Scribd
Upload
25 views5 pages

CS_3307_01_Written_Assignment_Unit_2

Provides answers to unit 2 written assignment.

Uploaded by

Nel Matrix
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
25 views5 pages

CS_3307_01_Written_Assignment_Unit_2

Provides answers to unit 2 written assignment.

Uploaded by

Nel Matrix
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

Written Assignment Unit 2

Department of Computer Science

University of the People

CS 3307 - 01 – OPERATING SYSTEMS 2 - AY2025-T2

Dr. Osama Aloqaily (Instructor)

November 21st, 2024


INTRODUCTION TO PARALLEL COMPUTING

Parallel computing is a way of solving big problems faster by splitting them into smaller, separate

tasks that can be worked on at the same time by multiple computers or processors (Heavy.AI,

n.d.). These processors share information as needed and then combine their results to complete

the overall task. The main idea is to get things done more quickly by using several processors

working together instead of just one (Heavy.AI, n.d.). Imagine you're at a pizza restaurant, and

the chef is making one pizza at a time. This way of doing a task is called sequential computing in

the world of computation. every order is completed one by one. Now imagine there are four

chefs, each making their own pizza at the same time. This is called parallel computing. By

breaking a larger task (making pizzas) into smaller tasks (one pizza per chef) and completing

them all simultaneously, it results in Faster services and more pizzas being made.

According to Heavy.AI (n.d.), Parallel computing can be broken into four main types, which are

like different ways to divide and speed up tasks using computers. They are briefly explained

below:

Bit-level parallelism: This method makes the computer handle bigger chunks of data at once, so

it doesn’t have to work as hard or repeat as many steps to finish a task.

Instruction-level parallelism: Think of this as deciding which small steps in a task can be done

at the same time. Sometimes the computer figures this out as it’s running (dynamic), and other

times it’s planned ahead of time by programmers (static).

Task parallelism: This involves splitting a big job into different tasks and running them all at the

same time, but they all work on the same overall goal. It’s like having a team where each person

does a different job, but they’re all working on the same project.
Super word-level parallelism: This is a fancy way of saying the computer can spot patterns and

do certain repeated actions all at once, instead of one at a time, to save time and effort.

Parallel computing is used in many fields beyond just IT, helping to solve complex problems

faster and more efficiently. For example, in the world of finance, parallel computing is crucial for

things like analyzing risks, detecting fraud, and tracking the stock market in real time

(Abhyankar, 2022). For example, in high-frequency trading, computers use parallel computing to

look at market data all at once, spot good trading opportunities, and make trades in fractions of a

second (Abhyankar, 2022). Banks also use parallel computing to process millions of financial

records at the same time, helping them quickly assess risks or detect any unusual activity.

Another work environment in which it is used is in scientific research, where parallel computing

is used for things like weather forecasting, climate studies, and physics simulations. For example,

when predicting the weather, computers break down complex calculations into smaller tasks that

are done simultaneously, allowing meteorologists to make more accurate predictions faster. In

fields like physics and engineering, researchers rely on parallel computing to run simulations that

help them understand things like how fluids move, how particles interact, or how structures

respond to forces.

For businesses that rely on parallel computing, Linux is often the best choice for an operating

system. The reason is that Linux is designed to handle many tasks at once, making it great for

situations where multiple processes need to run in parallel (Kamuri, 2024). It can divide big jobs

and assign them to different parts of the computer's hardware, like its processors, so the work gets

done faster (Kamuri, 2024). This is especially useful for demanding tasks like scientific research

or machine learning, which require a lot of computing power.


In conclusion, parallel computing plays a big role in modern computer systems, and without it,

performing computer-related tasks will look like cars stuck up in a traffic line waiting for their

turn to be processed.
Reference:

What is Parallel Computing? Definition and FAQS. HEAVY.AI. (n.d.).

https://www.heavy.ai/technicalglossary/parallelcomputing#:~:text=Parallel%20computing

%20refers%20to%20the,part%20of%20an%20overall%20algorithm.

Abhyankar, A. (2022, January 7). Parallel Computing for Finance | Medium. Medium.

https://abhyankar-ameya.medium.com/parallel-computing-for-finance-ec053d8fb20f

Kamuri, S. (2024, March 27). Code 360 by Coding Ninjas. 2024 Naukri.com.

https://www.naukri.com/code360/library/parallel-operating-system

You might also like