Accelerating System Simulations
|
|
- Cornelia Montgomery
- 5 years ago
- Views:
Transcription
1 Accelerating System Simulations 김용정부장 Senior Applications Engineer 2013 The MathWorks, Inc. 1
2 Why simulation acceleration? From algorithm exploration to system design Size and complexity of models increases Time needed for a single simulation increases Number of test cases increases Test cases become larger Need to reduce simulation time during design simulation time for large scale testing during prototyping 2
3 MATLAB is quite fast Optimized and widely-used libraries BLAS Basic Linear Algebra Subroutines (multithreaded) LAPACK Linear Algebra Package JIT (Just In Time) Acceleration On-the-fly multithreaded code generation for increased speed Built-in support for vector and matrix operations 3
4 Application LTE Physical Downlink Control Channel (PDCCH) 4
5 Workflow Start with a baseline algorithm Profile it to introduce a performance yardstick Introduce the following optimizations: Better MATLAB serial programming techniques Using System objects MATLAB to C code generation (MEX) Parallel Computing GPU-optimized System objects Rapid Accelerator mode of simulation in Simulink 5
6 Simulation acceleration options in MATLAB Better MATLAB code User s Code System objects MATLAB to C Parallel Computing GPU processing 6
7 Profiling MATLAB algorithms Profiler summarizes MATLAB code execution total time spent within each function which lines of code use the most processing time Helps identify algorithm bottlenecks 7
8 Effective MATLAB programming techniques Example of pre-allocation y=[]; for n=1:len/tx G=[u(idx1(n)) u(idx2(n));... -conj(u(idx2(n))) conj(u(idx1(n)))]; y=[y;g]; end y=complex(zeros(len,tx)); y(idx1,1)=u(idx1); y(idx1,2)=u(idx2); y(idx2,1)=-conj(u(idx2)); y(idx2,2)=conj(u(idx1)); Pre-allocation Initialize an array using its final size Helps avoid dynamically resizing arrays in a loop Vectorization Convert code from using scalar loops to using matrix/vector operations Helps MATLAB leverage processor-optimized libraries for vector processing 8
9 Using System objects of DSP & Communications System Toolboxes Example of System objects System objects facilitate stream processing Can accelerate simulation because function s = Alamouti_DecoderS(u,H) %#codegen % STBC Combiner persistent htddec if isempty(htddec) htddec= comm.ostbccombiner(... 'NumTransmitAntennas',2,'NumReceiveAntennas',2); end s = step(htddec, u, H); Decouple declaration from the execution of the algorithms Reduce overhead of parameter handling in the loop Most of them implemented as MATLAB executables (MEX) 9
10 MATLAB to C code generation MATLAB Coder Automatically generate a MEX function Call the generated MEX file within testbench Verify same numerical results Assess the baseline function and the generated MEX function for speed 10
11 Parallel Simulation Runs Worker TOOLBOXES BLOCKSETS Worker Worker Worker Task 1 Task 2 Task 3 Task 4 >> Demo Time Time 11
12 Summary matlabpool available workers No modification of algorithm Use parfor loop instead of for loop Parallel computation or simulation leads to further acceleration More cores = more speed 12
13 Simulation acceleration options in MATLAB Better MATLAB code User s Code System objects MATLAB to C Parallel Computing GPU processing 13
14 What is a Graphics Processing Unit (GPU) Originally for graphics acceleration, now also used for scientific calculations Massively parallel array of integer and floating point processors Typically hundreds of processors per card GPU cores complement CPU cores Dedicated high-speed memory 14
15 Why would you want to use a GPU? Speed up execution of computationally intensive simulations For example: Performance: A\b with Double Precision 15
16 Ease of Use Options for Targeting GPUs 1) Use GPU with MATLAB built-in functions 2) Execute MATLAB functions elementwise on the GPU 3) Create kernels from existing CUDA code and PTX files Greater Control 16
17 Data Transfer between MATLAB and GPU % Push data from CPU to GPU memory Agpu = gpuarray(a) % Bring results from GPU memory back to CPU B = gather(bgpu) 17
18 GPU Processing with Communications System Toolbox Alternative implementation for many System objects take advantage of GPU processing Use Parallel Computing Toolbox to execute many communications algorithms directly on the GPU GPU System objects comm.gpu.turbodecoder comm.gpu.viterbidecoder comm.gpu.ldpcdecoder comm.gpu.pskdemodulator comm.gpu.awgnchannel Easy-to-use syntax Dramatically accelerate simulations 18
19 Example: Turbo Coding Impressive coding gain High computational complexity Bit-error rate performance as a function of number of iterations = comm.turbodecoder( NumIterations, numiter, 19
20 Acceleration with GPU System objects Version Elapsed time Acceleration CPU 8 hours GPU 40 minutes 12.0 Same numerical results Cluster of 4 GPUs 11 minutes 43.0 = comm.turbodecoder( comm.gpu.turbodecoder( NumIterations, N, = comm.awgnchannel( = comm.gpu.awgnchannel( 20
