Michael Reibel Boesen 1 , Didier Keymeulen 2 , Jan Madsen 1 , Thomas Lu 2 , Tien-Hsin Chao 2 1 : Technical University of Denmark 2 : NASA Jet Propulsion Laboratory November 3rd, 2010 Integration of the Self- Healing eDNA Architecture in an Embedded System and Evaluation of it Using a Fourier Transform Spectrometer Instrument Application 1
34
Embed
Michael Reibel Boesen 1, Didier Keymeulen 2, Jan Madsen 1, Thomas Lu 2, Tien-Hsin Chao 2 1 : Technical University of Denmark 2 : NASA Jet Propulsion Laboratory.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Michael Reibel Boesen1, Didier Keymeulen2, Jan Madsen1, Thomas Lu2, Tien-Hsin Chao2
1: Technical University of Denmark2: NASA Jet Propulsion Laboratory
November 3rd, 2010
Integration of the Self-Healing eDNA Architecture in an
Embedded System and Evaluation of it Using a Fourier Transform
Spectrometer Instrument Application
1
Big picture
2
eDNA: Self-healing hardware arch.DTU InformaticsMichael, Jan Madsen, Pascal Schleuniger
Fast design and impl. using CompactRIO for space instrumentsGreg Flesch (JPL)Didier Keymeulen (JPL)
Tunable Laser Spectrometer (MSL)
RampFFT AVG
Analogoutput
PowerPC, 800MHz, VxWorks
Analog
input
ADCDAC
FPGA Virtex540MHz clock
DAQ
CompactRIO
Liquid Crystal Waveguide-based Fourier Transform SpectrometerTien-Hsin Chao (JPL)Thomas Lu (JPL)Scott Davis (Vescent Photonics)George Farca (Vescent Photonics)
Motivation:Why Self-healing in Fourier Transform
Spectrometer
• Harsh environment increases probability of permanent & transient faults– Fault in control: Cause damage of instrument– Fault in data processing: Loss of vital science
data• Repairs impossible, high risk or very
expensive• Need for autonomous hardware self-
healing
3
Agenda
• eDNA: Self-healing hardware architecture• Case study application: Fourier Transform
Spectrometer• Hardware/software implementation &
CompactRIO• Self-healing of FTS: Control & data processing• Performance evaluation
4
NA
NA
NANA
NANA
NA
NA
NA
eDNA architecture overview
5
32
32
A
BμPRAM
Load S0,00Jump Z, SPLoad S0,01
Ribosomal DNA
Pkg in Pkg out
Communicationlayer
Control Layer
Computationalgranule
Computationlayer
eCell
eCell
eCell
eCell
eCell
eCell
eCell
eCell eCell
001010100100110
eDNAprog.
eDNA Compiler
6
while (b != 0) do if (b<a)then a = a – b else b = b – a endifendwhile
1
2
4
while
exp
if
Trans-lation
3
exp
Placement
eDNA program
Genome 1
Genome 2
Genome 3
Genome 4
Encoding
EXPR(a=a-b)
Data
Data
Start 1
Func.
Comm
1. Placement
2. Functionality
3. Communication• All eCells have
copy
=> Completely distributedarchitecture
ID ADDR
01 (1,1)
02 (2,1)
03 (1,2)
04 (2,2)
4
2
1
Comm. type Comm. target
Map
eDNA Self-reconfiguration
7
NA
NA
NANA
NANA
NA
NA
NA
(1,3)
(1,2)
(1,1)
(2,2)
(2,1)
(3,2)
(3,1)
(2,3) (3,3)
P1234
P1234
P1234
P1234
P1234
P1234
P1234
P1234
Pkg in Pkg out
P1234
ID ADDR
01 (1,1)
02 (2,1)
03 (1,2)
04 (2,2)
Genome 1
Genome 2
Genome 3
Genome 4
1. Addr relate to ID
2. ID relate to Genome
3. No genome => spare
eDNA Self-healing
1. Fault-detection: TMR-based algorithm: Cell C and spare detects fault at Cell F
2. Spare localization: Cell C locates closest spare-cell K
3. Self-reconfiguration: Broadcast table update– Effects: Function & Communication restoration and Isolation of faulty cell
1. Functionality restoration: “Moved” to (3,1):
2. Communication restoration: Now going to (3,1) instead of (1,1)
Case study:Liquid Crystal Waveguide-based Fourier Transform Spectrometer
10
FFT
Data Acquisition
Change OPD bychanging voltageon electrodes
Averaging
Prototype: SLD: 1450-1700nm, Resolution: 3-4nm
Ramp
Gas
• No moving parts
Fourier Transform Spectrometer HW/SW Integration on CompactRIO Platform
• HW: Real-time embedded controller architecture (CompactRIO) consisting of– PowerPC at 800MHz running VxWorks– Xilinx V5-LX110 FPGA– Analog input module– Analog output module
• High-level SW tool support: LabVIEW– FPGA synthesis: Graphical programming language– Integration of VHDL code– Integration of I/O
• Very fast path-to-flight• Design, test & prototype with hardware-in-the-loop (TRL 0-5)• Straight to deploy/flight: Using Honeywell hardware (TRL 6-9)
11
FTS HW/SW integrationMapping of components
12
eDNA
Self-healing hardware for FTSIntegration of eDNA onto CompactRIO (1)
13
eDNAVHDL code- Virtex 5
LabVIEW FPGA- Component Level IP Node
LabVIEWCLIP
XMLVHDLDescr.
