an insight into signify design and framework for distributed signal processing system by
DESCRIPTION
An Insight into SIGNIFY Design and Framework for Distributed Signal Processing System By Kirti Chawla Mentor & Guide Dr. R. S Anand Asst. Professor, Dept. Of Electrical Engineering, IIT - Roorkee. Introduction. Contents. Introduction Brief view Problem definition - PowerPoint PPT PresentationTRANSCRIPT
An Insight
into
SIGNIFY
Design and Framework for Distributed Signal Processing System
By
Kirti Chawla
Mentor & Guide
Dr. R. S AnandAsst. Professor, Dept. Of Electrical Engineering, IIT - Roorkee
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
• Background• Work done at MIT• Work done at University of California-Berkeley
• Associated fields• Distributed Systems• Sensor Networks• Digital Signal Processing• Computer Networks• Wireless Communication
• Domain & nature of Research• Hardware (Motes, RF …)• Software (Ad-Hoc Networks, Software Architecture …)
• Issues• Hardware (Computation Backbone, Motes …)• Software (Routing, Security …)
Introduction
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
• “Distributed – ness”
• Collaborative Vs Distributed Signal Processing
• Tradeoffs
Brief View
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
• Distributed Arithmetic
• A brief example of approach
• Scalability and Robustness
Problem Definition
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
• Process level distributed signal processing
• Operation level distributed signal processing
• Limitations
• Advantages
Process level Vs Operation level
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
System Architecture
• Challenges/Design considerations
• Amount of data• Method of acquisition• Nature of operating environment• Transparency• Active or passive data• Data-routing• User-interfaces• Security• Status identification• Job identification• Visualization of data
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
System Architecture
Existing sensor-network
…
Data-collection points
Computation server
• System Overview
…
Signal data router
…
Processing elements
Layer 2
Layer 1
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
• System Overview
System Architecture
DPMS
SPS FDS WDS
Client
GPS
Legend • SPS – Signal Processing Server• FDS – Filter Design Server• WDS – Window Design Server• GPS – Graphics Processing Server• DPMS – Distributed Processing Management Server
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
• Detailed specification
System Architecture
ConnectionManagementComponent
SignalProcessingFunctions
SystemLog
Component
Layer 2Server
Communication
SPS
WDS
1
ConnectionManagementComponent
FilterDesign
Functions
SystemLog
Component
FDS
ConnectionManagementComponent
Graphics &Plot
Functions
SystemLog
Component GPS
ConnectionManagementComponent
WindowDesign
Functions
SystemLog
Component
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
• Detailed specification
System Architecture
Layer 1Server
Communication1
ConnectionManagementComponent
SystemLog
Component
RequestRouting
Component
DPMS
Client
SystemShell
Component
SystemLog
Component
ConnectionManagementComponent
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
• Hardware & software specification
System Architecture
PARAM 10000
SPS FDS WDS DPMS
X86-P4
GPS Client
Hostnamee250b e250d e250c e250a
Infiniti Intellix
IP-Address 192.9.204.210 (e250a)
192.9.204.211 (e250b)
192.9.204.212 (e250c)
192.9.204.213 (e250d)
192.168.124.224 (Infiniti)
192.168.124.225 (Intellix)
Net mask255.255.255.0 (alias) 255.255.255.0 (alias)
ProcessorSUN Enterprise 250 Processor @ 400
MHz, total nodes – 8INTEL P4 processor @
1.6 GHz
Operating System Solaris 8 Linux 7.1
LanguageC, with MPI, network & math library C with network & math
library
RoleSignal processing & Routing Plotting & client interface
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
How it is done ?
Client
DPMS
SPS FDS WDS GPS
Job
Signal Data Router
Client Information
Packet&
Signal Data
Legend
Connections
Possible flows
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
How it is done ?
• VISION Scripting Language
STARTROUTE: <name of aggregate server>FILE: <data-file name>OPCODE: <operation code>END
Example: (Perform convolution on data-sets)
STARTROUTE: SPSFILE: DATA.SIGNIFYOPCODE: SIGNIFY_CONEND
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
How it is done ?
• Client Information Packet
Hostname IP – address CPU – type file – type client – id opcode
• System modules
Security module Signal catching module Message passing module
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
How it is done ?
