Program level-parallelism based on granularity size, Computer Engineering

Assignment Help:

Program Level:

It is the next level consisting of independent programs for parallelism. Coarse Granularity  size is used at this level containing ten thousands of instructions. Time sharing is get at this level of parallelism. Parallelism at this level has been exploited through the operating system.

                             The relation between parallelism and grain sizes levels has been given in Table 1.

                               1676_Program Level.png

Coarse grain parallelism is traditionally executed in tightly shared memory or coupled multiprocessors like the Cray Y-MP. Loosely coupled systems are used to implemented medium grain program segments. Fine grain parallelism has been considered  in SIMD organization of computers.

 


Related Discussions:- Program level-parallelism based on granularity size

Cache simulater, Requirements You are required to program (in a high l...

Requirements You are required to program (in a high level language such as C, C++, Java) and implement a cache simulator which will have the following inputs and outputs:-

Why eprom chips are mounted in packages, Why EPROM chips are mounted in pac...

Why EPROM chips are mounted in packages that have transparent window? Since the erasure needs dissipating the charges trapped in the transistors of memory cells. This can be co

Explain in detail companding, Explain in detail companding. Companding...

Explain in detail companding. Companding: It is the process of compressing and expanding. This includes compressing the signal at the transmitter and expanding this at the re

Explain differences between folded and non-folded network, Explain differen...

Explain differences between folded and non-folded network. Folded network: While all the inlets/outlets are connected to the subscriber lines, the logical connection shows as

Analysis of amdahls law, The outcomes of analysis of Amdahl's law are: 1...

The outcomes of analysis of Amdahl's law are: 1) To optimize the performance of parallel computers, modified compilers need to be developed which should aim to decrease the numb

Data hazards in computer architecture, Data hazards -  computer architec...

Data hazards -  computer architecture : A main effect of pipelining is to alter the relative timing of instructions by overlapping their execution. This introduces contro

Explain FIFO page replacement algorithm, Explain FIFO Page replacement algo...

Explain FIFO Page replacement algorithm. FIFO policy: This policy only removes pages in the order they entered in the main memory. By using this policy we simply eliminate a

Colour management, There are three primary colours in pigments - Red, Yello...

There are three primary colours in pigments - Red, Yellow and Blue. There are two ways to produce more colours:   Physical Mixing: Physically mix colours to produce a new colour

Security protocols used for e-commerce applications, Explain dissimilar sec...

Explain dissimilar security protocols used for e-commerce applications.   The e-commerce systems of today are composed of a number of components including: a commerce server, d

What is real time clock, Real time clock A real-time clock keeps the t...

Real time clock A real-time clock keeps the time in real time - i.e. in hours and minutes. Software for the real-time clock comprises an interrupt service procedure which is c

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