4300 COMP Computer Architecture
Performance Measurement
Dr. Xiao Qin
Auburn University
http://www.eng.auburn.edu/~xqin
[e-mail]
Fall, 2010
1
What is Computer Architecture ?
Application (Netscape)
Software
Hardware
Operating System
Compiler
(Unix;
Assembler Windows 9x)
Processor Memory I/O system
Instruction Set
Architecture
Datapath & Control
Digital Design
Circuit Design
transistors, IC layout
comp 4300
Key Idea: levels of abstraction
2
hide unnecessary implementation details
helps us cope with enormous complexity of
real systems
Computer Architectures
Changing Definition
1950s to 1960s Computer Architecture Course:
Computer Arithmetic
1970s to mid 1980s Computer Architecture Course:
Instruction Set Design, especially ISA appropriate for
compilers
1990s to 2000s Computer Architecture Course:
Design of CPU, memory system, I/O system,
Multiprocessors, Networks
2010s: Computer Architecture Course:
Self adapting systems? Self organizing structures?
Green Architecture? DNA Systems/Quantum
Computing?
3
COMP 4300 Course Focus
Understanding the design techniques, machine
structures, technology factors, evaluation methods
that will determine the form of computers in 21st
Century
Technology
Parallelism
Applications
Computer Architecture:
Instruction Set Design
Instruction-level Parallelism
Memory Hierarchy Design
History
Operating
Systems
4
Programming
Languages
Interface Design
(ISA)
Compilers
Measurement & Evaluation
Computer Engineering Methodology
Implementation
Complexity
Evaluate Existing
Systems for
Systems
Bottlenecks
Bottlenecks
Technology
Trends
Implement Next
Generation System
Benchmarks
Page 35.
Simulate New
Designs and
Organizations
Workloads
Architecture design is an iterative process: Searching the space
of possible designs at all levels of computer systems
5
Machine Organization
5 classic components of any computer
Personal Computer
Computer
Processor
(CPU)
(active)
Control
(brain)
Datapath
(brawn)
Memory
(passive)
(where
programs,
& data
live when
running)
Devices
Input
Output
The components of every computer, past and present, belong to one of
these five categories
6
Keyboard,
Mouse
Disk
(where
programs,
& data
live when
not running)
Display,
Printer
Performance Measurement
Outline
Performance Metrics: How do we conclude that
System-A is better than System-B?
Measuring CPU time
Amdahls Law: Relates total speedup of a
system to the speedup of some portions of that
system.
7
Importance of Measurement
Architecture design is an
iterative process:
Search the possible design space
Make selections
Evaluate the selections made
Good measurement tools
are required to accurately
evaluate the selection.
Cost /
Performance
Analysis
Good Ideas
Bad Ideas
8
Mediocre Ideas
Two notions of performance
Plane
DC to Paris
Speed
Passengers
Throughput
(pmph)
Boeing 747
6.5 hours
610 mph
470
286,700
BAD/Sud
Concodre
3 hours
1350 mph
132
178,200
Which has higher performance?
1. Time to deliver 1 passenger?
2. Time to deliver 400 passengers?
9
Example of Response Time v.
Throughput
Flying Time: Concorde Boeing vs. 747?
Concord is 6.5 hours / 3 hours
= 2.2 times as fast (response time,)
Throughput: Boeing vs. Concorde?
Boeing 747: 286,700 p-mph / 178,200
p-mph = 1.6 times as fast (throughput, )
Time to do the task (Interest to users)
execution time, response time, latency, etc.
Tasks per day, hour, week, sec, (Interest to system
administrators)
throughput, bandwidth, etc.
10
Performance
Definitions
We are primarily concerned with response time
To maximize performance, we must minimize
response time for some task:
Performancex > Performancey
response_timex < response_timey
"X is n times as fast as Y" means
Performancex = n X Performancey
11
What is Execution Time?
Definition 1:
Total time to complete a task, including disk accesses,
memory accesses, I/O activities, operating system
overhead, ...
wall-clock time, response time, or elapsed time
Definition 2: measure time processor is working on
your
program only (since multiple processes running at
same time)
CPU execution time or CPU time
Often divided into system CPU time (in OS) and user CPU
time (in user program)
How to Measure
Time?
User actual elapsed time to complete particular
task is only true basis for comparison
sum of I/O time, User + System CPU, time spent
on other tasks, boot time, etc.
alternatives may mislead!
CPU designer want measure relating to how fast
processor hardware can perform basic functions
(CPU execution time)
Measuring CPU
Most computers are constructed using a clock that
time
runs at a constant rate and determines when
events take place in the hardware
These discrete time intervals called
clock cycles
Length of clock period: clock cycle time
(e.g., 2 nanoseconds or 2 ns) and clock rate (e.g., 500
megahertz, or 500 MHz), which is the inverse of the
clock period;
1
2 10 Sec.
-9
= 500MHz
Execution time = # Clock cycles X
clock cycle time
Example of Measuring CPU
CPU time
CPU time = Seconds = Instructions x Cycles x Seconds
= Seconds = Instructions x Cycles x Seconds
tPime Instruction Cycle
Program
rogram
Program
Program
Instruction
Cycle
If a computer has a clock rate of 50
MHz, how long does it take to execute a
program with 1,000 instructions, if the
CPI for the program is 3.5?
Using the equation
CPU time = Instruction count x CPI / clock
rate
gives
15
6
CPU time = 1000 x 3.5 / (50 x 10 )
Example of Measuring CPU
time
If a computers clock rate increases from 200 MHz
to 250 MHz and the other factors remain the
same, how many times faster will the computer
bCPU time old
e?
clock rate new
250 MHz
------------------- = ---------------------- = ---------------- = 1.25
CPU time new
clock rate old
200 MHZ
What simplifying assumptions did we make?
16
Performance
Two computers M1 xamplethe same instruction
E and M2 with
set.
For a given program, we have
Clock rate
(MHz)
CPI
M1
50
2.8
M2
75
3.2
How many times faster is M2 than M1 for this
program? M1 x CPIM1 / Clock RateM1
ExTimeM1
IC
2.8/50
=
=
= 1.31
ExTimeM2
ICM2 x CPIM2 / Clock RateM2
3.2/75
17
For Next Time
1. Read Chapter 1.4-1.7
2. Performance Measurement (cont.)
18