Indexing Large-Scale Raster Geospatial Data Using Massively Parallel GPGPU Computing

1
Indexing Large-Scale Raster Geospatial Data
Using Massively Parallel GPGPU Computing

• Jianting Zhang
• City College of New Yorkjzhang_at_cs.ccny.cuny.edu

Le Gruenwald University of Oklahoma
ggruenwald_at_ou.edu
Simin You CUNY Graduate Center syou_at_gc.cuny.edu
2
GPU-Based Parallel Processing of Large-Scale
Raster Data
From field measurements
To multi-dimensional arrays
To tree indices
Traditionally database indexing is considered
expensive
Can we borrow some computing power from gamers
that own tens of millions of graphic cards?
GPGPU technologies are for both gamers and
scientists!
3
Data Structure, Parallel Algorithm and Results

• Nvidia Quadro FX3700 Card
• 112 core (500M HZ)
• 512M Device Memory

23X speedup compared to a single 2G HZ Intel
E5405 CPU core
Come to our poster and we will show you how to
grow trees out of matrices on GPUs!