Scribd
Upload
4 views2 pages

BE Comp - High Performance Computing

This document is an examination paper for a High Performance Computing course, consisting of four questions from which candidates must choose to answer. Each question includes sub-questions covering topics such as SIMD and MIMD architectures, memory access types, data decomposition techniques, and load balancing mapping techniques. The exam is structured to assess knowledge in parallel computing and its applications, with a total duration of one hour and a maximum score of 30 marks.

Uploaded by

pritambpatil02
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 views2 pages

BE Comp - High Performance Computing

This document is an examination paper for a High Performance Computing course, consisting of four questions from which candidates must choose to answer. Each question includes sub-questions covering topics such as SIMD and MIMD architectures, memory access types, data decomposition techniques, and load balancing mapping techniques. The exam is structured to assess knowledge in parallel computing and its applications, with a total duration of one hour and a maximum score of 30 marks.

Uploaded by

pritambpatil02
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

Total No. of Questions : 4] SEAT No.

:
PA-10170 [Total No. of Pages : 2

: 25
[6010]-40

: 11
B.E. (Computer Engineering) (Insem)

09
HIGH PERFORMANCE COMPUTING

/04 71
(2019 Pattern) (Semester - VIII) (410250) (Theory)

23
8
/20
Time : 1 Hour]
.38 13 [Max. Marks : 30
0
Instructions to the candidates:
03
7.1 GP

1) Answer Q.1 or Q.2, Q.3 or Q.4.


2) Neat diagrams must be drawn wherever necessary.
CE
84

3) Figures to the right indicate full marks.


4) Assume suitable data, if necessary.
6

5
3.1

1:2
10

:1
Q1) a) Explain with suitable diagram SIMD, MIMD architecture. [4]
09
4/2 1
3
7
b) Explain the impact of Memory Latency & Memory Bandwidth on system
02
38

performance. [6]
4.3 01
3/0

c) Explain Message Passing Costs in Parallel Computers in parallel machines.


GP
80

[5]
CE

OR
8
7.1
6

:25
3.1

Q2) a) Describe Uniform-memory-access and Non-uniform-memory-access with


: 11
10

diagrammatic representation. [6]


09
/04 71

b) Describe the scope of parallel computing. Give applications of parallel


23

computing. [4]
8
/20
.38 13

c) Write a short note on (Any Two) [5]


0
03
7.1 GP

i) Dataflow Models
CE
84

ii) Demand Driven Computation

iii) Cache Memory


6
3.1
10

P.T.O.
Q3) a) Explain any three data decomposition techniques with examples. [6]
b) Explain different characteristics of tasks. [4]

: 25
: 11
c) Explain classification of Dynamic mapping techniques. [5]

09
/04 71
23
OR

8
/20
.38 13
0
Q4) a) What are mapping techniques for load balancing? Explain at least two
03
7.1 GP

mapping techniques. [4]


CE
84

b) Explain any three parallel algorithm models with suitable examples. [6]
c) Draw the task-dependency graph for finding the minimum number in the
6

5
3.1

sequence {4, 9, 1, 7, 8, 11, 2, 12} where each node in the tree represents

1:2
the task of finding the minimum of a pair of numbers. Compare this with
10

:1
09
serial version of finding minimum number from an array. [5]
4/2 1
3
7
02
38

 
4.3 01
3/0
GP
80
CE
8
7.1
6

:25
3.1

: 11
10

09
/04 71
23
8
/20
.38 13
0
03
7.1 GP
CE
84
6
3.1
10

[6010]-40 2

You might also like