Scribd
Upload
89 views2 pages

Solution of Sample Exercises in Chapter 2 2.4

This document summarizes solutions to sample exercises from Chapter 2. It calculates the number of instructions for two machines (M1 and M2) given cycle times and speeds. It also calculates the throughput and cost-effectiveness of M1 and M2 for a program, finding M1 is more cost-effective. Other sections calculate new clock speeds needed for equivalent performance, compare CPI values between base and optimized machines, calculate new CPI given instruction mix changes, compare program run times on different computers, and uses Amdahl's Law to determine speedups from improvements.

Uploaded by

Guilherme
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
89 views2 pages

Solution of Sample Exercises in Chapter 2 2.4

This document summarizes solutions to sample exercises from Chapter 2. It calculates the number of instructions for two machines (M1 and M2) given cycle times and speeds. It also calculates the throughput and cost-effectiveness of M1 and M2 for a program, finding M1 is more cost-effective. Other sections calculate new clock speeds needed for equivalent performance, compare CPI values between base and optimized machines, calculate new CPI given instruction mix changes, compare program run times on different computers, and uses Amdahl's Law to determine speedups from improvements.

Uploaded by

Guilherme
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

SOLUTION OF SAMPLE EXERCISES IN CHAPTER 2

2.4
We are given the number of cycles per second and the number of seconds, so we
can calculate the number of required cycles for each machine. If we divide this by the
CPI well get the number of instructions.
For M1, we have
3 seconds 200 106cycles/second = 600 10 cycles per program / 10 cycles per
instruction = 60 106instructions per program.
For M2, we have
4 second 300 106 cycles/second = 1200 106cycles per program / 9.4 cycles per
instruction = 127.7 106instructions per program.
2.9
We do this problem by finding the amount of time that program 2 can be run in an
hour and using that for executions per second, the throughput measure.
3600
Executions of P2 per hour=

seconds
seconds
200
hour
Execution of P1
seconds
Execution of P2
3600

Executions of P2 per hour on M1=

3600
Executions of P2 per hour on M2=

seconds
200 100
1600
hour
=
= 53
3
3
seconds
200 5
2600
hour
=
= 650
4
4

650
=1.2 times
533
faster than M1. The cost-effectiveness of the machines is to be measured in units
of throughput on program 2 per dollar, so
With performance measured by throughput for program 2, machine M2 is

Cost-effectiveness of M1=

533
= 0.053
10,000

Cost-effectiveness of M2=

650
= 0.043
15,000

Thus, M1 is more cost-effective than M2. (Machine costs are from Exercise 2.5.)

2.12
2.18

M1 would be as fast if the clock rate were 1.25 higher, so 500 1.25 = 625 MHz.
CPI for Mbase = 2 0.4 + 3 0.25 + 3 0.25 + 5 0.1 = 2.8
CPI for Mopt = 2 0.4 + 2 0.25 + 3 0.25 + 4 0.1 = 2.45

2.21

This problem can be done in one of two ways. Either find the new mix and adjust
the frequencies first or find the new (relative) instruction count and divide the CPI by
that. We use the latter.
Ratio of instructions=0.9 0.4+0.9 0.25+0.85 0.25+0.1 0.95=0.81

So we can calculate CPI as


CPI=

2 0.9 0.4 + 3 0.9 0.25 + 3 0.85 0.25 + 5 0.1 0.95


= 3.1
0.81

2.29
Program
Program 1 (seconds)

Weight
10

Computer A
1

Computer B
10

Computer C
20

Program 2 (seconds)

1000

100

20

9.18

18.2

20

Weighted AM

So B is fastest; it is 1.10 times faster than C and 5.0 times faster than A. For an equal
number of executions of the programs, the ratio of total execution times A:B:C is
1001:110:40, thus C is 2.75 times faster than B and 25 times faster than A.
2.44
Using Amdahls law (or just common sense) we can determine the following:
Speedup if we improve only multiplication =100/(30+50+20/4)=1.18
Speedup if we only improve memory access =100/(100-(50-50/2))=1.33
Speedup if both improvements are made=100/(30+50/2+20/4)=1.67

You might also like