Potential of parallelism-parallel computing, Computer Engineering

Potential of Parallelism

Problems in the actual world differ in respect of the degree of natural parallelism inherent in the personal problem domain. Some problems may be simply parallelized. On the other hand, there are some natural sequential difficulty (for ex: - computation of Fibonacci sequence) whose parallelization is almost impossible. The extent of parallelism may be enhanced by appropriate design of an algorithm to explain the problem consideration. If processes don't split address space and we could remove data dependency among instructions, we can attain higher level of parallelism. The idea of speed up is used as a calculate of the speed up that point out up to what degree to which a sequential program can be parallelised.  Speed up may be occupied as a sort of point of inherent parallelism in a program. In this admiration, Amdahl has specified a law, known as Amdahl's Law, which declare that potential program speedup is distinct by the fraction of code (P) that preserve be parallelised:   

                                                                     2436_Potential of Parallelism.png

If no element of the code can be parallelized, P = 0 and the speedup = 1 i.e. it is an essentially sequential program. If every code is parallelized, P = 1, the speedup is infinite. But basically, the code in no program can made 100% parallel. Hence speed up can never be immeasurable.

If 50% of the code is parallelized, maximum speedup = 2, meaning the code will scamper twice as fast. If we establish the amount of processors performing the parallel fraction of work, the link can be modelled by:

                                                                    1442_Potential of Parallelism 1.png

Where P = parallel fraction, S = serial fraction and N = number of processors. The Table 1 shows the value of speed up for different values P and N.

                                                                        Table 1

                                                                                        Speedup

                                                       --------------------------------

                                                        N          P = .50 P = .90 P = .99

                                                      -----      -------   -------   -------

                                                        10          1.82     5.26     9.17

                                                        100        1.98     9.17     50.25

                                                        1000      1.99     9.91     90.99

                                                        10000    1.99     9.91     99.02

The Table 1 suggest that speed up increase as P increases. However, after a definite Limits N does not have a lot impact on the value of pace up. The reason being that, for N processors to remain dynamic, the code must be, in some way or other, being divisible in, independent part, roughly N parts each part taking almost same total of time.

Posted Date: 3/1/2013 4:29:04 AM | Location : United States







Related Discussions:- Potential of parallelism-parallel computing, Assignment Help, Ask Question on Potential of parallelism-parallel computing, Get Answer, Expert's Help, Potential of parallelism-parallel computing Discussions

Write discussion on Potential of parallelism-parallel computing
Your posts are moderated
Related Questions
When can a user program execution be interrupted? It won't be desirable to interrupt a program when an instruction is being executed and is in a state such as instruction decod

NetDynamics Application Server was the primary Java-based integrated software platform. The product was developed by NetDynamics Inc. As Java became the dominant development langua

Explain importance of the different types of distributing frames used in exchanges. Here MDF = main distribution frame; MF = main feeder; FP = feeder point; BF = branch f

What are the steps comprised in authentication? Steps in Authentication: The control over the access of the resources within the repository is exercised in two steps tha

Question 1 Give a brief explanation on message oriented middleware Question 2 Describe Distributed object model Question 3 Explain File systems in a distributed computing Env

Case Study - A taxi company has 200 taxies. The company provides its services to all the nine districts in Mauritius, about 20 taxies per district. A taxi is normally attached to

Q. Define Atomic Directive in FORTAN? Atomic directive guarantees a specific storage location is updated atomically rather than exposing it to odds of multiple simultaneous wri

Q. How to Transmits data in the active message buffer? int pvm_bcast( char *group, int msgtag ) Transmits data in the active message buffer to a group of processes. msgt

If  the input to T-flipflop is 100 Hz signal, the final output of the three T-flipflops in cascade is ? Ans. The  final  output  of  the  three  T-flip-flops in cascade is 12

Define DMA. The transfer of data among a fast storage device such as magnetic disk and memory if often limited by the speed of the CPU. Removing the CPU from the path and letti