CS1104: Computer Organisation http://www.comp.nus.edu.sg/~cs1104

1
CS1104 Computer Organisation http//www.comp.nus.
edu.sg/cs1104

• School of Computing
• National University of Singapore

2
PII Lecture 2 Performance

• Performance Definition
• Factors Affecting Performance
• Measurement Parameters for Performance
• Co-relation Among Performance Parameters
• Chapter 2 of Pattersons book 2.1, 2.2, 2.3
  first part of 2.7 and 2.9.

3
Performance Definition

• Purchasing perspective
• Given a collection of machines, which has the
• best performance?
• least cost?
• best performance/cost?
• Design perspective
• Faced with design options, which has the
• best performance improvement?
• least cost?
• best performance/cost?

4
Performance Definition (2)

• Both require
• basis for comparison
• metric for evaluation
• Our goal is to understand performance of
  machines architectural design.

5
Two Notions of Performance

• Which has higher performance?
• Time to do ONE task (execution time)
• Execution time, response time, latency
• Tasks per day, hour, week, (performance)
• Throughput, bandwidth.
• Response time and throughput might be in
  opposition.

6
Two Notions of Performance (2)

• Time of AirBus vs. Boeing 747?
• AirBus is 1350 mph / 610 mph 2.2 times faster
  6.5 hours / 3 hours
• Throughput of AirBus vs. Boeing 747?
• AirBus is 178,200 pmph / 286,700 pmph 0.62
  times faster
• Boeing is 286,700 pmph / 178,200 pmph 1.6
  times faster
• Boeing is 1.6 times (60) faster in terms of
  throughput.
• AirBus is 2.2 times (120) faster in terms of
  flying time.

7
Definitions

• Performance is in units of things-per-second
• Bigger is better
• If we are primarily concerned with response time
• X is n times faster than Y means the speedup n
  is

8
Computer Performance

• Response Time (latency)
• Time between start and end of an event (execution
  time).
• How long does it take for my job to run?
• How long does it take to execute a job?
• How long must I wait for the database query?
• Throughput
• Total amount of work (or number of jobs) done in
  a given time.
• How many jobs can the machine run at once?
• What is the average execution rate?
• How much work is getting done?

9
Computer Performance (2)

• If we upgrade a machine with a new processor,
  what do we increase? Answer Response Time.
• If we add a new machine to the lab what do we
  increase? Answer Throughput.

10
Execution Time

• Elapsed Time
• counts everything (disk and memory accesses,
  I/O, etc.)
• a useful number, but often not good for
  comparison purposes.
• CPU time
• doesn't count I/O or time spent running other
  programs.
• can be broken up into system time, and user time.

11
Execution Time (2)

• Our focus user CPU time
• time spent executing the lines of code that are
  "in" our program.

12
Execution Time (3)

• Instead of reporting execution time in seconds,
  we often use clock cycles (basic time unit in
  machine).

• Cycle time (or cycle period) time between two
  consecutive rising edges, measured in seconds.
• Clock rate (or clock frequency) cycles per
  second (1 Hz 1 cycle/second).
• Example A 200 MHz clock has cycle time of
  1/(200x106) 5 x 10-9 seconds 5 nanoseconds.

...
13
Execution Time (4)

• Therefore, to improve performance (everything
  else being equal), you can do the following
• ? Reduce the number of cycles for a program,
  or
• ? Reduce the clock cycle time, or said in
  another way,
• ? Increase the clock rate.

14
Cycles in a Program

• Could we assume that number of cycles number
  of instructions? Or number of cycles is
  proportional to number of instructions?

15
Cycles in a Program (2)

• No, the assumption is incorrect.
• The tasks of different instructions take
  different amount of time to finish.
• For example, a Multiple instruction may take more
  cycles than an Add instruction, floating-point
  operations take longer than integer operations.
• Accessing memory takes more time than accessing
  registers.