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
How it is done ?
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
How it is done ?
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
Results
Output of Signal Processing Server
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
Results
Conditions & Observations
1. The tests suggest the time taken by Signal Processing Server for performing standard operations, when considered serially.2. Data-sets are increased linearly.3. The tests serves provides means to assess performance of standard operations and provide directions to optimizations .
Signal Processing Server Output
00.20.40.60.8
1
1 2 3 4 5
Data Sets in 100
Tim
e in
se
co
nd
s
Convolution
DFT
IDFT
FFT
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
Results
Output of Window Design Server
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
Results
Window Design Server Output
0
0.1
0.2
0.3
1 2 3 4 5
Data Sets in 100T
ime
in s
ec
on
ds
BartlettWindow
BlackmanWindow
HanningWindow
HammingWindow
Conditions & Observations
1. The tests suggest the time taken by Window Design Server for performing standard operations, when considered serially.2. Data-sets are increased linearly.3. The tests serves provides means to assess performance of standard operations and provide directions to optimizations .
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
Conclusion
The traditional approach of Signal Processing posesa lot of questions, that needs to be sorted out.
The suggested approach presents a novel way to utilizelegacy systems and open software framework
to achieve the computational gains comparable tohigh end uni-processor system.
The system also presents scalable architecture,so that more processors can be utilized
to achieve better results.
The system is also suitable for heterogeneousenvironment utilizing blend of processors
and operating environments.
The system utilizes computationally intensive sub-setof all algorithms to test the load and stress onthe system for checking overall performance.
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
Further work
• Enabling operation-level “distributed-ness”• Programming specifications for signal processing operations• Construction of FDS & GPS• Tweaking software architecture for performance• Enabling connectivity with sensor-networks
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
References
[1] Li. Lee, “Distributed Signal Processing”, Ph.D. Thesis, Department Of Electrical Engineering, M.I.T., June 2000.[2] Pradeep S. Sinha, “Distributed Operating System”, pp 1-10, IEEE Press, 1983.[3] John G. Proakis and Dimitris G. Manolakis, “Digital Signal Processing – Principles, Algorithms & applications”, Prentice Hall Of India, Jan 2000[4] J.D Ullman and J.E Hopcroft, “Introduction to Automata Theory”, Addison Wesley, 1999.[5] A.S Tanenbaum, “Computer Networks”, 3rd edition, Prentice Hall Of India, 2000.[6] David E. Culler, Jaswinder Pal Singh and Anoop Gupta, “Parallel Computer Architecture – A hardware / software approach”, Morgan Kaufman – Elsevier Science India, 2002.[7] Roman Kuc, “Introduction to Digital Signal Processing”, 1st edition, McGraw Hill, 1988.[8] W. Richard Stevens, “UNIX Network Programming, Network APIs : Sockets & XTI”, Volume 1, 3rd edition, Addison Wesley, 1999.[9] Brian W. Kerninghan and Dennis M. Ritchie, “The C programming language”, 2nd edition, Prentice Hall Of India, 1999.[10] W. Richard Stevens, “Advanced Programming in UNIX environment”, 2nd edition, Addison Wesley, 1999.[11] Haluk Topcuoglu, Salim Hariri and Min-You Wu, “Performance-Effective and low-cost task scheduling for Heterogeneous computing”, IEEE Transactions on Parallel and Distributed Systems, Vol. 13. No.3, pp 260- 261, March 2002.[12] Center for Development of Advanced Computing, “C-MPI user’s manual”, pp 1-15 1998.
Contents
• Introduction
• Brief view
• Problem definition
• Process level Vs Operation Level
• System Architecture
• How it is done ?
• Results
• Conclusion
• Further work
• References
References
[13] Code composer studio: dspvillage.ti.com/docs/catalog/devtools
[14] Berkley’s SensorWeb Project : www.eecs.berkeley.edu
[15] Khoral Package : www.khoral.com
[16] National Science Foundation : www.nsf.gov
[17] Defense Advanced Research Project Agency : www.darpa.mil
[18] Xerox PARC : www.parc.xerox.com
[19] Xilinx Systems : www.xilinx.com
[20] Message Passing Interface : www.mpiforum.com
[21] PARAM 10000 : www.cdacindia.com/html/npsf/param10k/param1.asp