Parallelism based on granularity size-granularity, Computer Engineering

Assignment Help:

Parallelism based on Granularity size

Granularity:  Granularity or Grain size is a determine which measure how much computation is devoted in a process.Granularity size is determined by counting the number of instructions in a program section. The following types of grain sizes have been recognized (shown in Figure):

                                        2282_Parallelism based on Granularity size-Granularity.png

 1)   Fine Grain: This type includes approximately less than 20 instructions.

2)   Medium Grain: This type includes approximately less than 500 instructions.

3)   Coarse Grain: This type includes approximately greater than or identical to one thousand instructions.

Based on these Granularity sizes, parallelism can be specified at various stages in a program. These parallelism stages form a hierarchy according to which, lower the level, the greater is the granularity of the process. The degree of parallelism reduces with increase in level. Every stages according to a granularity size demands scheduling and communication overhead. Following are the parallelism levels (shown in Figure ):

                                     788_Parallelism based on Granularity size-Granularity 1.png


Related Discussions:- Parallelism based on granularity size-granularity

What are the advantages of using structure in c program, What are the advan...

What are the advantages of using structure in C Program Declaring a struct is a two-stage process. The first stage defines a new data type that has the required structure which

Parallelism conditions, Parallelism Conditions As discussed earlier, pa...

Parallelism Conditions As discussed earlier, parallel computing needs that the segments to be implemented in parallel must be free of each other. Thus, before implementing para

How reassembling of ip fragments is advantageous, Reassembling of IP fragme...

Reassembling of IP fragments at the ultimate destination is advantageous. Give reasons. Needing the ultimate destination to reassemble the fragments has two major advantages. F

Why we need the need of parallel computation, THE NEED OF PARALLEL COMPUTAT...

THE NEED OF PARALLEL COMPUTATION   With the growth of computer science, computational pace of the processors has also increased many a times. Though, there are definite constr

War (write after read) - data hazards , WAR (write after read) - Data hazar...

WAR (write after read) - Data hazards in computer architecture: WAR (write after read) - j tries to write at destination before it is read by i , hence i  wrongly gets the n

How do you find out the flaw, How do you find out the flaw, which of the ad...

How do you find out the flaw, which of the address getting written wrongly. Fill the full memory once with either random data or sequential data then after filling totally rea

What happens if acknowledge() is called within a transaction, As per the JM...

As per the JMS specification, when you are in a transaction, the acknowledge Mode is ignored. If acknowledge() is known as within a transaction, it is ignored.

What is rolap, Functioning of ROLAP happens concurrently with relational da...

Functioning of ROLAP happens concurrently with relational databases. Data and tables are stored as relational tables. To hold new information or data new tables are formed. Functio

Application area of artificial intelligence, 1. The State of the Art: What ...

1. The State of the Art: What can AI do today? A concise answer is difficult because there are so many activities in so many subfields. Here we sample a few applications other

Write Your Message!

Captcha
Free Assignment Quote

Assured A++ Grade

Get guaranteed satisfaction & time on delivery in every assignment order you paid with us! We ensure premium quality solution document along with free turntin report!

All rights reserved! Copyrights ©2019-2020 ExpertsMind IT Educational Pvt Ltd