DISTRIBUTED AND PARALLEL COMPUTING
SKR 3202
Chapter 4 : Performance and
Scalability of Parallel System
(w6)
TOPIC LEARNING OUTCOMES
Performance Evaluation
Effect of Granularity and
Data Mapping on
Performance
Explain and analysis the
performance metrics of
parallel system(C1, A2)
Describe the basic concept
of granularity and how it
effects the parallel
system(C4, P3)
2
SKR 3202 :: Chapter 4
4.1 Performance Evaluation for Parallel System
It is important to study the performance of parallel programs
with a view to determining the best algorithm, evaluating
hardware platforms, and examining the benefits from
parallelism.
A number of metrics have been used based on the desired
outcome of performance analysis.
A sequential algorithm is evaluated by its runtime (in general,
asymptotic runtime as a function of input size); the
performance of algorithms applied to very large input datasets.
The parallel runtime of a program depends on the input size,
the number of processors, and the communication parameters
of the machine.
Asymptotically i.e., as the input size goes to infinity.
3
SKR 3202 :: Chapter 4
4.1 Performance Evaluation (cont.)
A number of performance measures are intuitive.
Wall clock time - the time from the start of the first processor
to the stopping time of the last processor in a parallel
ensemble.
But how does this scale when the number of processors is
changed of the program is ported to another machine altogether?
How much faster is the parallel version?
“If I use two processors, shouldn't my program run twice as fast?”
No - a number of overheads, including wasted computation,
communication, idling, and contention cause degradation in
performance.
44
SKR 3202 :: Chapter 4
4.1 Performance Evaluation (cont.)
Serial runtime of a program
Refers to the time elapsed between the beginning and the end of
its execution on a sequential computer.
The parallel runtime
Refers to the time that elapses from the moment the first
processor starts to the moment the last processor finishes
execution.
We denote the serial runtime by T
s
and the parallel runtime by
T
P
.
55
SKR 3202 :: Chapter 4