0% found this document useful (0 votes)
5 views

be_computer-engineering_semester-8_2024_may_high-performance-computing-hpc-2019-pattern

The document is an examination paper for a B.E. (Computer Engineering) course on High Performance Computing, consisting of 8 questions. Candidates are instructed to answer specific pairs of questions and must include diagrams where necessary. The paper covers topics such as communication operations, performance metrics, CUDA architecture, and parallel algorithms.

Uploaded by

trushitghetiya
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
5 views

be_computer-engineering_semester-8_2024_may_high-performance-computing-hpc-2019-pattern

The document is an examination paper for a B.E. (Computer Engineering) course on High Performance Computing, consisting of 8 questions. Candidates are instructed to answer specific pairs of questions and must include diagrams where necessary. The paper covers topics such as communication operations, performance metrics, CUDA architecture, and parallel algorithms.

Uploaded by

trushitghetiya
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Total No. of Questions: 8] SEAT No.

8
23
PB2256 [6263]-94
[Total No. of Pages :2

ic-
tat
B.E. (Computer Engineering)

5s
HIGH PERFORMANCE COMPUTING

1:2
(2019 Pattern) (Semester-VIII) (410250)

02 91
3:4
0
Time : 2½ Hours] [Max. Marks : 70

41
8/0 13
Instructions to the candidates:
1) Answer Q.1 or Q.2, Q.3 or Q.4, Q5 or Q6, Q7 or Q8.
0
5/2
2) Figures to the right indicate full marks.
.23 GP

3) Neat diagrms must be drawn wherever necessary.


4) Make suitable assumptions whenever necessary.
E
80

8
C

23
Q1) a) What is one-to-all broadcast? Explain it with the help of algorithm for

ic-
16

tat
one-to-all broadcast on hypercube. Comment on cost calculation. [7]
8.2

5s
b) Explain scatter and gather communication operation. [6]
.24

1:2
91
c) Explain circular shift operation. [4]
49

3:4
30

OR
41
01
02

Q2) a) Explain all to all broadcast and all to all reduction communication
5/2
GP

operation with example? Discuss cost analysis. [7]


8/0

b) Explain in detail Blocking and Non-Blocking Communication Using MPI.


CE
80

8
[6]

23
.23

c) Comment on “Improving the Speed of Communication Operations.”[4]


ic-
16

tat
8.2

5s
.24

1:2

Q3) a) Explain various sources of overhead in parallel systems. [7]


91
49

3:4

b) Show effect of granularity on performance with addition of n numbers on


30
41

p processing elements. [6]


01
02

c) Explain amdahl’s and gustafson’s law. [4]


5/2
GP

OR
8/0
CE
80

Q4) a) Explain different performance Metrics for Parallel Systems. [7]


.23

b) Explain parallel Matrix-Matrix multiplication algorithm with example. [6]


16

c) Comment on “Scalability of Parallel Systems”. [4]


8.2
.24

P.T.O.
49
8
Q5) a) Draw and explain CUDA architecture in details. [8]

23
b) Describe processing flow of cuda along with cuda c functions. [6]

ic-
c) Write advantages and limitations of CUDA. [4]

tat
5s
OR

1:2
Q6) a) Explain how the CUDA C program executes at the kernel level with

02 91
3:4
example. [8]

0
b) Explain cuda memory model in brief. [6]

41
c)
8/0 13
Write applications of cuda. [4]
0
5/2
.23 GP

Q7) a) What are the issues in sorting on parallel computers, explain with
E

example? [8]
80

8
C

23
b) Explain BFS for parallel execution & analyze its complexity. [6]

ic-
c) Write short note on Kubernets. [4]
16

tat
OR
8.2

5s
Q8) a) Compare an algorithm for sequential and parallel Merge sort. Analyze the
.24

1:2
91
complexity for the same. [8]
49

3:4
b) Explain Parallel Depth First Search algorithm in detail. [6]
30
41

c) Write short note on GPU Applications. [4]


01
02
5/2
GP
8/0


CE
80

8
23
.23

ic-
16

tat
8.2

5s
.24

1:2
91
49

3:4
30
41
01
02
5/2
GP
8/0
CE
80
.23
16
8.2
.24
49

[6263]-94 2

You might also like