Presentation is loading. Please wait.

Presentation is loading. Please wait.

MIT Lincoln Laboratory 1 of 4 MAA 3/8/2016 Development of a Real-Time Parallel UHF SAR Image Processor Matthew Alexander, Michael Vai, Thomas Emberley,

Published byAdrian Ryan Modified over 8 years ago

Similar presentations

Presentation on theme: "MIT Lincoln Laboratory 1 of 4 MAA 3/8/2016 Development of a Real-Time Parallel UHF SAR Image Processor Matthew Alexander, Michael Vai, Thomas Emberley,"— Presentation transcript:

1 MIT Lincoln Laboratory 1 of 4 MAA 3/8/2016 Development of a Real-Time Parallel UHF SAR Image Processor Matthew Alexander, Michael Vai, Thomas Emberley, Stephen Mooney, Joseph Rizzari HPEC 2010 September 16, 2010 This work is sponsored by the Army under Air Force Contract FA8721-05-0002. Opinions, interpretations, conclusions and recommendations are those of the authors and are not necessarily endorsed by the United States Government.

2 MIT Lincoln Laboratory 2 of 4 MAA 3/8/2016 Problem Statement Objective: Design and develop a real-time parallel SAR image processing system for rapid integration on an airborne Dash-8 platform Method: Use Open System Architecture real-time development methodology to produce a parallel image processing system that executes on ruggedized COTS hardware Programmatic constraints: Size, weight, and power (SWaP) 1500 lbs, 10kW Demanding real-time requirement SAR image formation and change detection in less than 10 minutes Schedule 18 months

3 MIT Lincoln Laboratory 3 of 4 MAA 3/8/2016 Open Architecture Development Methodology Intel (Matlab) Intel (parallel C++) Intel (parallel Matlab) Intel (C++) Focus: Algorithm development Computational optimizations Signal processing code C++ code Parallel mapping Signal processing code Serial processing development: 1.Finalize Matlab signal processing stream 2.Convert Matlab code to serial C/C++ code Parallel processing development: 1.Parallelize Matlab code using pMatlab to determine optimal mappings 2.Convert serial C/C++ code to parallel C/C++ code (use pMatlab maps) Open Architecture Development Methodology enables rapid prototyping Middleware software allows for scalable infrastructure on different hardware configurations

4 MIT Lincoln Laboratory 4 of 4 MAA 3/8/2016 Results Software Integration Lab Systems Integration Lab Twin OtterDash-8 Test Strategy Intel (Matlab) 10 hours Intel (parallel C++) 10 minutes Intel (C++) Intel (Parallel Matlab) 136 Intel cores perform real-time image processing within programmatic constraints - 1.632 TFLOPS throughput - 544 Gbytes Memory - 10 Tbytes storage

Download ppt "MIT Lincoln Laboratory 1 of 4 MAA 3/8/2016 Development of a Real-Time Parallel UHF SAR Image Processor Matthew Alexander, Michael Vai, Thomas Emberley,"

Similar presentations

The HPEC Challenge Benchmark Suite

The HPEC Challenge Benchmark Suite
Clare Smtih SHARC Presentation1 The SHARC Super Harvard Architecture Computer.

Clare Smtih SHARC Presentation1 The SHARC Super Harvard Architecture Computer.
Accelerators for HPC: Programming Models Accelerators for HPC: StreamIt on GPU High Performance Applications on Heterogeneous Windows Clusters

Accelerators for HPC: Programming Models Accelerators for HPC: StreamIt on GPU High Performance Applications on Heterogeneous Windows Clusters
Yaron Doweck Yael Einziger Supervisor: Mike Sumszyk Spring 2011 Semester Project.

Yaron Doweck Yael Einziger Supervisor: Mike Sumszyk Spring 2011 Semester Project.
Andrew Prout, William Arcand, David Bestor, Chansup Byun, Bill Bergeron, Matthew Hubbell, Jeremy Kepner, Peter Michaleas, Julie Mullen, Albert Reuther,

Andrew Prout, William Arcand, David Bestor, Chansup Byun, Bill Bergeron, Matthew Hubbell, Jeremy Kepner, Peter Michaleas, Julie Mullen, Albert Reuther,
K-means clustering –An unsupervised and iterative clustering algorithm –Clusters N observations into K clusters –Observations assigned to cluster with.