21 Key Operations in Turbo Coding Function CPU GPU Version 1 % Turbo Encoder htenc = comm.turboencoder('trellisstructure',poly2trellis(4, [13 15], 13),.. 'InterleaverIndices', intrlvrindices) % AWG Noise hawgn = comm.awgnchannel('noisemethod', 'Variance'); % BER measurement hber = comm.errorrate; % Turbo Decoder htdec = comm.turbodecoder( 'TrellisStructure',poly2trellis(4, [13 15], 13),... 'InterleaverIndices', intrlvrindices,'numiterations', numiter); % Turbo Encoder htenc = comm.turboencoder('trellisstructure',poly2trellis(4, [13 15], 13),.. 'InterleaverIndices', intrlvrindices) % AWG Noise hawgn = comm.awgnchannel('noisemethod', 'Variance'); % BER measurement hber = comm.errorrate; % Turbo Decoder htdec = comm.gpu.turbodecoder( 'TrellisStructure',poly2trellis(4, [13 15], 13),... 'InterleaverIndices', intrlvrindices,'numiterations', numiter); ber = zeros(3,1); %initialize BER output %% Processing loop while ( ber(1) < MaxNumErrs && ber(2) < MaxNumBits) data = randn(blklength, 1)>0.5; % Encode random data bits yenc = step(htenc, data); %Modulate, Add noise to real bipolar data modout = 1-2*yEnc; rdata = step(hawgn, modout); % Convert to log-likelihood ratios for decoding llrdata = (-2/noiseVar).*rData; % Turbo Decode decdata = step(htdec, llrdata); % Calculate errors ber = step(hber, data, decdata); end ber = zeros(3,1); %initialize BER output %% Processing loop while ( ber(1) < MaxNumErrs && ber(2) < MaxNumBits) data = randn(blklength, 1)>0.5; % Encode random data bits yenc = step(htenc, data); %Modulate, Add noise to real bipolar data modout = 1-2*yEnc; rdata = step(hawgn, modout); % Convert to log-likelihood ratios for decoding llrdata = (-2/noiseVar).*rData; % Turbo Decode decdata = step(htdec, llrdata); % Calculate errors ber = step(hber, data, decdata); end 21
22 Profile results in Turbo Coding Function CPU GPU Version 1 % Turbo Encoder <0.01 htenc = comm.turboencoder('trellisstructure',poly2trellis(4, [13 15], 13),.. 'InterleaverIndices', intrlvrindices) % AWG Noise <0.01 hawgn = comm.awgnchannel('noisemethod', 'Variance'); % BER measurement <0.01 hber = comm.errorrate; % Turbo Decoder <0.01 htdec = comm.turbodecoder( 'TrellisStructure',poly2trellis(4, [13 15], 13),... 'InterleaverIndices', intrlvrindices,'numiterations', numiter); % Turbo Encoder <0.01 htenc = comm.turboencoder('trellisstructure',poly2trellis(4, [13 15], 13),.. 'InterleaverIndices', intrlvrindices) % AWG Noise <0.01 hawgn = comm.awgnchannel('noisemethod', 'Variance'); % BER measurement <0.01 hber = comm.errorrate; % Turbo Decoder 0.02 htdec = comm.gpu.turbodecoder( 'TrellisStructure',poly2trellis(4, [13 15], 13),... 'InterleaverIndices', intrlvrindices,'numiterations', numiter); <0.01 ber = zeros(3,1); %initialize BER output %% Processing loop while ( ber(1) < MaxNumErrs && ber(2) < MaxNumBits) 0.30 data = randn(blklength, 1)>0.5; % Encode random data bits 2.33 yenc = step(htenc, data); %Modulate, Add noise to real bipolar data 0.05 modout = 1-2*yEnc; 1.50 rdata = step(hawgn, modout); % Convert to log-likelihood ratios for decoding 0.03 llrdata = (-2/noiseVar).*rData; % Turbo Decode decdata = step(htdec, llrdata); % Calculate errors 0.17 ber = step(hber, data, decdata); end <0.01 ber = zeros(3,1); %initialize BER output %% Processing loop while ( ber(1) < MaxNumErrs && ber(2) < MaxNumBits) 0.28 data = randn(blklength, 1)>0.5; % Encode random data bits 2.38 yenc = step(htenc, data); %Modulate, Add noise to real bipolar data 0.05 modout = 1-2*yEnc; 1.45 rdata = step(hawgn, modout); % Convert to log-likelihood ratios for decoding 0.04 llrdata = (-2/noiseVar).*rData; % Turbo Decode decdata = step(htdec, llrdata); % Calculate errors 0.17 ber = step(hber, data, decdata); end 22
23 Key Operations in Turbo Coding Function CPU GPU Version 2 % Turbo Encoder htenc = comm.turboencoder('trellisstructure',poly2trellis(4, [13 15], 13),.. 'InterleaverIndices', intrlvrindices) % AWG Noise hawgn = comm.awgnchannel('noisemethod', 'Variance'); % BER measurement hber = comm.errorrate; % Turbo Decoder htdec = comm.turbodecoder('trellisstructure',poly2trellis(4, [13 15], 13),... 'InterleaverIndices', intrlvrindices,'numiterations', numiter); %% Processing loop while ( ber(1) < MaxNumErrs && ber(2) < MaxNumBits) data = randn(blklength, 1)>0.5; % Encode random data bits yenc = step(htenc, data); %Modulate, Add noise to real bipolar data modout = 1-2*yEnc; rdata = step(hawgn, modout); % Convert to log-likelihood ratios for decoding llrdata = (-2/noiseVar).*rData; % Turbo Decode decdata = step(htdec, llrdata); % Calculate errors ber = step(hber, data, decdata); end % Turbo Encoder htenc = comm.turboencoder('trellisstructure',poly2trellis(4, [13 15], 13),.. 'InterleaverIndices', intrlvrindices) % AWG Noise hawgn = comm.gpu.awgnchannel ('NoiseMethod', 'Variance'); % BER measurement hber = comm.errorrate; % Turbo Decoder - setup for Multi-frame or Multi-user processing numframes = 30; htdec = comm.gpu.turbodecoder('trellisstructure',poly2trellis(4, [13 15], 13),... 'InterleaverIndices', intrlvrindices,'numiterations',numiter, NumFrames,numFrames); %% Processing loop while ( ber(1) < MaxNumErrs && ber(2) < MaxNumBits) data = randn(numframes*blklength, 1)>0.5; % Encode random data bits yenc = gpuarray(multiframestep(htenc, data, numframes)); %Modulate, Add noise to real bipolar data modout = 1-2*yEnc; rdata = step(hawgn, modout); % Convert to log-likelihood ratios for decoding llrdata = (-2/noiseVar).*rData; % Turbo Decode decdata = step(htdec, llrdata); % Calculate errors ber=step(hber, data, gather(decdata)); end 23
