Total No. of Questions : 4] SEAT No.

8
23
PA-10170 [Total No. of Pages : 2

ic-
[6010]-40

tat
3s
B.E. (Computer Engineering) (Insem)

9:0
HIGH PERFORMANCE COMPUTING

02 91
(2019 Pattern) (Semester - VIII) (410250) (Theory)

9:0
0
30
Time : 1 Hour]
3/0 13 [Max. Marks : 30
0
Instructions to the candidates:
4/2
.23 GP

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

2) Neat diagrams must be drawn wherever necessary.
E
80

3) Figures to the right indicate full marks.

8
C

23
4) Assume suitable data, if necessary.

ic-
16

tat
8.2

3s
Q1) a) Explain with suitable diagram SIMD, MIMD architecture. [4]
.24

9:0
91
49

9:0
b) Explain the impact of Memory Latency & Memory Bandwidth on system
30
30

performance. [6]
01
02

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

4/2
GP

[5]
3/0
CE

OR
80

8
23
.23

ic-
16

tat
Q2) a) Describe Uniform-memory-access and Non-uniform-memory-access with
8.2

3s

diagrammatic representation. [6]

.24

9:0
91

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

49

9:0

computing. [4]
30
30
01
02

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

4/2
GP

i) Dataflow Models
3/0
CE
80

ii) Demand Driven Computation

.23

iii) Cache Memory

16
8.2
.24

P.T.O.
49
 8
Q3) a) Explain any three data decomposition techniques with examples. [6]

23
ic-
b) Explain different characteristics of tasks. [4]

tat
3s
c) Explain classification of Dynamic mapping techniques. [5]

9:0
02 91
9:0
OR

0
30
3/0 13
0
Q4) a) What are mapping techniques for load balancing? Explain at least two
4/2
.23 GP

mapping techniques. [4]

E
80

b) Explain any three parallel algorithm models with suitable examples. [6]

8
C

23
ic-
c) Draw the task-dependency graph for finding the minimum number in the
16

tat
sequence {4, 9, 1, 7, 8, 11, 2, 12} where each node in the tree represents
8.2

3s
the task of finding the minimum of a pair of numbers. Compare this with
.24

9:0
serial version of finding minimum number from an array. [5]
91
49

9:0
30
30

 
01
02
4/2
GP
3/0
CE
80

8
23
.23

ic-
16

tat
8.2

3s
.24

9:0
91
49

9:0
30
30
01
02
4/2
GP
3/0
CE
80
.23
16
8.2
.24

[6010]-40 2
49
Total No. of Questions : 8] SEAT No. :

8
23
P-558 [Total No. of Pages : 2

ic-
[6004]-493

tat
7s
B.E. (Computer Engineering)

9:2
02 91
High Performance Computing

4:2
0
(2019 Pattern) (Semester - VIII) (410250)

31
7/0 13
0
Time : 2½ Hours] [Max. Marks : 70
6/2
.23 GP

Instructions to the candidates:

1) Answer Q.1 or Q.2, Q.3 or Q.4, Q.5 or Q.6, Q.7 or Q.8.
E
80

8
2) Neat diagrams must be drawn wherever necessary.
C

23
3) Figures to the right indicate full marks.

ic-
16

tat
8.2

7s
Q1) a) Explain with diagram One-to-all broadcast on an eight-node ring with
.24

9:2
91
recursive doubling technique. Node 0 is the source of the broadcast.
49

4:2
Also Explain all to one reduction with node 0 as destination. [7]
30
31

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

01
02

MPI. [6]
6/2
GP

c) Write a short note on prefix-sum operation. [4]

7/0
CE

OR
80

8
23
.23

Q2) a) What is all to all broadcast communication operation? Explain all to

all broadcast on an eight node ring with step wise diagrams. (Show ic-
16

tat
first two steps and last communication step). [7]
8.2

7s
.24

9:2

b) Explain scatter and gather communication operation with diagram. [6]

91
49

4:2

c) Explain circular shift operation? [4]

30
31
01
02

Q3) a) Explain parallel Matrix —Matrix multiplication algorithm with

6/2
GP

example? [7]
7/0

b) Explain different performance Metrics for Parallel Systems. [6]

CE
80

c) Explain Minimum Execution Time and Minimum Cost Optimal

.23

Execution Time. [4]

16
8.2

OR
.24
49

P.T.O.
Q4) a) What is granularity? What are effects of granularity on performance of

8
parallel systems? [7]

23
ic-
b) Explain various sources of overhead in parallel systems? [6]

tat
c) Explain “Scaling Down (downsizing)” a parallel system with example.

