By : Arjun Radhakrishnan Supervisor : Prof. M. Inggs.

Slides:



Advertisements
Similar presentations
Ben Barsdell Matthew Bailes Christopher Fluke David Barnes.
Advertisements

Scalable Multi-Cache Simulation Using GPUs Michael Moeng Sangyeun Cho Rami Melhem University of Pittsburgh.
Timothy Blattner and Shujia Zhou May 18, This project is sponsored by Lockheed Martin We would like to thank Joseph Swartz, Sara Hritz, Michael.
Team Presentation July 22, Jodrell Bank is the original arboretum for Manchester University. Immediately after World War II, first radio telescope.
HPCC Mid-Morning Break High Performance Computing on a GPU cluster Dirk Colbry, Ph.D. Research Specialist Institute for Cyber Enabled Discovery.
Measuring Dispersion in Signals from the Crab Pulsar Jared Crossley National Radio Astronomy Observatory Tim Hankins & Jean Eilek New Mexico Tech Jared.
The Highest Time-Resolution Measurements in Radio Astronomy: The Crab Pulsar Giant Pulses Tim Hankins New Mexico Tech and NRAO, Socorro, NM Extreme Astrophysics.
Development of a track trigger based on parallel architectures Felice Pantaleo PH-CMG-CO (University of Hamburg) Felice Pantaleo PH-CMG-CO (University.
A many-core GPU architecture.. Price, performance, and evolution.
GPU Computing with CUDA as a focus Christie Donovan.
2009/04/07 Yun-Yang Ma.  Overview  What is CUDA ◦ Architecture ◦ Programming Model ◦ Memory Model  H.264 Motion Estimation on CUDA ◦ Method ◦ Experimental.
The Transient Radio Sky to be Revealed by the SKA Jim Cordes Cornell University AAS Meeting Washington, DC 8 January 2002.
LYU0101 Wireless Digital Information System Lam Yee Gordon Yeung Kam Wah Supervisor Prof. Michael Lyu Second semester FYP Presentation 2001~2002.
GPU-Based Frequency Domain Volume Rendering Ivan Viola, Armin Kanitsar, and Meister Eduard Gröller Institute of Computer Graphics and Algorithms Vienna.
CUDA Programming Lei Zhou, Yafeng Yin, Yanzhi Ren, Hong Man, Yingying Chen.
Discovery (?) for new population of isolated neutron star “ Transient radio bursts from rotating neutron star ” M.A. McLaughlin et al., Nat. Feb. 16, 2006.
CS 732: Advance Machine Learning Usman Roshan Department of Computer Science NJIT.
A Performance and Energy Comparison of FPGAs, GPUs, and Multicores for Sliding-Window Applications From J. Fowers, G. Brown, P. Cooke, and G. Stitt, University.
Heterogeneous Computing Dr. Jason D. Bakos. Heterogeneous Computing 2 “Traditional” Parallel/Multi-Processing Large-scale parallel platforms: –Individual.
Dakota Johnson, Tildon Johnson, Kyle Barker Rowan County Senior High School Mentor: Mrs. Jennifer Carter Abstract Data Analysis Acknowledgements Radio.
Communication-Minimizing 2D Convolution in GPU Registers Forrest N. Iandola David Sheffield Michael Anderson P. Mangpo Phothilimthana Kurt Keutzer University.
Atacama Large Millimeter/submillimeter Array Expanded Very Large Array Robert C. Byrd Green Bank Telescope Very Long Baseline Array Digital Signal Processing.
GPGPU platforms GP - General Purpose computation using GPU
Announcements. Radio Astronomy of Pulsars Tiffany Pewett
Chapter 2 Basic Communication Theory Basic Communications Theory w Understand the basic transmission theory, and figure out the maximum data rate. w.
SAGE: Self-Tuning Approximation for Graphics Engines
CSU0021 Computer Graphics © Chun-Fa Chang CSU0021 Computer Graphics September 10, 2014.
Motivation “Every three minutes a woman is diagnosed with Breast cancer” (American Cancer Society, “Detailed Guide: Breast Cancer,” 2006) Explore the use.
Pulsing Prizes By: Kyle Wenger and Megan Weaver, (Broadway High School, Broadway, VA) How old might they be? Using the ATNF catalog we have approximated.
Scalable Data Clustering with GPUs Andrew D. Pangborn Thesis Defense Rochester Institute of Technology Computer Engineering Department Friday, May 14 th.
PULSARS & TRANSIENT SOURCES Pushing the Envelope with SKA Jim Cordes, Cornell 28 Feb 2000  Frontiers of Neutron Star Science  Complete census of transient.
P ulsa R E xploration and S earch TO Jintao Luo NRAO-CV CREDIT: Bill Saxton, NRAO/AUI/NSF.
Abstract Pulsars are highly magnetized, rotating neutron stars that emit a beam of electromagnetic radiation. The radiation can only be observed when the.
Christopher Mitchell CDA 6938, Spring The Discrete Cosine Transform  In the same family as the Fourier Transform  Converts data to frequency domain.
Implementation of Parallel Processing Techniques on Graphical Processing Units Brad Baker, Wayne Haney, Dr. Charles Choi.
FPGA-based Dedispersion for Fast Transient Search John Dickey 23 Nov 2005 Orange, NSW.
By Arun Bhandari Course: HPC Date: 01/28/12. GPU (Graphics Processing Unit) High performance many core processors Only used to accelerate certain parts.
YOU LI SUPERVISOR: DR. CHU XIAOWEN CO-SUPERVISOR: PROF. LIU JIMING THURSDAY, MARCH 11, 2010 Speeding up k-Means by GPUs 1.
Programming Concepts in GPU Computing Dušan Gajić, University of Niš Programming Concepts in GPU Computing Dušan B. Gajić CIITLab, Dept. of Computer Science.
Use of GPUs in ALICE (and elsewhere) Thorsten Kollegger TDOC-PG | CERN |
Diane Marinkas CDA 6938 April 30, Outline Motivation Algorithm CPU Implementation GPU Implementation Performance Lessons Learned Future Work.
Accelerating a Software Radio Astronomy Correlator By Andrew Woods Supervisor: Prof. Inggs & Dr Langman.
Computational Biology 2008 Advisor: Dr. Alon Korngreen Eitan Hasid Assaf Ben-Zaken.
Molecular Dynamics Simulations on a GPU in OpenCL Alex Cappiello.
Short Time Fourier Transform-based method for fast transients detection Centre for eResearch, University of Auckland, New Zealand,
Hulse Team Pulsar Research Adam Kelsey, Consuela Hancock, Magaly Rosales, Cameron Deem, What Exactly Is A Pulsar? A pulsar is a rapidly spinning neutron.
Hardware Acceleration Using GPUs M Anirudh Guide: Prof. Sachin Patkar VLSI Consortium April 4, 2008.
Real-time Acquisition and Processing of Data from the GMRT Pulsar Back- ends Ramchandra M. Dabade (VNIT, Nagpur) Guided By, Yashwant Gupta.
IP Routing Processing with Graphic Processors Author: Shuai Mu, Xinya Zhang, Nairen Zhang, Jiaxin Lu, Yangdong Steve Deng, Shu Zhang Publisher: IEEE Conference.
Introduction “Tick, tock, tick, tock.” Clocks help keep us on schedule everyday, but how does our own galaxy keep in time? Pulsar’s are natures very own,
GPUs: Overview of Architecture and Programming Options Lee Barford firstname dot lastname at gmail dot com.
by Arjun Radhakrishnan supervised by Prof. Michael Inggs
Accelerating Spherical Harmonic Transforms on the NVIDIA® GPGPU
After the Supernova: Pulsars Melissa Anholm University of Wisconsin-Milwaukee 29 September, 2008.
GPU Accelerated MRI Reconstruction Professor Kevin Skadron Computer Science, School of Engineering and Applied Science University of Virginia, Charlottesville,
Big data Usman Roshan CS 675. Big data Typically refers to datasets with very large number of instances (rows) as opposed to attributes (columns). Data.
Program Optimizations and Recent Trends in Heterogeneous Parallel Computing Dušan Gajić, University of Niš Program Optimizations and Recent Trends in Heterogeneous.
GROUP 6 WIDEBAND ARTIFICIAL PULSAR Alexander Botten Kerlin Canelli Advisor: Randy McCullough.
Sudhanshu Khemka.  Treats each document as a vector with one component corresponding to each term in the dictionary  Weight of a component is calculated.
CS 732: Advance Machine Learning
Some GPU activities at the CMS experiment Felice Pantaleo EP-CMG-CO EP-CMG-CO 1.
CUDA Compute Unified Device Architecture. Agent Based Modeling in CUDA Implementation of basic agent based modeling on the GPU using the CUDA framework.
Photos placed in horizontal position with even amount of white space between photos and header Sandia National Laboratories is a multi-program laboratory.
Real-time Digital Signal Processing Digital Filters.
Accelerating K-Means Clustering with Parallel Implementations and GPU Computing Janki Bhimani Miriam Leeser Ningfang Mi
Matthew Royle Supervisor: Prof Shaun Bangay.  How do we implement OpenCL for CPUs  Differences in parallel architectures  Is our CPU implementation.
Stencil-based Discrete Gradient Transform Using
Long-Term Timing of Globular Cluster Pulsars
DCT IMAGE COMPRESSION.
Presentation transcript:

By : Arjun Radhakrishnan Supervisor : Prof. M. Inggs

 Pulsars and pulsar dispersion  Graphics Processing Units (GPUs)  Research method and Results  Conclusion and Future Work 2

 Pulsars are highly magnetised rotating neutron stars  They emit beams of electromagnetic radiation from their poles 3 Figure 1: A Pulsar with its ‘lighthouse’ beam [hartrao.ac.za]

 Pulsar emissions are distorted upon passing through the ionised Interstellar Medium (ISM)  Lower frequency components of the pulse are delayed more than higher frequencies

Figure 2: Dedispersion 2 5

 Class of consumer parallel processor that has come into use in the last 15 years  Use growing exponentially due to demand from billion-dollar video game industry  NVIDIA and AMD (ATI) are currently major players in the industry  GPUs do not have much on-chip memory – can pack in lots of compute power 6

 Justification for SKA  Large frequency range  1TB of data per minute  SKA needs real-time processing as data storage is not feasible  No communication needed between GPU kernels 7

 Worked at UIUC on the QP GPU cluster  Implemented the following coherent pulsar dedispersion algorithm 4 :  Fourier transform input signal  Apply a phase rotation  Inverse Fourier transform 8

 Code testing is still being conducted  Some trends noted are:  Speedup of up to 5x over CPU implementation  Performance improved approximately linearly with the number of GPUs used  Best performance for larger datasets (minimises effect of IO bottleneck) 9

 GPUs definitely show promise in this application  Further speedup may be possible by using an asynchronous data transfer  Analyse the network requirements and limitations when deployed 10

1. Cordes & McLaughlin (2003), “Searches for Fast Radio Transients”, The Astronomical Journal, vol. 596, pp Jim Cordes, “The SKA as a Radio Synoptic Survey Telescope: Widefield Surveys for Transients, Pulsars and ETI”, SKA Memo NVIDIA, NVIDIA CUDA Programming Guide 4. Walter Brisken, “Real-time Digital Signal Processing for Radio Astronomy” AstroGPU 11

12