24 Profile results in Turbo Coding Function CPU GPU Version 2 % Turbo Encoder <0.01 htenc = comm.turboencoder('trellisstructure',poly2trellis(4, [13 15], 13),.. 'InterleaverIndices', intrlvrindices) % AWG Noise <0.01 hawgn = comm.awgnchannel('noisemethod', 'Variance'); % BER measurement <0.01 hber = comm.errorrate; % Turbo Decoder <0.01 htdec = comm.turbodecoder( 'TrellisStructure',poly2trellis(4, [13 15], 13),... 'InterleaverIndices', intrlvrindices,'numiterations', numiter); %% Processing loop while ( ber(1) < MaxNumErrs && ber(2) < MaxNumBits) 0.30 data = randn(blklength, 1)>0.5; % Encode random data bits 2.33 yenc = step(htenc, data); %Modulate, Add noise to real bipolar data 0.05 modout = 1-2*yEnc; 1.50 rdata = step(hawgn, modout); % Convert to log-likelihood ratios for decoding 0.03 llrdata = (-2/noiseVar).*rData; % Turbo Decode decdata = step(htdec, llrdata); % Calculate errors 0.17 ber = step(hber, data, decdata); end % Turbo Encoder <0.01 htenc = comm.turboencoder('trellisstructure',poly2trellis(4, [13 15], 13),.. 'InterleaverIndices', intrlvrindices) % AWG Noise 0.03 hawgn = comm.gpu.awgnchannel ('NoiseMethod', 'Variance'); % BER measurement <0.01 hber = comm.errorrate; % Turbo Decoder - setup for Multi-frame or Multi-user processing 0.01 numframes = 30; 0.01 htdec = comm.gpu.turbodecoder('trellisstructure', poly2trellis(4, [13 15], 13),'InterleaverIndices', intrlvrindices, 'NumIterations',numIter, NumFrames,numFrames); %% Processing loop while ( ber(1) < MaxNumErrs && ber(2) < MaxNumBits) 0.22 data = randn(numframes*blklength, 1)>0.5; % Encode random data bits 2.45 yenc = gpuarray(multiframestep(htenc, data, numframes)); %Modulate, Add noise to real bipolar data 0.02 modout = 1-2*yEnc; 0.31 rdata = step(hawgn, modout); % Convert to log-likelihood ratios for decoding 0.01 llrdata = (-2/noiseVar).*rData; % Turbo Decode decdata = step(htdec, llrdata); % Calculate errors 0.09 ber=step(hber, data, gather(decdata)); end 24
25 Things to note when targeting GPU Minimize data transfer between CPU and GPU. Using GPU only makes sense if data size is large. Some functions in MATLAB are optimized and can be faster than the GPU equivalent (eg. FFT). Use arrayfun to explicitly specify elementwise operations. 25
26 Summary Acceleration methodologies in MATLAB & Simulink Technology / Product 1. Best Practices in Programming Vectorization & pre-allocation Environment tools. (i.e. Profiler, Code Analyzer) 2. Better Algorithms Ideal environment for algorithm exploration Rich set of functionality (e.g. System objects) MATLAB, Toolboxes, System Toolboxes MATLAB, Toolboxes, System Toolboxes 3. More Processors or Cores High level parallel constructs (e.g. parfor, matlabpool) Utilize cluster, clouds, and grids 4. Refactoring the Implementation Compiled code (MEX) GPUs, FPGA-in-the-Loop Parallel Computing Toolbox, MATLAB Distributed Computing Server MATLAB, MATLAB Coder, Parallel Computing Toolbox 26
27 Thank You Q & A 27
Modeling a 4G LTE System in MATLAB
Modeling a 4G LTE System in MATLAB Part 2: Simulation acceleration Houman Zarrinkoub PhD. Signal Processing Product Manager MathWorks houmanz@mathworks.com 2011 The MathWorks, Inc. 1 Why simulation acceleration?
More informationModeling a 4G LTE System in MATLAB Idin Motedayen-Aval Senior Applications Engineer MathWorks
Modeling a 4G LTE System in MATLAB Idin Motedayen-Aval Senior Applications Engineer MathWorks Idin.motedayen-aval@mathworks.com 2012 The MathWorks, Inc. 1 Agenda 4G LTE and LTE Advanced True Global standard
More informationSpeeding up MATLAB Applications Sean de Wolski Application Engineer
Speeding up MATLAB Applications Sean de Wolski Application Engineer 2014 The MathWorks, Inc. 1 Non-rigid Displacement Vector Fields 2 Agenda Leveraging the power of vector and matrix operations Addressing
More informationParallel and Distributed Computing with MATLAB The MathWorks, Inc. 1
Parallel and Distributed Computing with MATLAB 2018 The MathWorks, Inc. 1 Practical Application of Parallel Computing Why parallel computing? Need faster insight on more complex problems with larger datasets
More informationGetting Started with MATLAB Francesca Perino
Getting Started with MATLAB Francesca Perino francesca.perino@mathworks.it 2014 The MathWorks, Inc. 1 Agenda MATLAB Intro Importazione ed esportazione Programmazione in MATLAB Tecniche per la velocizzazione
More informationOptimizing and Accelerating Your MATLAB Code
Optimizing and Accelerating Your MATLAB Code Sofia Mosesson Senior Application Engineer 2016 The MathWorks, Inc. 1 Agenda Optimizing for loops and using vector and matrix operations Indexing in different
More informationParallel and Distributed Computing with MATLAB Gerardo Hernández Manager, Application Engineer
Parallel and Distributed Computing with MATLAB Gerardo Hernández Manager, Application Engineer 2018 The MathWorks, Inc. 1 Practical Application of Parallel Computing Why parallel computing? Need faster
More informationMit MATLAB auf der Überholspur Methoden zur Beschleunigung von MATLAB Anwendungen
Mit MATLAB auf der Überholspur Methoden zur Beschleunigung von MATLAB Anwendungen Frank Graeber Application Engineering MathWorks Germany 2013 The MathWorks, Inc. 1 Speed up the serial code within core
More informationSpeeding up MATLAB Applications The MathWorks, Inc.
