles
24
Example
ALU
50%
1
Load
20%
2
Store
10%
2
Branch
20%
2
9/23/2004
25
Solution
Instr.
Fi
CPIi
CPIixFi
Ii
CPIi
CPIixIi
ALU
.5
.5
.5-X
.5-X
Load
.2
.4
.2-X
.4-2X
Store
.1
.2
.1
.2
Branch
.2
.4
.2
.6
2X
Reg/Mem
1.0
CPI=1.5
1-X
(1.7-X)/(1-X)
26
Toy benchmarks
Synthetic benchmarks
Kernels
Real programs
27
27