Scribd
Upload
2 views

Assignment 01 Retake

This document outlines the details of Assignment #1 (Retake) for the course Parallel and Distributed Computing at COMSATS University Islamabad, Lahore Campus, including submission guidelines and marking criteria. The assignment consists of three parts focused on analyzing and modifying a given code to address dependencies for parallelization. The deadline for submission is March 24, 2025, and it must be handwritten with no late submissions accepted.

Uploaded by

abma959595
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
2 views

Assignment 01 Retake

This document outlines the details of Assignment #1 (Retake) for the course Parallel and Distributed Computing at COMSATS University Islamabad, Lahore Campus, including submission guidelines and marking criteria. The assignment consists of three parts focused on analyzing and modifying a given code to address dependencies for parallelization. The deadline for submission is March 24, 2025, and it must be handwritten with no late submissions accepted.

Uploaded by

abma959595
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

COMSATS University Islamabad, Lahore Campus

Assignment #1 (Retake) – SPRING 2025


Course Title: Parallel and Distributed Computing Course Code: CSC334 Credit Hours: 3(2,1)
Course Instructor: Ms. Muntha Amjad Programme Name: BCS
Semester: Batch: Section: Date: 20/03/2025
Deadline: 24/03/2025 Maximum Marks: 10
Important Instructions / Guidelines:
 Submit the assignment, in class, before the start of the lecture.
 Strictly handwritten. Typed assignment will result in zero marks.
 No late submission allowed.
 Any solution found to be copied would strictly result in zero marks.

Question 01: [Marks: 4 + 4 + 2 = 10]


CLO: <2> Apply principles and concepts of parallel and distributed computing to solve computational problems;
Bloom Taxonomy Level: <Applying>

(a) The code given below cannot be parallelized due to multiple dependencies. Draw the dependency
graph showing all data-dependences, output-dependences, and anti-dependences.

for i = 1 to 50
A[i] = B[i-1] + C[i]
B[i] = A[i+2] + C[i]
s = s + C[i]

(b) Modify the code given in (a) to remove the dependencies (where possible) and draw the updated
dependency graph showing all data-dependences, output-dependences, and anti-dependences.

(c) Can this code now be parallelized? If yes, write the parallel code.

You might also like