Scribd
Upload
1K views3 pages

HPC Question Bank From SNGCE, Kadayirippu

This document contains 5 modules that cover topics in parallel processing and high performance computing. Module 1 defines key terms and concepts in parallel processing like parallelism and Flynn's classification of parallel systems. It also covers techniques for achieving parallelism in uniprocessor systems and evaluating performance of high performance computers. Module 2 focuses on pipeline processors, including classification, design, handling hazards, and examples. Module 3 discusses SIMD (Single Instruction Multiple Data) computers, interconnection networks, and associative array processing. Module 4 covers multiprocessor systems, synchronization methods, and parallel languages. The final module describes dataflow architectures like token store machines and the Irvine dataflow computer.

Uploaded by

Celex Varghese
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
1K views3 pages

HPC Question Bank From SNGCE, Kadayirippu

This document contains 5 modules that cover topics in parallel processing and high performance computing. Module 1 defines key terms and concepts in parallel processing like parallelism and Flynn's classification of parallel systems. It also covers techniques for achieving parallelism in uniprocessor systems and evaluating performance of high performance computers. Module 2 focuses on pipeline processors, including classification, design, handling hazards, and examples. Module 3 discusses SIMD (Single Instruction Multiple Data) computers, interconnection networks, and associative array processing. Module 4 covers multiprocessor systems, synchronization methods, and parallel languages. The final module describes dataflow architectures like token store machines and the Irvine dataflow computer.

Uploaded by

Celex Varghese
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/ 3

Question Bank

MODULE 1

1. Define parallelism and high performance computing.


2. Define uniprocessor system, multiprocessing system and parallel processing
system.
3. Explain the concept of multiprogramming and time sharing system.
4. Explain different techniques developed in uniprocessor systems to achieve
parallelism.
5. How to evaluate the performance of High performance computers?
6. Explain the different programmatic levels of parallel processing.
7. What is spatial parallelism?
8. State Fengs scheme of parallel processing.
9. Explain Flynns classification of parallel processing system with neat
diagrams.
10. Explain the significance of Fengs classification of computers.
11. Explain the Indian contribution to parallel processing.
12. Explain the three architectural classification schemes briefly.

Module 2
1. What are the classification of pipeline processors?
2. Short note on General Pipeline.
3. What is dynamic pipelining.Give one example.
4. Define vectorizing compiler and vectorization.
5. What is instruction pre-fetch and branch handling.
6. Explain with example, how PREFETCH and BRANCH are handled.
7. Explain the classification of pipeline processors in detail.
8. Explain the design of pipelined instruction unit.
9. Explain the principles of pipelining.
10. Explain the design of Arithmetic pipeline unit.
11. Design a floating point adder with four processing stages.
12. Write on different parallel processing applications in various fields.
13. Draw the diagram of a pipelined multiplier using CSA tree and explain its
working.

14. What is internal forwarding and register tagging?


15. Explain the three classes of data dependent hazards. How the hazards can be
avoided ?
16. Explain vector processing.
17. Define vectorizing compiler and vectorization.
Module 3
1. How to characterize a SIMD computer?
2. List the differences between static and dynamic networks.
3. Explain mesh connected network in detail.
4. Explain SIMD array processor in detail.
5. Explain associative array processing in detail.
6. What are interconnection networks?
7. Explain with figure on omega network.
8. Explain the features of various associative memory organizations.
9. Explain masking and data routing mechanisms.
10. What is multicache problem? Explain different methods to solve cache
coherence.
11. Explain with figures mesh connected networks with its routing functions
12. Explain routing functions of Barrel shifters.
13. Explain SIMD array processors in detail.
14. Discuss the various aspects of Matrix multiplication algorithm for SIMD
15. Write notes on
a) SIMD matrix multiplication.
b) Parallel sorting on array processors.

Module 4
1. What are loosely coupled and tightly coupled multiprocessors ?
2. Explain the working of loosely coupled multiprocessor systems, with the help
3.
4.
5.
6.
7.

of a diagram.
Explain the working of a hierarchically structured multiprocessor.
Explain various process synchronization methods.
How parallelism in programs are detected ?
Explain all process synchronization mechanisms.
Discuss the characteristic features of parallel languages..

8. What are the various bus arbitration algorithms employed to control access to
time shared bus ?
9. What are the usual assumptions made regarding critical regions?
10. Explain inter process communication mechanisms and read prevention
methods.
Module 5
1. Differentiate dataflow and control flow computers.
2. What is a token store machine?
3. Explain the advantages and disadvantages of data flow computers.
4. Explain the working of Irvine data flow computers.
5. How does data flow graph helps in the design of data flow computers?
6. How the data flow computers differ from conventional computers?
7. Explain different data flow architecture.
8. Write short note on design alternatives to data flow approach.
9. Discuss the advantages of any two data driven languages
10. Explain Dennis Machine
11. Explain Arvind machine
12. Differentiate between static and dynamic data flow computers

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy