Scribd
Upload
4 views3 pages

Question Paper Code:60435: Reg. No.

This document is an examination question paper for the M.Tech degree in Computer Science and Engineering, focusing on Multicore Architecture and Programming. It includes various questions on topics such as latency, bandwidth, parallel programming, OpenMP, MPI, and cache coherence. The paper is structured into three parts, with a total of 100 marks allocated across multiple questions requiring definitions, explanations, and programming examples.

Uploaded by

Vidhyaa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views3 pages

Question Paper Code:60435: Reg. No.

This document is an examination question paper for the M.Tech degree in Computer Science and Engineering, focusing on Multicore Architecture and Programming. It includes various questions on topics such as latency, bandwidth, parallel programming, OpenMP, MPI, and cache coherence. The paper is structured into three parts, with a total of 100 marks allocated across multiple questions requiring definitions, explanations, and programming examples.

Uploaded by

Vidhyaa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Reg. No.

Question Paper Code :60435


MEMTech. DEGREE EXAMINATIONS, NOVEMBERUDECEMBER 2023
Second Semester
Computer Science and Engineering
CP 4292- MULTICOREARCHITECTURE ANDPROGRAMMING
(Common to : M.Tech. Information Technology)
(Regulations 2021)
Time:Three hours Maximum: 100 marks
Answer ALL questions.
PART A (10 x 2 = 20 marks)

1 Define latency and bandwidth.


2. State Amdahl's law.

3. How data race occurs in parallel programming?


4. Define mutex.

5. Write a "Hello World" program using OpenMP.


6 What is loop carried dependencies?
programming.
7. Write the evaluation methods is distributed memory
8 What is wrapper script?
environment variables.
9 Name any two OpenMP
unpack?
10. What is the use of MPI pack and MPI

PART B-(5 x 13 = 65 marks)

architecture with a
11. (a) i) Outline the distributed shared memory
(6)
diagram.
interconnection networks (7)
ii) Explain in detail about
Or

multi-core architecture. (6)


(b) 6) Discuss in detail about the single and
programs.
() Outline the steps in designing and building parallel (7)
conditions for
deadlock and present an

12. (a) 6)
Explainthe four
parallel
computing
environment. example io
deadlock in a
(ii) Describethe communications procedure between threads in parale

programs.

Or

approaches andtools
for detecting data races.
List out the (6
(b) (0)(11) Explain how semaphores can be used to accomplish mutual
synchronization with example.
exclusion of parallel process (7
Discuss how data andfunctional parallelism are handled in shared
13. (a) ()
memory programming
with OpenMP. (6)
OpenMD
(1) With example, discuss about how loops are handled in
Or

(b) ) With suitable example, explain the library functions used in


OpenMP. (6)

(ii) Illustrate an OpenMP work sharing execution model with example.


()

14. (a) (1) State the difference between point-to-point and collective
communication in MPI. (6)
(ii) Explain the structure of MPIprogram with an example. (7)
Or

(b) ) Write a brief note on MPI derived datatypes. (6)


(iü) Describe the performance evaluation process of MPIprogram. (7)
15. (a) i) What does the n-body problem do? Give the pseudocode for n-body
solver. (6)
Gi) Write a note on thread paradigm and compare OpenMP and MPI
programming models. (7)

Or
(b) i) Discuss about the parallelizing the reduced solver using OpenMP.(6)
G) Explain about the implementation of tree search using MPI and
static partitioning. (7)

60435
PART C-(1 x 15 =15 marks)
(a) Define Cache Coherence problem. What are the two main approaches to
16. solve the cache coherence? Describe working of snooping cache and
explain directory-based coherence,
(15)
Or

Outline the process of parallelizing depth-first search algorithm using


(b) OnenMP with detailed example and elaborate the complete procedure.
(15)

60435
3

You might also like