16
Example 1 Clock Rate

• Our favorite program runs in 10 seconds on
  computer A, which has a 400 MHz clock. We are
  trying to help a computer designer build a new
  machine B, that will run this program in 6
  seconds. The designer can use new (or perhaps
  more expensive) technology to substantially
  increase the clock rate, but has informed us that
  this increase will affect the rest of the CPU
  design, causing machine B to require 1.2 times as
  many clock cycles as machine A for the same
  program. What clock rate should we tell the
  designer to target at?
• ANSWER
• For A Time 10 sec. cycles 1/400MHz
• For B Time 6 sec. 1.2 cycles
  1/clock_rate
• gt clock_rate 10 400 1.2 / 6 MHz 800MHz

17
Cycles per Instruction (CPI)

• A given program will require

• some number of instructions (machine
  instructions)
• some number of cycles
• some number of seconds

X CPI
X cycle time
18
Cycles per Instruction (CPI) (2)
Average cycles per instruction CPI (CPU Time
Clock Rate) / Instruction Count Clock Cycles /
Instruction Count

where
Ik instruction frequency

• Invest resources where time is spent!

19
Aspects of CPU Performance

• Performance is determined by execution time.
• Does any of these variables equal performance?
• number of cycles to execute program?
• number of instructions in program?
• number of cycles per second?
• average number of cycles per instruction?
• average number of instructions per second?
• Answer No to all.
• Common pitfall thinking that one of the
  variables is indicative of performance when it
  really isnt.

20
Aspects of CPU Performance (2)

• CPU performance depends on
• Clock cycle time ? Hardware technology and
  organization
• CPI ? Organization and ISA
• Instruction Count ? ISA and compiler
• Be careful of the following concepts
• Machine ? ISA and hardware organization
• Machine ? cycle time
• ISA hardware organization ? number of cycles
  for any instruction (this is not average CPI)
• ISA compiler program ? number of instructions
  executed
• Therefore, ISA Compiler Program Hardware
  organization Cycle time ? Total CPU time.

21
Example 2 CPI

• Suppose we have two implementations of the same
  instruction set architecture (ISA). For some
  program,Machine A has a clock cycle time of 10
  ns and a CPI of 2.0.Machine B has a clock cycle
  time of 20 ns and a CPI of 1.2.What machine is
  faster for this program, and by how much?
• ANSWERMachine A time _Inst 2.0 (CPI) 10
  ns (cycle time) Machine B time _Inst 1.2
  (CPI) 20 ns (cycle time) Performance(A) /
  Performance(B) 1.2 20 / (2.0 10) 1.2

22
Example 3 Number of Instructions

• A compiler designer is trying to decide between
  two code sequences for a particular machine.
  Based on the hardware implementation, there are
  three different classes of instructions Class
  A, Class B, and Class C, and they require one,
  two, and three cycles (respectively). First
  code seq. has 5 instructions 2 of A, 1 of B,
  and 2 of CSecond seq. has 6 instructions 4 of
  A, 1 of B, and 1 of C.Which sequence will be
  faster? How much?What is the CPI for each
  sequence?
• ANSWERCPI(S1) (2 1 1 2 2 3) / (2
  1 2) 2CPI(S2) (4 1 1 2 1 3) / (4
  1 1) 1.5Time(S1) (2 1 1 2 2 3)
  cycle_time 10 c_tTime(S2) (4 1 1 2
  1 3) cycle_time 9 c_tTime(S1) / Time(S2)
  10/9 1.1 and S2 is faster.

23
Sample Question

• You are given two machine designs IA1 and IA2 for
  performance benchmarking. Both IA1 and IA2 have
  the same ISA, but different hardware
  implementations and compilers. Assuming that the
  clock cycle times for IA1 IA2 are the same,
  performance study gives the following
  measurements for the two designs
• For design IA1
• Instruction Class CPI No. of Instructions
  Executed
• A 1 3,000,000,000,000,000,000
• B 2 2,000,000,000,000,000,000
• C 3 2,000,000,000,000,000,000
• D 4 1,000,000,000,000,000,000
• For design IA2
• A 2 2,700,000,000,000,000,000
• B 3 1,800,000,000,000,000,000
• C 3 1,800,000,000,000,000,000
• D 2 900,000,000,000,000,000