Speeding up MATLAB Applications 2009 The MathWorks, Inc. Agenda Leveraging the power of vector & matrix operations Addressing bottlenecks Utilizing additional processing power Summary 2 Example: Block
More informationMulticore Computer, GPU 및 Cluster 환경에서의 MATLAB Parallel Computing 기능
Multicore Computer, GPU 및 Cluster 환경에서의 MATLAB Parallel Computing 기능 성호현 MathWorks Korea 2012 The MathWorks, Inc. 1 A Question to Consider Do you want to speed up your algorithms? If so Do you have a multi-core
More informationLarge Data in MATLAB: A Seismic Data Processing Case Study U. M. Sundar Senior Application Engineer
Large Data in MATLAB: A Seismic Data Processing Case Study U. M. Sundar Senior Application Engineer 2013 MathWorks, Inc. 1 Problem Statement: Scaling Up Seismic Analysis Challenge: Developing a seismic
More informationDaniel D. Warner. May 31, Introduction to Parallel Matlab. Daniel D. Warner. Introduction. Matlab s 5-fold way. Basic Matlab Example
to May 31, 2010 What is Matlab? Matlab is... an Integrated Development Environment for solving numerical problems in computational science. a collection of state-of-the-art algorithms for scientific computing
More informationModeling a 4G LTE System in MATLAB
Modeling a 4G LTE System in MATLAB Part 3: Path to implementation (C and HDL) Houman Zarrinkoub PhD. Signal Processing Product Manager MathWorks houmanz@mathworks.com 2011 The MathWorks, Inc. 1 LTE Downlink
More informationMoving MATLAB Algorithms into Complete Designs with Fixed-Point Simulation and Code Generation
Moving MATLAB Algorithms into Complete Designs with Fixed-Point Simulation and Code Generation Houman Zarrinkoub, PhD. Product Manager Signal Processing Toolboxes The MathWorks Inc. 2007 The MathWorks,
More informationOptimization and Implementation of Embedded Signal Processing Algorithms Jonas Rutström Senior Application Engineer
Optimization and Implementation of Embedded Signal Processing Algorithms Jonas Rutström Senior Application Engineer 2016 The MathWorks, 1 Inc. Two important questions in embedded design... 1. What s your
More informationHigh Performance and GPU Computing in MATLAB
High Performance and GPU Computing in MATLAB Jan Houška houska@humusoft.cz http://www.humusoft.cz 1 About HUMUSOFT Company: Humusoft s.r.o. Founded: 1990 Number of employees: 18 Location: Praha 8, Pobřežní
More informationMit MATLAB auf der Überholspur Methoden zur Beschleunigung von MATLAB Anwendungen
Mit MATLAB auf der Überholspur Methoden zur Beschleunigung von MATLAB Anwendungen Michael Glaßer Application Engineering MathWorks Germany 2014 The MathWorks, Inc. 1 Key Takeaways 1. Speed up your serial
More informationIntroduction to C and HDL Code Generation from MATLAB
Introduction to C and HDL Code Generation from MATLAB 이웅재차장 Senior Application Engineer 2012 The MathWorks, Inc. 1 Algorithm Development Process Requirements Research & Design Explore and discover Design
More informationAudio Signal Processing in MATLAB Youssef Abdelilah Senior Product Manager
Audio Signal Processing in MATLAB Youssef Abdelilah Senior Product Manager 2014 The MathWorks, Inc. 1 Agenda Tunable parametric equalizer example Audio tone removal example 1 2 3 How to create a streaming
More informationModel-Based Design: Generating Embedded Code for Prototyping or Production
Model-Based Design: Generating Embedded Code for Prototyping or Production Ruth-Anne Marchant Application Engineer MathWorks 2016 The MathWorks, Inc. 1 2 ABB Accelerates Application Control Software Development
More informationParallel Computing with MATLAB
Parallel Computing with MATLAB CSCI 4850/5850 High-Performance Computing Spring 2018 Tae-Hyuk (Ted) Ahn Department of Computer Science Program of Bioinformatics and Computational Biology Saint Louis University
More informationMatCL - OpenCL MATLAB Interface
MatCL - OpenCL MATLAB Interface MatCL - OpenCL MATLAB Interface Slide 1 MatCL - OpenCL MATLAB Interface OpenCL toolkit for Mathworks MATLAB/SIMULINK Compile & Run OpenCL Kernels Handles OpenCL memory management
More informationScaling up MATLAB Analytics Marta Wilczkowiak, PhD Senior Applications Engineer MathWorks
Scaling up MATLAB Analytics Marta Wilczkowiak, PhD Senior Applications Engineer MathWorks 2013 The MathWorks, Inc. 1 Agenda Giving access to your analytics to more users Handling larger problems 2 When
More informationHow Real-Time Testing Improves the Design of a PMSM Controller
How Real-Time Testing Improves the Design of a PMSM Controller Prasanna Deshpande Control Design & Automation Application Engineer MathWorks 2015 The MathWorks, Inc. 1 Problem Statement: Design speed control
More informationTechnical Computing with MATLAB
Technical Computing with MATLAB University Of Bath Seminar th 19 th November 2010 Adrienne James (Application Engineering) 1 Agenda Introduction to MATLAB Importing, visualising and analysing data from
More informationIntro to System Generator. Objectives. After completing this module, you will be able to:
Intro to System Generator This material exempt per Department of Commerce license exception TSU Objectives After completing this module, you will be able to: Explain why there is a need for an integrated
More informationModel-Based Design for Video/Image Processing Applications
Model-Based Design for Video/Image Processing Applications The MathWorks Agenda Model-Based Design From MATLAB and Simulink to Altera FPGA Step-by-step design and implementation of edge detection algorithm