7s
[4]

9:2
02 91
4:2
0
Q5) a) What is CUDA? Explain different programming languages support in

31
7/0 13
CUDA. Discuss any three applications of CUDA. [8]
0
b) Describe processing flow of CUDA-C program with diagram. [6]
6/2
.23 GP

c) Explain the following terms in CUDA: device, host, device code,

E

Kernel. [4]
80

8
C

23
OR

ic-
16

Q6) a) Explain CUDA memory model. Discuss thread hierarchy. [8]

tat
8.2

7s
b) What is block dimension and grid dimension in CUDA? Write a CUDA
.24

9:2
kernel for addition of two vectors and explain how it will calculate addition
91
using threads. [6]
49

4:2
30

c) What is a Kernel in CUDA? What is kernel launch? Explain arguments

31

that can be specified in a Kernel launch. [4]

01
02
6/2
GP
7/0

Q7) a) Explain odd-even transportation in bubble sort using parallel

CE

formulation. Give one stepwise example solution using odd-even

80

8
23
transportation. [8]
.23

b) Explain Parallel Depth First Search algorithm in detail? ic-

[6]
16

tat
8.2

7s

c) What is Kubernets? Explain its features and applications. [4]

.24

9:2

OR
91
49

4:2

Q8) a) Write short notes on : [8]

30
31

i) Parallel Merge sort

01
02

ii) GPU applications

6/2
GP
7/0

b) What are the issues in sorting on parallel computers? Explain with

CE

appropriate example? [6]

80

c) Explain parallel BFS algorithm in brief.

.23

[4]
16
8.2


.24
49

[6004]-493 2
Total No. of Questions : 4] SEAT No. :

8
23
PB262 [Total No. of Pages : 1

ic-
[6270]-50

tat
B.E. (Computer Engineering) (Insem)

2s
HIGH PERFORMANCE COMPUTING

9:4
02 91
(2019 Pattern) (Semester - VIII) (410250)

3:3
0
Time : 1 Hour] [Max. Marks : 30

41
0/0 13
Instructions to the candidates:
0
1) Answer Q.1 or Q.2, Q.3 or Q.4.
3/2
.23 GP

2) Neat diagrams must be drawn wherever necessary.

3) Figures to the right side indicate full marks.
E
82

8
4) Assume suitable data necessary.
C

23
ic-
16

Q1) a) Explain the impact of Memory Latency & Memory Bandwidth on system

tat
8.2

performance? [6]

2s
.24

9:4
b) Write note on Communication costs in parallel machines? [5]
91
49

3:3
c) Explain with suitable diagram STMD, MIMD architecture? [4]
30
41

OR
01
02

Q2) a) Explain basic working principle of Super scalar Architecture? [6]

3/2
GP

b) Describe UMA and NUMA multicomputer platforms? [5]

0/0
CE

c) What is VLIW processor? Write any two advantages of VLIW? [4]

82

8
23
.23

Q3) a) Explain any three decomposition technique with example? ic-

[6]
16

tat
8.2

2s

b) Describe mapping technique for load balancing? [5]

.24

9:4

c) What are the characteristics of tasks. [4]

91
49

3:3

OR
30
41

Q4) a) Explain in details parallel algorithm models? [6]

01
02

b) Explain the different methods for Containing Interaction Overheads. [5]

3/2
GP

c) What are the characteristics of Inter-Task Interactions? [4]

0/0
CE
82
.23


16
8.2
.24
49
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
 https://www.rgpvonline.com

Total No. of Questions : 8] [1] [Total No. of Printed Pages : 1

Roll No ..................................

IT-722 (GS)
B.E. VII Semester Examination, June 2020
Grading System (GS)
High Performance Computing
Time : Three Hours
Maximum Marks : 70
Note: i) Attempt any five questions.
ii) All questions carry equal marks.
1. Discuss the architecture of high performance computing.
OR
Discuss programming models in high performance computing.

2. Describe the following term

a) Open MP
b) Programming paradigms and distributed memory processing.

3. Explain the Architectural configuration of parallel processing systems with block diagram.

4. a) Explain about caching.

b) Explain briefly:
i) Load balancing
ii) Sequential computing

5. Write short note on:

i) PVM
ii) UPC
iii) Petaflop programming

6. a) Explain the uses of temperal and spatial locality models.

b) Describe about computational grid with example.

7. Discuss the various issues to be faced in Cluster design.

8. Write a short notes (any two)

a) Loop invariants
b) Super scalar processors
c) Grid security infrastructure
d) Vector processing
******
IT-722 (GS)

https://www.rgpvonline.com