24
Sample Question (2)

• What is the CPI for each machine (IA1 and IA2)?
• Let Y 1,000,000,000,000,000,000.
• CPI(IA1) (13Y 22Y 32Y 41Y) /
  (3Y 2Y 2Y 1Y)
• 17Y / 8Y 2.125
• CPI(IA2) (23Y32Y32Y21Y)0.9 /
  (3Y2Y2Y1Y)0.9
• 20Y / 8Y 2.5
• Which machine is faster? By how much?
• Let C clock cycle.
• Time(IA1) 2.125 (8Y C)
• Time(IA2) 2.5 0.9 (8Y C)
• 2.25 (8Y C)
• IA1 is faster than IA2 by 2.25 / 2.125
  1.0588

25
Sample Question (3)

• To further improve the performance of the
  machines, a new compiler technique is
  introduced. The compiler can simply eliminate all
  class D instructions from the benchmark program
  without any side effects. That is, there is no
  change to the number of class A, B, and C
  instructions executed in the two machines. With
  this new technique, which machine is faster? By
  how much?
• Let Y 1,000,000,000,000,000,000 and C clock
  cycle.
• CPI(IA1) (1 3Y 2 2Y 3 2Y) / (3Y
  2Y 2Y)
• 13Y / 7Y 1.857
• CPI(IA2) (23Y 32Y 32Y) 0.9 / (3Y
  2Y 2Y) 0.9
• 18Y / 7Y 2.571
• Time(IA1) 1.857 (7Y C)
• Time(IA2) 2.571 0.9 (7Y C) 2.314
  (7Y C)
• IA1 is faster than IA2 by 2.314 / 1.857 1.246

26
Sample Question (4)

• Alternatively, to further improve the performance
  of the machines, a new hardware technique is
  introduced. The hardware can simply execute all
  class D instructions in zero times without any
  side effects. (There is still execution for class
  D instructions). With this new technique, which
  machine is faster? By how much?
• Let Y 1,000,000,000,000,000,000 and C clock
  cycle.
• CPI(IA1) (1 3Y 2 2Y 3 2Y 0 Y) /
  (3Y 2Y 2Y Y)
• 13Y / 8Y 1.625
• CPI(IA2) (23Y32Y32Y 0Y) 0.9 /
  (3Y2Y2YY) 0.9
• 18Y / 8Y 2.25
• Time(IA1) 1.625 (8Y C)
• Time(IA2) 2.25 0.9 (8Y C) 2.025
  (8Y C)
• IA1 is faster than IA2 by 2.025 / 1.625 1.2461

27
Key Concepts

• Performance is specific to a particular program.
• Total execution time is a consistent summary of
  performance
• For a given architecture, performance increase
  comes from
• increase in clock rate (without adverse CPI
  affects)
• improvement in processor organisation that lowers
  CPI
• compiler enhancement that lowers CPI and/or
  instruction count
• Pitfall expecting improvement in one aspect of
  a machines performance to affect the total
  performance.

28
Key Concepts (2)

• Basic formula for execution time.
• Performance factors CPI, total number of
  instructions executed, cycle time.
• Factors affecting their values
• Calculation of individual values
• Note Change of one factor might change more than
  one component (eg reduction of instruction types
  executed)
• Different performance matrix what it can tell
  and what it might mislead people.

29
Sample Question (1)

• Which of the following statements will affect the
  program execution time?
• Compiler technology
• Instruction set architecture
• Integration circuit chip technology
• Application software
• (i) and (iii)
• (ii) and (iii)
• (i), (ii), and (iii)
• All of the above
• None of the above

Answer
30
Sample Question (2)

• Execution time can always be improved by
• Combining simple instructions into complex
  instructions in the given ISA
• Improving the clock speed of the processor
• Using a new compiler that produces a shorter
  sequence of program code
• (ii) only
• (i) and (ii)
• (ii) and (iii)
• All of the above
• None of the above

Answer
31
Sample Question (3)

• The overall (average) CPI of a given program is
• decreased by decreasing the total number of
  instructions executed in a program, assuming all
  other hardware and software parameters remain the
  same.
• the sum of the CPIs of the individual types of
  instructions executed in the program.
• the average of the CPIs of the individual classes
  of instructions executed in the program. That is,
  if instruction class A, B, C, D, with
  corresponding CPI 1, 2, 3, 4, appear in a
  program, the overall CPI will be (1234)/4.
• decreased by doubling the clock speed of the
  processor, assuming all other hardware and
  software parameters remain the same.
• None of the above.