More informationDeep learning in MATLAB From Concept to CUDA Code
Deep learning in MATLAB From Concept to CUDA Code Roy Fahn Applications Engineer Systematics royf@systematics.co.il 03-7660111 Ram Kokku Principal Engineer MathWorks ram.kokku@mathworks.com 2017 The MathWorks,
More informationImplementing MATLAB Algorithms in FPGAs and ASICs By Alexander Schreiber Senior Application Engineer MathWorks
Implementing MATLAB Algorithms in FPGAs and ASICs By Alexander Schreiber Senior Application Engineer MathWorks 2014 The MathWorks, Inc. 1 Traditional Implementation Workflow: Challenges Algorithm Development
More informationMATLAB AND PARALLEL COMPUTING
Image Processing & Communication, vol. 17, no. 4, pp. 207-216 DOI: 10.2478/v10248-012-0048-5 207 MATLAB AND PARALLEL COMPUTING MAGDALENA SZYMCZYK, PIOTR SZYMCZYK AGH University of Science and Technology,
More informationModel-Based Design for effective HW/SW Co-Design Alexander Schreiber Senior Application Engineer MathWorks, Germany
Model-Based Design for effective HW/SW Co-Design Alexander Schreiber Senior Application Engineer MathWorks, Germany 2013 The MathWorks, Inc. 1 Agenda Model-Based Design of embedded Systems Software Implementation
More informationNumbaPro CUDA Python. Square matrix multiplication
NumbaPro Enables parallel programming in Python Support various entry points: Low-level (CUDA-C like) programming language High-level array oriented interface CUDA library bindings Also support multicore
More informationUsing Parallel Computing Toolbox to accelerate the Video and Image Processing Speed. Develop parallel code interactively
Using Parallel Computing Toolbox to accelerate the Video and Image Processing Speed Presenter: Claire Chuang TeraSoft Inc. Agenda Develop parallel code interactively parallel applications for faster processing
More informationINTRODUCTION TO MATLAB PARALLEL COMPUTING TOOLBOX
INTRODUCTION TO MATLAB PARALLEL COMPUTING TOOLBOX Keith Ma ---------------------------------------- keithma@bu.edu Research Computing Services ----------- help@rcs.bu.edu Boston University ----------------------------------------------------
More information개발과정에서의 MATLAB 과 C 의연동 ( 영상처리분야 )
개발과정에서의 MATLAB 과 C 의연동 ( 영상처리분야 ) Application Engineer Caleb Kim 2016 The MathWorks, Inc. 1 Algorithm Development with MATLAB for C/C++ Programmers Objectives Use MATLAB throughout algorithm development
More informationGeneral Purpose GPU Computing in Partial Wave Analysis
JLAB at 12 GeV - INT General Purpose GPU Computing in Partial Wave Analysis Hrayr Matevosyan - NTC, Indiana University November 18/2009 COmputationAL Challenges IN PWA Rapid Increase in Available Data
More informationModel-Based Design: Design with Simulation in Simulink
Model-Based Design: Design with Simulation in Simulink Ruth-Anne Marchant Application Engineer MathWorks 2016 The MathWorks, Inc. 1 2 Outline Model-Based Design Overview Modelling and Design in Simulink
More informationAvnet Speedway Design Workshop
Accelerating Your Success Avnet Speedway Design Workshop Creating FPGA-based Co-Processors for DSPs Using Model Based Design Techniques Lecture 4: FPGA Co-Processor Architectures and Verification V10_1_2_0
More informationReal-Time Testing in a Modern, Agile Development Workflow
Real-Time Testing in a Modern, Agile Development Workflow Simon Eriksson Application Engineer 2015 The MathWorks, Inc. 1 Demo Going from Desktop Testing to Real-Time Testing 2 Key Take-Aways From This
More informationIntegrate MATLAB Analytics into Enterprise Applications
Integrate Analytics into Enterprise Applications Lyamine Hedjazi 2015 The MathWorks, Inc. 1 Data Analytics Workflow Preprocessing Data Business Systems Build Algorithms Smart Connected Systems Take Decisions
More informationEmbarquez votre Intelligence Artificielle (IA) sur CPU, GPU et FPGA
Embarquez votre Intelligence Artificielle (IA) sur CPU, GPU et FPGA Pierre Nowodzienski Engineer pierre.nowodzienski@mathworks.fr 2018 The MathWorks, Inc. 1 From Data to Business value Make decisions Get
More informationMATLAB. Senior Application Engineer The MathWorks Korea The MathWorks, Inc. 2
1 Senior Application Engineer The MathWorks Korea 2017 The MathWorks, Inc. 2 Data Analytics Workflow Business Systems Smart Connected Systems Data Acquisition Engineering, Scientific, and Field Business
More information컴퓨터비전의최신기술 : Deep Learning, 3D Vision and Embedded Vision
1 컴퓨터비전의최신기술 : Deep Learning, 3D Vision and Embedded Vision 김종남 Application Engineer 2017 The MathWorks, Inc. 2 Three Main Topics New capabilities for computer vision system design: Deep Learning 3-D Vision
More informationdesigning a GPU Computing Solution
designing a GPU Computing Solution Patrick Van Reeth EMEA HPC Competency Center - GPU Computing Solutions Saturday, May the 29th, 2010 1 2010 Hewlett-Packard Development Company, L.P. The information contained
More informationGPU ACCELERATED DATABASE MANAGEMENT SYSTEMS
CIS 601 - Graduate Seminar Presentation 1 GPU ACCELERATED DATABASE MANAGEMENT SYSTEMS PRESENTED BY HARINATH AMASA CSU ID: 2697292 What we will talk about.. Current problems GPU What are GPU Databases GPU
More informationMATLAB Based Optimization Techniques and Parallel Computing
MATLAB Based Optimization Techniques and Parallel Computing Bratislava June 4, 2009 2009 The MathWorks, Inc. Jörg-M. Sautter Application Engineer The MathWorks Agenda Introduction Local and Smooth Optimization
