A CUDA Approach Gary Resnick Scott Badenhorst Department of Computer Science University of Cape Town 17 March 2010 Introduction Approach Plan Outcomes Overview Radio Astronomy ID: 278689
Download Presentation The PPT/PDF document "A GPU Implementation of Extragalactic Ra..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
A GPU Implementation of Extragalactic Radio Source DetectionA CUDA Approach
Gary
Resnick
Scott
Badenhorst
Department of Computer Science
University of Cape Town
17 March, 2010Slide2
IntroductionApproachPlanOutcomes
OverviewSlide3
Radio AstronomySlide4
A radio image of the sky Slide5
Radio InterferometrySlide6
What is a Source?Slide7Slide8Slide9
PipelineSlide10Slide11
Source ExtractionSlide12
Source Extraction PipelineSlide13
FITS Data CubeSlide14
Blob Detection (XY)Slide15
Characterisation (Z)Slide16
HI (Neutral Hydrogen)Slide17
AIPSIMFITIMSADSource ExtractorDeblend
Duchamp
Own variation
Related WorkSlide18
PlanBack down to EarthSlide19
Can the GPU be utilized for efficient image source extraction? How well does a GPU solution scale to handle large image data volumes?
Can we improve the processing time of current source extraction software?
Research QuestionsSlide20
The accuracy of the GPU implementations are greater than or equate to current extraction algorithms Sufficient reliability of faint source detection
Spurious detections (Type I error) are constrained by a
p-
value of 0.05
Attaining a speedup on the GPU implementations in the order of
10
x or greater than traditional CPU implementations
Key Success FactorsSlide21
Work Allocation
Team
IndividuallySlide22
Each member will independently implement a CPU implementation of a source extraction algorithm and then port it to the GPUSource ExtractionSlide23
Interfaces with Framework
Source Extraction
Segments (grids) of pixels
List of sources
Validation & Filtration
Validated source listSlide24
Factor
Probability
Impact
Risk
Failure to acquire data
low
low
low
Stakeholder departure
low
high
low
Data/code loss
low
high
medium
Unsuccessful module implementation
medium
medium
medium
Hardware failure
low
medium
high
Cascading delay
medium
high
medium
Risks
Risk FactorsSlide25
Radio Survey DataSynthesizedReal Sky Map
Implemented in C/C++ & CUDA on GNU/Linux
CFITSIO & WCSLIB Libraries
Developed on NVIDIA (CUDA Compliant) Fermi architecture
High-end machine with current gen NVIDIA card(s)
People
Resources RequiredSlide26
OutcomesSlide27
Software developed for source extraction and catalogue generation. Two independent reports A website and poster Presentation to demonstrate the project.
Deliverables & MilestonesSlide28
Open SourceDistributed under GNU GPL Akin to Duchamp & SeXtractorGNU/Linux Compatibility
Comparable
performance/accuracy across
distros
Institutions maintain data ownership
Retains rights to catalogues
produced
Data Integrity
Standardized input and output formats
Ethical, Professional & Legal IssuesSlide29
We present an approach to solving a problem within Astronomy that needs to be addressedOur approach is well thought out and relevant A balanced and fair work load has been allocated to each member
The project has minimal unmitigated risks
ConclusionSlide30
Questions?Slide31
Project Timeline