TopLevelVHDLFile
Integrationin LabVIEWas regular I/O
Developer level
Self-healing hardware for FTSFTS data processing and control on eDNA
• SW Toolkit: Simulation, optimization and compilation env.
14
Write eDNA DownloadTranslate
Sim
FFT
AVG
Ramp
Self-healing hardware for FTSeDNA performance evaluation
• Focus– eDNA Execution time vs. LabVIEW FPGA
impl.– Self-healing time– Execution time before and after healing
• Note: No TMR fault detection yet
15
Self-healing hardware for FTSeDNA performance evaluation
• eDNA signals that an error occurred Data removed from dataset Advanced TMR-based protocol in-the-works
• Fairness of comparison?– eDNA: FPGA type platform on top of FPGA– FPGA-based prototype: What we have right
now16
Measurement LabVIEW eDNA
Execution time AVG 2.42 us 219 us
Self healing time N/A 110 us
Worst case recovery time N/A 1 sample lost
Area type Factor
# Slices 6x
# Flip-Flops 4x
# LUTs 6x
Self-healing hardware for FTSeDNA performance evaluation
17
(1,3)
(1,2)
(1,1)
(2,2)
(2,1)
(3,2)
(2,3) (3,3)(1,3)
(1,2)
(1,1)
(2,2)
(2,1)
(3,2)
(3,1)
(2,3) (3,3)
Autonomous
(3,1)
Self-healing hardware for FTSeDNA performance evaluation
Depends on cell placement
18
(1,3)
(1,2)
(1,1)
(2,2)
(2,1)
(3,2)
(2,3) (3,3)(1,3)
(1,2)
(1,1)
(2,2)
(2,1)
(3,2)
(3,1)
(2,3) (3,3)
Autonomous
(3,1)
Ramp results
19
Measurement LabVIEW eDNA
Execution time ramp 1 us 242 us
Self healing time N/A 110 us
Worst case recovery time N/A 1 sample lost
Area type Factor
# Slices 6x
# Flip-Flops 4x
# LUTs 6x
DCT/FFT results
• FFT implemented using FFT.VI in LabVIEW
• eDNA DCT
20
Measurement LabVIEW eDNA
Execution time FFT/DCT 5.5ms 627.83ms to 42min
Self healing time N/A 123 us
Worst case recovery time N/A 1 sample lost
Conclusion (1)
• eDNA self-healing architecture demonstrated in real world application
• Fast integration of eDNA architecture into embedded real-time system
• Data processing and control functionality of FTS compiled into eDNA code
21
Conclusion (2)
• Autonomous self-healing functionality comes at a high-cost
• Future improvements to eDNA– Reduce immense communication overhead
between cells in eDNA architecture– Replace 8-bit Xilinx PicoBlaze with ASIP– HW implementation of fault-detection
mechanism• Self-healing time: A fraction of execution
• eDNA architecture:– Michael R. Boesen, Jan Madsen - eDNA: A Bio-Inspired Reconfigurable
Hardware Cell Architecture Supporting Self-organisation and Self-healing, NASA/ESA Adaptive Hardware Systems (AHS’09) 2009, San Francisco.
– Michael R. Boesen, Pascal Schleuniger, Jan Madsen - Feasibility Study of a Self-healing Hardware Platform, Applied Reconfigurable Computing Conference (ARC’10), Bangkok.
• LCW-FTS:– Chao, T., Lu, T., Davis, S. R., Rommel, S. D., Farca, G., Luey, B., Martin, A. and
Anderson, Michael: Compact Liquid Crystal Waveguide Based Fourier Transform Spectrometer for In-Situ and Remote Gas and Chemical Sensing, Society of Photographic Instrumentation Engineers (SPIE) 2008.