More informationCUDA. Matthew Joyner, Jeremy Williams
CUDA Matthew Joyner, Jeremy Williams Agenda What is CUDA? CUDA GPU Architecture CPU/GPU Communication Coding in CUDA Use cases of CUDA Comparison to OpenCL What is CUDA? What is CUDA? CUDA is a parallel
More informationIntegrate MATLAB Analytics into Enterprise Applications
Integrate Analytics into Enterprise Applications Aurélie Urbain MathWorks Consulting Services 2015 The MathWorks, Inc. 1 Data Analytics Workflow Data Acquisition Data Analytics Analytics Integration Business
More informationScaling MATLAB. for Your Organisation and Beyond. Rory Adams The MathWorks, Inc. 1
Scaling MATLAB for Your Organisation and Beyond Rory Adams 2015 The MathWorks, Inc. 1 MATLAB at Scale Front-end scaling Scale with increasing access requests Back-end scaling Scale with increasing computational
More informationUSING THE SYSTEM-C LIBRARY FOR BIT TRUE SIMULATIONS IN MATLAB
USING THE SYSTEM-C LIBRARY FOR BIT TRUE SIMULATIONS IN MATLAB Jan Schier Institute of Information Theory and Automation Academy of Sciences of the Czech Republic Abstract In the paper, the possibilities
More informationModel-Based Design for Altera FPGAs Using HDL Code Generation The MathWorks, Inc. 1
Model-Based Design for Altera FPGAs Using HDL Code Generation Z 2011 The MathWorks, Inc. 1 Separate Views of DSP Implementation System Designer FPGA Designer Algorithm Design System Test Bench RTL Design
More informationWhat s New with the MATLAB and Simulink Product Families. Marta Wilczkowiak & Coorous Mohtadi Application Engineering Group
What s New with the MATLAB and Simulink Product Families Marta Wilczkowiak & Coorous Mohtadi Application Engineering Group 1 Area MATLAB Math, Statistics, and Optimization Application Deployment Parallel
More informationMatlab for Engineers
Matlab for Engineers Alistair Johnson 31st May 2012 Centre for Doctoral Training in Healthcare Innovation Institute of Biomedical Engineering Department of Engineering Science University of Oxford Supported
More informationHigh-Performance Data Loading and Augmentation for Deep Neural Network Training
High-Performance Data Loading and Augmentation for Deep Neural Network Training Trevor Gale tgale@ece.neu.edu Steven Eliuk steven.eliuk@gmail.com Cameron Upright c.upright@samsung.com Roadmap 1. The General-Purpose
More informationMATLAB: The challenges involved in providing a high-level language on a GPU
MATLAB: The challenges involved in providing a high-level language on a GPU Jos Martin jos.martin@mathworks.co.uk 2013 The MathWorks, Inc. 1 Agenda Why did we introduce GPU support? What did we do? What
More informationMATLAB Parallel Computing Toolbox Benchmark for an Embarrassingly Parallel Application
MATLAB Parallel Computing Toolbox Benchmark for an Embarrassingly Parallel Application By Nils Oberg, Benjamin Ruddell, Marcelo H. García, and Praveen Kumar Department of Civil and Environmental Engineering
More informationPractical Introduction to CUDA and GPU
Practical Introduction to CUDA and GPU Charlie Tang Centre for Theoretical Neuroscience October 9, 2009 Overview CUDA - stands for Compute Unified Device Architecture Introduced Nov. 2006, a parallel computing
More informationModeling HDL components for FPGAs in control applications
Modeling HDL components for FPGAs in control applications Mark Corless, Principal Application Engineer, Novi MI 2014 The MathWorks, Inc. 1 Position sensing High resolution voltage modulation Critical diagnostics
More information2015 The MathWorks, Inc. 1
2015 The MathWorks, Inc. 1 MATLAB 의 C 코드생성 워크플로우및최적화요령 정승혁과장 2015 The MathWorks, Inc. 2 MATLAB Coder User Story Using MATLAB Try a new idea quickly Evaluation of the system by testing and analysis High
More informationDesigning and Targeting Video Processing Subsystems for Hardware
1 Designing and Targeting Video Processing Subsystems for Hardware 정승혁과장 Senior Application Engineer MathWorks Korea 2017 The MathWorks, Inc. 2 Pixel-stream Frame-based Process : From Algorithm to Hardware
More informationUsing Intel Math Kernel Library with MathWorks* MATLAB* on Intel Xeon Phi Coprocessor System
Using Intel Math Kernel Library with MathWorks* MATLAB* on Intel Xeon Phi Coprocessor System Overview This guide is intended to help developers use the latest version of Intel Math Kernel Library (Intel
More informationStream Processing with CUDA TM A Case Study Using Gamebryo's Floodgate Technology
Stream Processing with CUDA TM A Case Study Using Gamebryo's Floodgate Technology Dan Amerson, Technical Director, Emergent Game Technologies Purpose Why am I giving this talk? To answer this question:
More informationCUDA Programming Model
CUDA Xing Zeng, Dongyue Mou Introduction Example Pro & Contra Trend Introduction Example Pro & Contra Trend Introduction What is CUDA? - Compute Unified Device Architecture. - A powerful parallel programming
More information2015 The MathWorks, Inc. 1
2015 The MathWorks, Inc. 1 웨어러블디바이스의신호분석 Senior Application Engineer 김종남 2015 The MathWorks, Inc. 2 Agenda Internet Of Things Signal Analytics and Classification : On data from wareable and mobile device
More informationDesign and Verify Embedded Signal Processing Systems Using MATLAB and Simulink
Design and Verify Embedded Signal Processing Systems Using MATLAB and Simulink Giorgia Zucchelli, Application Engineer, MathWorks 10 January 2013, Technical University Eindhoven 2013 The MathWorks, Inc.
