Assignment
Fast learner based on MST-2
Department BE-CSE/IT-3rdYear
Subject Name Parallel and Distributed Computing
Subject Code 22CST-354
Data and Control Parallelism
Question no.1: Illustrate how data parallelism enhances computational speed in large-scale
processing.
Performance Metrics & Amdahl’s Law
Question no.2: A computational task consists of 80% parallelizable operations and 20%
inherently sequential operations.
a) Calculate the maximum theoretical speedup if the system uses 16 processors.
b) What would be the speedup if the number of processors increases to 64?
c) Analyze whether increasing the number of processors beyond 64 provides any significant
improvement in speedup.
Single vs. Multiple Program Performance & Benchmarks
Question no.3: Compare the performance evaluation of single-program execution versus
multiple-program execution in parallel computing. Identify and explain the significance of two
widely used benchmarking techniques for assessing parallel processor performance.
Parallel Processor Organization and Topology
Question no.4: Discuss the advantages and limitations of shared memory multiprocessors and
distributed memory networks in terms of scalability and data consistency.
Matrix Multiplication Algorithms
Question no.5: Write a program code to implement parallel matrix multiplication using
OpenMP for shared memory systems.
Sorting Large Datasets in a Financial Institution
Question no.6: A banking system needs to process and sort millions of daily transactions.
Using parallel sorting algorithms, the bank aims to reduce execution time and improve real-time
fraud detection.
1.Which parallel sorting algorithm (e.g., Parallel Merge Sort, Parallel QuickSort) would be
most efficient for sorting high-volume financial data? Justify your choice.
2. Implement Parallel Merge Sort using OpenMP or MPI to demonstrate how transaction data
can be processed faster.
Load Balancing & Task Scheduling
Question no.7: Discuss dynamic and static task scheduling techniques and their impact on
resource utilization in distributed systems. Propose a real-world scenario where effective load
balancing improves overall system performance
Edge Computing for IoT-based Smart Cities
Question no.8: A smart city project aims to process real-time traffic data using Edge and Fog
Computing to optimize traffic light scheduling.
1. What are the key advantages of Edge Computing over traditional cloud computing in smart
city applications?
2. Implement a simple Python-based task scheduling model for optimizing traffic signal timing
in an IoT-enabled smart city. Cloud Security Services
Cloud Security Services
Question no.9: Analyze the role of Cloud Security Services such as identity management,
multi-factor authentication, and firewalls in securing cloud infrastructures.
Parallelism in Cloud Platforms
Question no.10: Explain the role of MapReduce and Apache Spark in processing large-scale
data in the cloud.