Answer
32
Sample Question (4)

• Assuming all other hardware and software
  parameters remain the same, the total number of
  instructions executed in a program can be changed
  by
• changing the ISA of the processor.
• reducing the number of cycles needed to execute
  each instruction type in a program.
• increasing the number of cycles needed to execute
  each instruction type in a program.
• doubling the individual CPI of each instruction
  class executed in a program.
• None of the above.

Answer
33
Sample Question (5)

• Execution time can always be improved by
• changing the instruction set architecture of the
  processor from a complex one to a simple one.
• changing the instruction set architecture of the
  processor from a simple one to a complex one.
• changing the compiler so that a lower overall CPI
  value (and different program code sequence) is
  obtained.
• (i) and (iii)
• (i) only
• (ii) only
• (iii) only
• None of the above

Answer
34
Sample Question (6)

• Which of the following affects the overall CPI of
  a program on a given ISA?
• The CPIs of individual classes of instructions
  defined in the ISA.
• The number of instructions executed in the
  program.
• The clock speed of the processor.
• (i) only
• (ii) only
• (iii) only
• (i) and (ii) only
• (i), (ii) and (iii)

Answer
35
Sample Question (7)

• A program takes 5 seconds to execute on machine
  MM1 and 10 seconds to execute on machine MM2.
  Which of the following conclusions must be true?
• The number of instructions executed on MM1 is
  definitely fewer than that on MM2.
• The overall CPI on MM1 is definitely smaller than
  that on MM2.
• The clock speed of MM1 is definitely higher than
  that of MM2.
• All (a), (b), (c).
• None of the above.

Answer
36
Sample Question (8)

• To improve performance of a program, state what
  (increase/decrease/do nothing) you would do to
  the following, assuming that everything else
  being equal
• The number of required cycles.
• The number of instructions executed.
• The clock cycle time.
• The clock rate.

Decrease
Decrease
Decrease
Increase
37
Sample Question (9)

• Given a machine at 500 MHz, the measurement of a
  program execution is as follows
• Instr. Class CPI Frequency
• A 1 10
• B 2 20
• C 3 30
• D 4 40
• What happens to (i) overall CPI, (ii) execution
  time, if
• Instruction distribution is A 40, B 30,
  C20, D10.
• The CPIs of all instruction classes are doubled.
• Answer increase/decrease/unchanged.

a) CPI decreases, execution time decreases.
b) CPI increases, execution time increases.
38
Sample Question (10)

• State whether these statements are true or false
• Instruction set architecture is mainly about the
  digital and circuit design of microprocessor.
• My 400MHz PC is always faster than the SoCs
  SUN450 system, which runs at 336 MHz.
• CPU execution time of a program is defined as the
  elapsed time between the program submission to
  the generation of the result.

a) False.
b) False.
c) False.
39
Sample Question (11)

• Given a machine at 500 MHz, the measurement of a
  program execution is as follows
• Instr. Class CPI Frequency
• A 1 10
• B 2 20
• C 3 30
• D 4 40
• What happens to (i) overall CPI, (ii) execution
  time, if
• Equal instruction distribution among 4 classes
  (25 each)
• Clock rate is increased to 800 MHz.
• Answer increase/decrease/unchanged.

a) CPI decreases, execution time decreases.
b) CPI unchanged, execution time decreases.
40
Sample Question (12)

• Given a machine at 500 MHz, the measurement of a
  program execution is as follows
• Instr. Class CPI Frequency
• A 1 10
• B 2 20
• C 3 30
• D 4 40
• What happens to (i) overall CPI, (ii)
  instruction count, (iii) clock speed, if
• A different compiler is used to produce the
  executable code of a program.
• A new hardware implement of the given ISA is
  used.
• Answer changed/unchanged.

a) CPI changed, IC changed, CS unchanged.
b) CPI changed, IC unchanged, CS changed.
41
End of file