More informationCMSC 714 Lecture 6 MPI vs. OpenMP and OpenACC. Guest Lecturer: Sukhyun Song (original slides by Alan Sussman)
CMSC 714 Lecture 6 MPI vs. OpenMP and OpenACC Guest Lecturer: Sukhyun Song (original slides by Alan Sussman) Parallel Programming with Message Passing and Directives 2 MPI + OpenMP Some applications can
More informationSDACCEL DEVELOPMENT ENVIRONMENT. The Xilinx SDAccel Development Environment. Bringing The Best Performance/Watt to the Data Center
SDAccel Environment The Xilinx SDAccel Development Environment Bringing The Best Performance/Watt to the Data Center Introduction Data center operators constantly seek more server performance. Currently
More informationModel-Based Embedded System Design
Model-Based Embedded System Design Pieter J. Mosterman Senior Research Scientist The MathW orks, Inc. 2007 The MathWorks, Inc. Agenda Introduction Embedded Systems Design Demo A Design Activity Dynamic
More informationSupporting Data Parallelism in Matcloud: Final Report
Supporting Data Parallelism in Matcloud: Final Report Yongpeng Zhang, Xing Wu 1 Overview Matcloud is an on-line service to run Matlab-like script on client s web browser. Internally it is accelerated by
More informationIntroducing Simulink R2012b for Signal Processing & Communications Graham Reith Senior Team Leader, UK Application Engineering
Introducing Simulink R2012b for Signal Processing & Communications Graham Reith Senior Team Leader, UK Application Engineering 2012 The MathWorks, Inc. 1 Simulink R2012b the most significant upgrade to
More informationRTW SUPPORT FOR PARALLEL 64bit ALPHA AXP-BASED PLATFORMS. Christian Vialatte, Jiri Kadlec,
RTW SUPPORT FOR PARALLEL 64bit ALPHA AXP-BASED PLATFORMS Christian Vialatte, Jiri Kadlec, Introduction Presentation of software supporting the Real-Time Workshop (Matlab 5.3), targeting AD66 ISA and AD66-PCI
More informationUsing a GPU in InSAR processing to improve performance
Using a GPU in InSAR processing to improve performance Rob Mellors, ALOS PI 152 San Diego State University David Sandwell University of California, San Diego What is a GPU? (Graphic Processor Unit) A graphics
More informationWhat s New in MATLAB and Simulink
What s New in MATLAB Simulink Fabrizio Sara 2015 The MathWorks, Inc. 1 Engineers scientists 2 Engineers scientists Develop algorithms Analyze data write MATLAB code. 3 Engineers scientists deploy algorithms
More informationGeorgia Institute of Technology Center for Signal and Image Processing Steve Conover February 2009
Georgia Institute of Technology Center for Signal and Image Processing Steve Conover February 2009 Introduction CUDA is a tool to turn your graphics card into a small computing cluster. It s not always
More informationAccelerate FPGA Prototyping with
Accelerate FPGA Prototyping with MATLAB and Simulink September 21 st 2010 Stephan van Beek Senior Application Engineer 1 From Idea to Implementation DESIGN Algorithm Development MATLAB Simulink Stateflow
More informationSpartan -6 LX150T Development Kit Hardware Co-Simulation Reference Design User Guide
Spartan -6 LX150T Development Kit H/W Co-Simulation Reference Design User Guide Spartan -6 LX150T Development Kit Hardware Co-Simulation Reference Design User Guide Version 0.8 Revision History Version
More informationCoarse Grain Reconfigurable Arrays are Signal Processing Engines!
Coarse Grain Reconfigurable Arrays are Signal Processing Engines! Advanced Topics in Telecommunications, Algorithms and Implementation Platforms for Wireless Communications, TLT-9707 Waqar Hussain Researcher
More informationData Analytics with MATLAB. Tackling the Challenges of Big Data
Data Analytics with MATLAB Tackling the Challenges of Big Data How big is big? What characterises big data? Any collection of data sets so large and complex that it becomes difficult to process using traditional
More informationHigher Level Programming Abstractions for FPGAs using OpenCL
Higher Level Programming Abstractions for FPGAs using OpenCL Desh Singh Supervising Principal Engineer Altera Corporation Toronto Technology Center ! Technology scaling favors programmability CPUs."#/0$*12'$-*
More informationModeling and Simulating Social Systems with MATLAB
Modeling and Simulating Social Systems with MATLAB Lecture 6 Optimization and Parallelization Olivia Woolley, Tobias Kuhn, Dario Biasini, Dirk Helbing Chair of Sociology, in particular of Modeling and
More informationParallel Processing Tool-box
Parallel Processing Tool-box Start up MATLAB in the regular way. This copy of MATLAB that you start with is called the "client" copy; the copies of MATLAB that will be created to assist in the computation
More informationParallel Computing with Matlab and R
Parallel Computing with Matlab and R scsc@duke.edu https://wiki.duke.edu/display/scsc Tom Milledge tm103@duke.edu Overview Running Matlab and R interactively and in batch mode Introduction to Parallel
More informationDesigning and Prototyping Digital Systems on SoC FPGA The MathWorks, Inc. 1
Designing and Prototyping Digital Systems on SoC FPGA Hitu Sharma Application Engineer Vinod Thomas Sr. Training Engineer 2015 The MathWorks, Inc. 1 What is an SoC FPGA? A typical SoC consists of- A microcontroller,
More informationA Design Framework for Mapping Vectorized Synchronous Dataflow Graphs onto CPU-GPU Platforms
A Design Framework for Mapping Vectorized Synchronous Dataflow Graphs onto CPU-GPU Platforms Shuoxin Lin, Yanzhou Liu, William Plishker, Shuvra Bhattacharyya Maryland DSPCAD Research Group Department of
More informationHardware and Software Co-Design for Motor Control Applications
Hardware and Software Co-Design for Motor Control Applications GianCarlo Pacitti Senior Application Engineer, MathWorks 2015 The MathWorks, Inc. 1 Agenda Why use Hardware and Software for motor control?
