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 is java swing, Swing is a GUI toolkit for Java. It is one kind of the ...

Swing is a GUI toolkit for Java. It is one kind of the Java Foundation Classes (JFC). Swing haves graphical user interface (GUI) widgets such as text boxes, buttons, split-panes, a

Explain bernstein conditions for detection of parallelism, Bernstein Condit...

Bernstein Conditions for Detection of Parallelism For execution of a number of instructions or a block of instructions in parallel, it must be made certain that instructions ar

Learning weights in perceptrons, Learning Weights in Perceptrons: Furt...

Learning Weights in Perceptrons: Furthermore details are we will look at the learning method for weights in multi-layer networks next lecture. Thus the following description o

Explain data mining, Data Mining is an analytic method designed to explore...

Data Mining is an analytic method designed to explore data and then to validate the findings by applying the detected patterns to latest subsets of data.  The ultimate goal of dat

Explain the process of skolemization., Problem 1. Explain briefly the p...

Problem 1. Explain briefly the process of matching production rules against working memory 2. What are the different kinds of knowledge that need to be represented in AI? Ex

Explain the differences of casex and casez, Explain the differences of case...

Explain the differences of casex and casez over the case statement? casex operator has to be used when both high impedance value (z) and unknown (x) in any bit  has  to  be  t

Higher order predicate logic - artificial intelligence, Higher Order Predic...

Higher Order Predicate Logic: In first order predicate logic, we are allowed to quantify over objects only. If we let  ourselves  to  quantify  over  predicate  or  function  s

Hardware implementation for signed-magnitude data, Hardware Implementation ...

Hardware Implementation for signed-magnitude data When multiplication  is  implemented  in  digital  computer,  we  change  process lightly. Here, in place of providing registe

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