Chapter 4 Assessing and Understanding Performance

1
Chapter 4Assessing and Understanding Performance
Computer Organization

• Kevin Schaffer
• Department of Computer Science
• Hiram College

2
Airplane Example
3
Defining Performance

• Execution time (response time) is the time it
  takes to complete a task
• Used as a measure of performance for
  user-interactive systems like desktop computers
• Throughput is the amount of work done in a given
  time
• Used as a measure of performance for
  non-user-interactive systems like servers

4
Execution Time/Performance
5
Relative Performance

• Commonly we want to compare performance of two
  different computers
• If X is n times faster than Y, then...

6
Measuring Time

• Wall-clock time is the total time to complete a
  task including OS overhead, I/O time, etc.
• CPU time is the time spent by the CPU and
  excluding time spent waiting for I/O devices
• User CPU time is the time the CPU spends
  executing a program excluding time performing OS
  tasks, which is called system CPU time
• Time can also be measured in clock cycles

7
Clock Cycles

• Clock cycle time (clock period) is the length of
  one clock cycle in seconds (ps, ns)
• Clock rate (clock frequency) is the number of
  clock cycles per second measured in Hertz (GHz,
  MHz)
• Clock rate 1 / Clock cycle time
• Make sure units match
• Shortcuts
• Clock rate (MHz) Clock cycle time (ns) 1000
• Clock rate (GHz) Clock cycle time (ps) 1000

8
Performance Factors

• Program is a sequence of instructions
• Each instruction requires a some number of clock
  cycles to execute

9
Execution Time

• Instruction count number of instructions
  executed
• Clock cycles per instruction (CPI) average
  number of clock cycles to execute an instruction

10
Instruction Count

• Static instruction count is the number of
  instructions in a stored program
• Dynamic instruction count is the number of
  instructions the processor executes while running
  a program
• For evaluating performance, we always look at the
  dynamic instruction count
• When comparing processors that implement the same
  instruction set, instruction count is typically
  ignored

11
Clock Cycles Per Instruction

• CPI is the average number of cycles it takes to
  complete an instruction
• Typically CPI is calculated as a weighted average
  over all the instruction classes

12
What Affects Performance?

• Algorithm
• Instruction count, maybe CPI
• Programming language
• Instruction count, CPI
• Compiler
• Instruction count, CPI
• Instruction set architecture
• Instruction count, CPI, clock rate

13
Evaluating Performance

• Set of programs run on a computer is a workload
• A benchmark is a workload specifically designed
  to measure a computer's performance
• The best benchmarks are made up of real programs
• Synthetic benchmarks, on the other hand, try to
  measure low-level performance by repeating short
  blocks of code

14
SPEC

• Standard sets of benchmarks for modern computers
  based on real programs
• Covers a number of application areas including
  graphics, file servers, web servers, etc.
• CPU benchmarks measure CPU performance on integer
  and floating-point programs

15
SPEC CPU/Intel Pentium
16
Speedup

• Speedup tells us how many times faster our system
  is after making some improvement
• That is, a speedup of a 2 means the new version
  is twice as fast as the old one

17
Amdahl's Law

• Amdahl's law provides a limit on the improvement
  in system performance from an improvement in one
  part of the system
• Demonstrates the law of diminishing returns
• f is the fraction of the computation that is
  improved
• s is the speedup of the improvement

18
Amdahl's Law (2)

• Alternate form of Amdahl's law based on actual
  execution time instead of fractions
• This is the form used by the book

19
Poor Performance Measures

• Clock rate
• Instructions per second (IPS)
• Floating-point operations per second (FLOPS)

20
Power Efficiency

• Power consumption affects battery life (laptops)
  and the amount of heat generated
• Modern mobile processors implement features to
  reduce power usage such as dynamic clock scaling
• Goal is to maximize performance/power ratio

21
Pentium M Performance
22
Performance/Power