More informationWhat s New for MATLAB David Willingham
What s New for MATLAB David Willingham 2015 The MathWorks, Inc. 1 MATLAB Execution Engine Redesigned execution engine runs MATLAB code faster All MATLAB code is now JIT compiled A platform for future improvements
More informationDeveloping a Data Driven System for Computational Neuroscience
Developing a Data Driven System for Computational Neuroscience Ross Snider and Yongming Zhu Montana State University, Bozeman MT 59717, USA Abstract. A data driven system implies the need to integrate
More informationCUDA PROGRAMMING MODEL Chaithanya Gadiyam Swapnil S Jadhav
CUDA PROGRAMMING MODEL Chaithanya Gadiyam Swapnil S Jadhav CMPE655 - Multiple Processor Systems Fall 2015 Rochester Institute of Technology Contents What is GPGPU? What s the need? CUDA-Capable GPU Architecture
More informationWhat's new in MATLAB and Simulink for Model-Based Design
What's new in MATLAB and Simulink for Model-Based Design Magnus Jung Application Engineer 2016 The MathWorks, Inc. 1 What s New? 2 Model-Based Design Workflow RESEARCH REQUIREMENTS DESIGN Scheduling Event
More informationParallel Computing with MATLAB on Discovery Cluster
Parallel Computing with MATLAB on Discovery Cluster Northeastern University Research Computing: Nilay K Roy, MS Computer Science, Ph.D Computational Physics Lets look at the Discovery Cluster Matlab environment
More informationAdvanced CUDA Optimization 1. Introduction
Advanced CUDA Optimization 1. Introduction Thomas Bradley Agenda CUDA Review Review of CUDA Architecture Programming & Memory Models Programming Environment Execution Performance Optimization Guidelines
More informationHardware Implementation and Verification by Model-Based Design Workflow - Communication Models to FPGA-based Radio
Hardware Implementation and Verification by -Based Design Workflow - Communication s to FPGA-based Radio Katsuhisa Shibata Industry Marketing MathWorks Japan 2015 The MathWorks, Inc. 1 Agenda Challenges
More informationCUDA and OpenCL Implementations of 3D CT Reconstruction for Biomedical Imaging
CUDA and OpenCL Implementations of 3D CT Reconstruction for Biomedical Imaging Saoni Mukherjee, Nicholas Moore, James Brock and Miriam Leeser September 12, 2012 1 Outline Introduction to CT Scan, 3D reconstruction
More informationVidushi: Parallel Implementation of Alpha Miner Algorithm and Performance Analysis on CPU and GPU Architecture
Vidushi: Parallel Implementation of Alpha Miner Algorithm and Performance Analysis on CPU and GPU Architecture Divya Kundra Computer Science Indraprastha Institute of Information Technology, Delhi (IIIT-D),
More informationPorting the NAS-NPB Conjugate Gradient Benchmark to CUDA. NVIDIA Corporation
Porting the NAS-NPB Conjugate Gradient Benchmark to CUDA NVIDIA Corporation Outline! Overview of CG benchmark! Overview of CUDA Libraries! CUSPARSE! CUBLAS! Porting Sequence! Algorithm Analysis! Data/Code
More informationGPU-Accelerated Beat Detection for Dancing Monkeys
GPU-Accelerated Beat Detection for Dancing Monkeys Philip Peng University of Pennsylvania Yanjie Feng University of Pennsylvania Abstract In music-based rhythm games, the game system needs to create patterns
More informationMATLAB to iphone Made Easy
MATLAB to iphone Made Easy Generating readable and portable C code from your MATLAB algorithms for your iphone or ipad app Bill Chou 2014 The MathWorks, Inc. 1 2 4 Quick Demo MATLAB Coder >> Demo 5 Agenda
More informationSystem Requirements & Platform Availability by Product for R2016b
& Platform Availability by Product for R2016b View general system requirements. Product Aerospace Blockset Requires Aerospace Control recommended Aerospace Antenna RF recommended Phased Array recommended
More informationThe Use of Computing Clusters and Automatic Code Generation to Speed Up Simulation Tasks
The Use of Computing Clusters and Automatic Code Generation to Speed Up Simulation Tasks Jason R. Ghidella 1, Amory Wakefield 2, Silvina Grad-Freilich 3, Jon Friedman 4 and Vinod Cherian 5 The MathWorks,
More informationDynamic Cuda with F# HPC GPU & F# Meetup. March 19. San Jose, California
Dynamic Cuda with F# HPC GPU & F# Meetup March 19 San Jose, California Dr. Daniel Egloff daniel.egloff@quantalea.net +41 44 520 01 17 +41 79 430 03 61 About Us! Software development and consulting company!
More information