This document discusses a supercomputer called HYPE-2 built by Santosh Pandey, Ram Sharan Chaulagain, and Prakash Gyawali under the supervision of Prof. Dr. Subarna Shakya. It provides an overview of multiprocessor and multicore systems and discusses how HYPE-2 uses a distributed memory architecture with dynamic scaling to achieve high performance computing capabilities for research applications like cryptography, data mining, and weather forecasting. Performance tests showed near-linear speedup as nodes were added, with the system able to handle complex computations through inter-process communication, though it is not as powerful as larger supercomputers.

1. Santosh Pandey
Ram Sharan Chaulagain
Prakash Gyawali
- A supercomputer( HYPE -2 )
Supervisor
Prof. Dr. Subarna Shakya

5. OUR OPTIONS:
MULTIPROCESSOR SYSTEM MULTICOMPUTER SYSTEM

7.  Speedup in multiprocessing
 Depends on parallelizable code
S(P)=Speedup on P processors
T(1)=Time to process in 1 processors
T(P)= Time to process in processors
f=Inherently sequential code
p= Parallelizable code

8.  High performance computing for research
 Achieving super computing at a cheaper rate
than mainframes

9.  Muni Sakhya (1980’s)
 16 nodes
 First and the only one

11.  Middleware
 Network Architecture
 Multicore Computers

13.  SIMD (Single Instruction Multiple Data)
 MIMD (Multiple Instruction Multiple Data)

14.  Every application don’t have same parallelism model
 Specific Applications must be programmed
 Extend Methods of our Architecture

17.  Dynamic Worker Addition and Reduction
 Fault Tolerant
 Scalable System

19. Star Topology

20.  Parallel Working

21.  Server Thread for each Worker at Server side
 New Process for each Worker at Client side
SERVER
THREAD1
• Provide Chunk 1 To Client1
THREAD 2
• Provide Chunk 2 To Client2
THREAD
N
• Provide Chunk N To Client N
Connect
to server
Take chunk
to process
Process
Provide
output to
server
Connect
to server
Take chunk
to process
Process
Provide
output to
server
Connect
to server
Take chunk
to process
Process
Provide
output to
server

22.  Running thousands of flops operations
 Integration for finding the value of Pi

24. Time (ms)
0
10000
20000
30000
40000
50000
1,4
1,3
2,1
3,1
3,2
3,3
4,3
Time (ms)

25. 1(10000) 2(20000) 5(50000) 7(70000) 15(150000)
Speedup 1 1.954 4.8 5.9 18
1
1.954
4.8
5.9
18
-5
0
5
10
15
20
25
Speedup
No. of Nodes
Speedup for 100 Million Iterations
Fig : Exponential Speedup

26. 1(10000) 2(20000) 5(50000) 7(70000)15(150000)
Speedup 1 1.954 4.8 5.9 18
1
1.954
4.8
5.9
18
-5
0
5
10
15
20
25
Speedup
No. of Nodes
Speedup for 100 Million Iterations
Theory vs. Practical Data

27.  No official data for comparing
 Probably the fastest in Nepal

28.  Cryptography
 Data Mining
 Weather Forecasting
 Research
 Artificial Intelligence

33.  Not comparable with bigger super computer due to
less nodes
 Extension of Architecture library to define new
application

34.  Supporting Complex Computations
 Inter-process Communication for dependent tasks
 Implementing GPU for Computation

35. Websites:
 Don Berker. Robert G. Brown. Greg Lindahl. Forrest Hoffman.
Putchong Uthayopas. Kragen Sitaker. Frequently Asked Questions
[Online]. Available: http://www.beowulf.org/overview.faq.html
 Technopedia. Computer Cluster [Online]. Available:
http://www.technopedia.com/definition/6581/computer-cluster
 Dr. Wu-chun. Feng. (2015). The Green500 list- November 2015 [Online].
Available: http://www.green500/list/green201511
Books:
 Shiflet, Introduction to Computational Science: Modeling and
Simulation for Sciences, Princeton University Press, 2014.
 Kumar, Lenina, MATLAB: Easy Way to Learning, PHI Learning, 2016.
 Etter, Introduction to MATLAB, Prentice Hall, 2015
 Lemay Laura, Charles L. Perkins, Teach Yourself Java in 21 Days,
Samsnet, 1996.