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,

Slides:

Advertisements

Similar presentations

The HPEC Challenge Benchmark Suite

Advertisements

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

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,

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.

A many-core GPU architecture.. Price, performance, and evolution.

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.

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.

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.

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:

 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.

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.

Software Pipelining for Stream Programs on Resource Constrained Multi-core Architectures IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEM 2012 Authors:

REXAPP Bilal Saqib. REXAPP  Radio EXperimentation And Prototyping Platform Based on NOC  REXAPP Compiler.

© 2001 Mercury Computer Systems, Inc. Real-Time Geo- Registration on High-Performance Computers Alan Chao Monica Burke ALPHATECH, Inc. High Performance.

MIT Lincoln Laboratory hch-1 HCH 5/26/2016 Achieving Portable Task and Data Parallelism on Parallel Signal Processing Architectures Hank Hoffmann.

HPEC_NDP-1 MAH 10/11/2015 MIT Lincoln Laboratory Efficient Multidimensional Polynomial Filtering for Nonlinear Digital Predistortion Matthew Herman, Benjamin.

Slide 1 MIT Lincoln Laboratory Toward Mega-Scale Computing with pMatlab Chansup Byun and Jeremy Kepner MIT Lincoln Laboratory Vipin Sachdeva and Kirk E.

RASAR Program Real-time Autonomous Synthetic Aperture Radar Objective: Develop a

Radar Pulse Compression Using the NVIDIA CUDA SDK

LATA: A Latency and Throughput- Aware Packet Processing System Author: Jilong Kuang and Laxmi Bhuyan Publisher: DAC 2010 Presenter: Chun-Sheng Hsueh Date:

CRISP & SKA WP19 Status. Overview Staffing SKA Preconstruction phase Tiered Data Delivery Infrastructure Prototype deployment.

Cousins HPEC 2002 Session 4: Emerging High Performance Software David Cousins Division Scientist High Performance Computing Dept. Newport,

Issues Autonomic operation (fault tolerance) Minimize interference to applications Hardware support for new operating systems Resource management (global.

Hardware Image Signal Processing and Integration into Architectural Simulator for SoC Platform Hao Wang University of Wisconsin, Madison.

HPEC2002_Session1 1 DRM 11/11/2015 MIT Lincoln Laboratory Session 1: Novel Hardware Architectures David R. Martinez 24 September 2002 This work is sponsored.

Haney - 1 HPEC 9/28/2004 MIT Lincoln Laboratory pMatlab Takes the HPCchallenge Ryan Haney, Hahn Kim, Andrew Funk, Jeremy Kepner, Charles Rader, Albert.

Nanco: a large HPC cluster for RBNI (Russell Berrie Nanotechnology Institute) Anne Weill – Zrahia Technion,Computer Center October 2008.

Template This is a template to help, not constrain, you. Modify as appropriate. Move bullet points to additional slides as needed. Don’t cram onto a single.

MIT Lincoln Laboratory SPP-HPEC09-1 BAM 12/5/2015 A Special-Purpose Processor System with Software-Defined Connectivity Benjamin Miller, Sara Siegal, James.

An Open Architecture for an Embedded Signal Processing Subsystem

Slide-1 Multicore Theory MIT Lincoln Laboratory Theory of Multicore Algorithms Jeremy Kepner and Nadya Bliss MIT Lincoln Laboratory HPEC 2008 This work.

Sponsored By Abstract 1 Ritamar Siurano – Undergraduate Student Prof. Domingo Rodriguez – Advisor Abigail Fuentes – Graduate StudentProf. Ana B. Ramirez.

Sponsored By Abstract 1 Ritamar Siurano – Undergraduate Student Prof. Domingo Rodriguez – Advisor Abigail Fuentes – Graduate Student Prof. Ana B. Ramirez.

Slide-1 Parallel MATLAB MIT Lincoln Laboratory Multicore Programming in pMatlab using Distributed Arrays Jeremy Kepner MIT Lincoln Laboratory This work.

Advanced Hardware/Software Optimization Techniques for Application Specific MCSoC m Yumiko Kimezawa Supervised by Prof. Ben Abderazek Adapted Systems.

HPEC HN 9/23/2009 MIT Lincoln Laboratory RAPID: A Rapid Prototyping Methodology for Embedded Systems Huy Nguyen, Thomas Anderson, Stuart Chen, Ford.

1 WRB 09/02 HPEC Lincoln Lab Sept 2002 Poster B: Software Technologies andSystems W. Robert Bernecky Naval Undersea Warfare Center Ph: (401) Fax:

Cray XD1 Reconfigurable Computing for Application Acceleration.

High Performance Flexible DSP Infrastructure Based on MPI and VSIPL 7th Annual Workshop on High Performance Embedded Computing MIT Lincoln Laboratory

PTCN-HPEC-02-1 AIR 25Sept02 MIT Lincoln Laboratory Resource Management for Digital Signal Processing via Distributed Parallel Computing Albert I. Reuther.

The objective of Nonlinear Equalization (NLEQ) is to extend the dynamic range of RF receivers by reducing in-band nonlinear distortions. This enables detection.

3 Copyright © 2006, Oracle. All rights reserved. Designing and Developing for Performance.

Daniele Lezzi Execution of scientific workflows on federated multi-cloud infrastructures IBERGrid Madrid, 20 September 2013.

HPEC-1 SMHS 7/7/2016 MIT Lincoln Laboratory Focus 3: Cell Sharon Sacco / MIT Lincoln Laboratory HPEC Workshop 19 September 2007 This work is sponsored.

George Viamontes, Mohammed Amduka, Jon Russo, Matthew Craven, Thanhvu Nguyen Lockheed Martin Advanced Technology Laboratories 3 Executive Campus, 6th Floor.

Atindra Mitra Joe Germann John Nehrbass

What Do Computers Do? A computer system is

Low-Cost High-Performance Computing Via Consumer GPUs

Parallel Matlab programming using Distributed Arrays

Albert I. Reuther & Joel Goodman HPEC Sept 2003

M. Richards1 ,D. Campbell1 (presenter), R. Judd2, J. Lebak3, and R

For Massively Parallel Computation The Chaotic State of the Art

Welcome: Intel Multicore Research Conference

FPGAs & Software Components

Many-core Software Development Platforms

Parallel Processing in ROSA II

Matthew Lyon James Montgomery Lucas Scotta 13 October 2010

Case Study Memory Controller مرتضي صاحب الزماني.

Multicore Programming in pMatlab using Distributed Arrays

IUPUI MURI SCHOOL OF ENGINEERING AND TECHNOLOGY

Deployment of SAR and GMTI Signal Processing on a Boeing 707 Aircraft using pMatlab and a Bladed Linux Cluster Jeremy Kepner, Tim Currie, Hahn Kim, Bipin.

Presentation transcript:

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 FA Opinions, interpretations, conclusions and recommendations are those of the authors and are not necessarily endorsed by the United States Government.

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

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

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 TFLOPS throughput Gbytes Memory - 10 Tbytes storage