K-means clustering –An unsupervised and iterative clustering algorithm –Clusters N observations into K clusters –Observations assigned to cluster with.
Real-Time Video Analysis on an Embedded Smart Camera for Traffic Surveillance Presenter: Yu-Wei Fan.

Real-Time Video Analysis on an Embedded Smart Camera for Traffic Surveillance Presenter: Yu-Wei Fan.
A many-core GPU architecture.. Price, performance, and evolution.

A many-core GPU architecture.. Price, performance, and evolution.
Characteristics of Realtime and Embedded Systems Chapter 1 6/10/20151.

Characteristics of Realtime and Embedded Systems Chapter 1 6/10/20151.
Science Advisory Committee Meeting - 20 September 3, 2010 Stanford University 1 04_Parallel Processing Parallel Processing Majid AlMeshari John W. Conklin.

Science Advisory Committee Meeting - 20 September 3, 2010 Stanford University 1 04_Parallel Processing Parallel Processing Majid AlMeshari John W. Conklin.
Device Driver for Generic ASC Module - Project Presentation - By: Yigal Korman Erez Fuchs Instructor: Evgeny Fiksman Sponsored by: High Speed Digital Systems.

Device Driver for Generic ASC Module - Project Presentation - By: Yigal Korman Erez Fuchs Instructor: Evgeny Fiksman Sponsored by: High Speed Digital Systems.
HPEC_GPU_DECODE-1 ADC 8/6/2015 MIT Lincoln Laboratory GPU Accelerated Decoding of High Performance Error Correcting Codes Andrew D. Copeland, Nicholas.

HPEC_GPU_DECODE-1 ADC 8/6/2015 MIT Lincoln Laboratory GPU Accelerated Decoding of High Performance Error Correcting Codes Andrew D. Copeland, Nicholas.
Cross Strait Quad-Regional Radio Science and Wireless Technology Conference, Vol. 2, p.p. 980 – 984, July 2011 Cross Strait Quad-Regional Radio Science.

Cross Strait Quad-Regional Radio Science and Wireless Technology Conference, Vol. 2, p.p. 980 – 984, July 2011 Cross Strait Quad-Regional Radio Science.
On Chip Nonlinear Digital Compensation for RF Receiver Karen M. G. V. Gettings, Andrew K. Bolstad, Show-Yah Stuart Chen, Benjamin A. Miller and Michael.

On Chip Nonlinear Digital Compensation for RF Receiver Karen M. G. V. Gettings, Andrew K. Bolstad, Show-Yah Stuart Chen, Benjamin A. Miller and Michael.
BENCHMARK SUITE RADAR SIGNAL & DATA PROCESSING CERES EPC WORKSHOP 2008-10-01.

BENCHMARK SUITE RADAR SIGNAL & DATA PROCESSING CERES EPC WORKSHOP
© 2010 The MITRE Corporation. All rights reserved. Session 2: Many Core Sharon Sacco / The MITRE Corporation HPEC 2010 Approved for Public Release: 10-3292.

© 2010 The MITRE Corporation. All rights reserved. Session 2: Many Core Sharon Sacco / The MITRE Corporation HPEC 2010 Approved for Public Release:
 Fiber optic network in ring topology  Custom software implementing a Time Division Multiplexing (TDM) scheme  Documentation summarizing conclusions.

 Fiber optic network in ring topology  Custom software implementing a Time Division Multiplexing (TDM) scheme  Documentation summarizing conclusions.
Parallel MATLAB in production supercomputing with applications in signal and image processing Ashok Krishnamurthy David Hudak John Nehrbass Siddharth.

"Parallel MATLAB in production supercomputing with applications in signal and image processing" Ashok Krishnamurthy David Hudak John Nehrbass Siddharth.
999999-1 XYZ 10/2/2015 MIT Lincoln Laboratory Sidecar Network Adapters: Open Architecture for ISR Data Sources Craig McNally, Larry Barbieri, Charles Yee.

XYZ 10/2/2015 MIT Lincoln Laboratory Sidecar Network Adapters: Open Architecture for ISR Data Sources Craig McNally, Larry Barbieri, Charles Yee.
HPEC-1 MIT Lincoln Laboratory Session 3: Cloud Computing Albert Reuther/ MIT Lincoln Laboratory HPEC Conference 16 September 2010.

HPEC-1 MIT Lincoln Laboratory Session 3: Cloud Computing Albert Reuther/ MIT Lincoln Laboratory HPEC Conference 16 September 2010.

Similar presentations

Ads by Google