Class Assignment #3 | SP21-BCS-022
Microprocessor and Assembly
Language
CLASS ASSIGNMENT # 3
Submitted by
H Ahsan ullah Farooqi
SP21-BCS-022
BCS 6A
Submitted TO:
MR: TAIMUR SHAHZAD
DEPARTMENT OF COMPUTER SCIENCE
COMSATS UNIVERSITY ISLAMABAD
Page 1 of 5
Class Assignment #3 | SP21-BCS-022
QUESTION-1
How CPU performance is evaluated? Discuss performance evaluations tools of
CPU briefly along with their equations and appropriate examples.
Answer:
CPU performance is a critical aspect of a computer system, and it is evaluated using
various metrics and tools. Here are some commonly used performance evaluation
tools and metrics for CPUs:
1) Clock Speed (Frequency):
Equation: Performance = Clock Speed (in Hz) / Cycles per Instruction (CPI)
Clock speed represents how many cycles a CPU can execute in a second. Higher
clock speeds generally result in better performance.
Example: A CPU with a clock speed of 3 GHz can execute 3 billion cycles per
second.
2) Instructions Per Cycle (IPC):
Equation: IPC = Instructions Executed / Cycles Executed
IPC measures how many instructions are executed per clock cycle. Higher IPC values
indicate better performance.
Example: If a CPU executes 4 instructions in 2 cycles, the IPC would be 2.
3) Throughput:
Equation: Throughput = Instructions per Second
Throughput measures the number of instructions a CPU can execute in one second.
Example: If a CPU executes 2 billion instructions per second, its throughput is 2 GHz.
4) CPI (Cycles Per Instruction):
Equation: CPI = Total Cycles / Total Instructions
CPI represents the average number of clock cycles per instruction. Lower CPI values
indicate better performance.
Example: If a CPU executes 5000 cycles for 1000 instructions, the CPI is 5.
5) Execution Time (Elapsed Time):
Equation: Execution Time = (Number of Instructions) * CPI * Clock Cycle Time
Execution time represents the total time taken to execute a program. Lower execution
times indicate better performance.
Example: If a program has 1000 instructions, CPI is 2, and clock cycle time is 0.5 ns,
the execution time is 1000 * 2 * 0.5 ns = 1000 ns.
Page 2 of 5
Class Assignment #3 | SP21-BCS-022
6) MIPS (Million Instructions Per Second) and MFLOPS (Million Floating-
Point Operations Per Second):
Equations:
MIPS = (Number of Instructions) / (Execution Time) * 10^6
MFLOPS = (Number of Floating-Point Operations) / (Execution Time) * 10^6
MIPS and MFLOPS are used to measure the rate of instruction and floating-point
operation execution, respectively.
7) Benchmarking Tools:
Tools like SPEC (Standard Performance Evaluation Corporation) benchmarks are
widely used to evaluate the performance of CPUs by running standardized sets of
programs and measuring their execution times
Page 3 of 5
Class Assignment #3 | SP21-BCS-022
QUESTION-2
Define system performance. Explain important parameters that are used to
measure the system performance theoretically and mathematically.
System Performance:
System performance refers to the overall effectiveness of a computer system. Key
parameters for measurement include:
Throughput:
Formula: Throughput = Completed Tasks / Time
Example: 1000 tasks/hour.
Response Time:
Formula: Response Time = Completion Time - Request Time
Example: 5 seconds for web page loading.
Execution Time:
Formula: Execution Time = Completion Time - Start Time
Example: 30 minutes for a program.
Scalability:
Formula: Scalability = Performance with 'n' Resources / Performance with 'm'
Resources
Example: Scalability of 2 with 4 CPUs.
Utilization:
Formula: Utilization = (Time Busy / Total Time) * 100
Example: 80% CPU utilization.
Efficiency:
Formula: Efficiency = (Useful Work Output / Total Input) * 100
Example: 80% efficiency in energy usage.
Reliability and Availability:
Formula: Availability = (Uptime / Total Time) * 100
Example: 900 operational hours in a 30-day month.
Page 4 of 5
Class Assignment #3 | SP21-BCS-022
QUESTION-3
Suppose that when Program A is run, the user CPU time is 3 seconds, the
elapsed wall clock time is 4 seconds, and the system performance is 10
MFLOP/sec. Assume that there are no other processes taking any significant
amount of time, and the computer is either doing calculations in the CPU, or
doing I/O, but it can't do both at the same time. We are now replacing the
processor with one that runs six times faster but doesn't affect the I/O speed.
What will the user CPU time, the wall clock time, and the MFLOP/sec
performance be now?
CPU performanceB/CPU performanceA = CPU timeA/CPU timeB
6 = 3/CPU timeB
User CPU Time = .5 seconds
Since the I/O time is unaffected by the performance increase, it still takes 1 second to
do I/O. Therefore it takes 1 + .5 = 1.5 seconds to run Program A on the faster CPU
Wallclock Time = 1.5 seconds
System Performance in MFLOPS = Number of Floating Point Operations *
106/Wallclock Time
Old System Performance (10) = #FLOP * 106/4
#FLOP = 40 * 106
New System Performance = 40 * 106/1.5
MFLOP/sec = 26.667
Page 5 of 5
