Jianting Zhang City College of New York

Slides:



Advertisements
Similar presentations
Multi-core and tera- scale computing A short overview of benefits and challenges CSC 2007 Andrzej Nowak, CERN
Advertisements

Early Linpack Performance Benchmarking on IPE Mole-8.5 Fermi GPU Cluster Xianyi Zhang 1),2) and Yunquan Zhang 1),3) 1) Laboratory of Parallel Software.
GPGPU Introduction Alan Gray EPCC The University of Edinburgh.
Parallel Geospatial Data Management for Multi-Scale Environmental Data Analysis on GPUs Visiting Faculty: Jianting Zhang, The City College of New York.
Data Parallel Quadtree Indexing and Spatial Query Processing of Complex Polygon Data on GPUs Jianting Zhang 1,2 Simin You 2, Le Gruenwald 3 1 Depart of.
GPU Computing with CUDA as a focus Christie Donovan.
1 ITCS 6/8010 CUDA Programming, UNC-Charlotte, B. Wilkinson, Jan 19, 2011 Emergence of GPU systems and clusters for general purpose High Performance Computing.
Supporting Web-based Visual Exploration of Large-Scale Raster Geospatial Data Using Binned Min-Max Quadtree Jianting Zhang 12, Simin You 2 City College.
Dynamic Tiled Map Services: Supporting Query-Based Visualization of Large-Scale Raster Geospatial Data Jianting Zhang 12, Simin You 2 City College 1 &
Introduction What is GPU? It is a processor optimized for 2D/3D graphics, video, visual computing, and display. It is highly parallel, highly multithreaded.
GPGPU platforms GP - General Purpose computation using GPU
U 2 SOD-DB: A Database System to Manage Large-Scale Ubiquitous Urban Sensing Origin-Destination Data Jianting Zhang 134 Hongmian Gong 234 Camille Kamga.
Background image by chromosphere.deviantart.com Fella in following slides by devart.deviantart.com DM2336 Programming hardware shaders Dioselin Gonzalez.
1 VLSI and Computer Architecture Trends ECE 25 Fall 2012.
Different CPUs CLICK THE SPINNING COMPUTER TO MOVE ON.
Computationally Efficient Histopathological Image Analysis: Use of GPUs for Classification of Stromal Development Olcay Sertel 1,2, Antonio Ruiz 3, Umit.
BY: ALI AJORIAN ISFAHAN UNIVERSITY OF TECHNOLOGY 2012 GPU Architecture 1.
Invitation to Computer Science 5th Edition
By Arun Bhandari Course: HPC Date: 01/28/12. GPU (Graphics Processing Unit) High performance many core processors Only used to accelerate certain parts.
Massively Parallel Mapping of Next Generation Sequence Reads Using GPUs Azita Nouri, Reha Oğuz Selvitopi, Özcan Öztürk, Onur Mutlu, Can Alkan Bilkent University,
MS Thesis Defense “IMPROVING GPU PERFORMANCE BY REGROUPING CPU-MEMORY DATA” by Deepthi Gummadi CoE EECS Department April 21, 2014.
General Purpose Computing on Graphics Processing Units: Optimization Strategy Henry Au Space and Naval Warfare Center Pacific 09/12/12.
1 © 2012 The MathWorks, Inc. Parallel computing with MATLAB.
YOU LI SUPERVISOR: DR. CHU XIAOWEN CO-SUPERVISOR: PROF. LIU JIMING THURSDAY, MARCH 11, 2010 Speeding up k-Means by GPUs 1.
Applying GPU and POSIX Thread Technologies in Massive Remote Sensing Image Data Processing By: Group 17 King Mongkut's Institute of Technology Ladkrabang.
Conclusions and Future Considerations: Parallel processing of raster functions were 3-22 times faster than ArcGIS depending on file size. Also, processing.
OCR GCSE Computing © Hodder Education 2013 Slide 1 OCR GCSE Computing Chapter 2: CPU.
Scientific Computing on Graphics Hardware Robert Strzodka, Dominik G ö ddeke Reading, UK, May
Debunking the 100X GPU vs. CPU Myth An Evaluation of Throughput Computing on CPU and GPU Present by Chunyi Victor W Lee, Changkyu Kim, Jatin Chhugani,
Processor Level Parallelism 2. How We Got Here Developments in PC CPUs.
Computer Engg, IIT(BHU)
Computer Graphics Graphics Hardware
Unit 2 Technology Systems
Distributed SAR Image Change Detection with OpenCL-Enabled Spark
Graphics Processor Graphics Processing Unit
Database management system Data analytics system:
Brad Baker, Wayne Haney, Dr. Charles Choi
Video RAM Presented by GHOLAMREZA KAKAMANSHADI
Why you should consider Nvidia Stocks
What is GPU? how does it work?
How will execution time grow with SIZE?
Oracle SQL*Loader
Constructing a system with multiple computers or processors
The Problem Finding a needle in haystack An expert (CPU)
Graphics Processing Unit
Real-Time Ray Tracing Stefan Popov.
Meng Lu and Edzer Pebesma
Towards GPU-Accelerated Web-GIS
Speedup over Ji et al.'s work
Computer-Generated Force Acceleration using GPUs: Next Steps
Faster File matching using GPGPU’s Deephan Mohan Professor: Dr
The Yin and Yang of Processing Data Warehousing Queries on GPUs
CPU and Embedded Systems
Constructing a system with multiple computers or processors
Constructing a system with multiple computers or processors
About Hardware Optimization in Midas SW
The Free Lunch Ended 7 Years Ago
Constructing a system with multiple computers or processors
1.1 The Characteristics of Contemporary Processors, Input, Output and Storage Devices Types of Processors.
A Comparison-FREE SORTING ALGORITHM ON CPUs
Computer Graphics Graphics Hardware
High-Performance Analytics on Large-Scale GPS Taxi Trip Records in NYC
CompSci 1: Principles of Computer Science Lecture 1 Course Overview
Objectives Describe how common characteristics of CPUs affect their performance: clock speed, cache size, number of cores Explain the purpose and give.
Learning Objectives To be able to describe the purpose of the CPU
Prototyping A Web-based High-Performance Visual Analytics Platform for Origin-Destination Data: A Case study of NYC Taxi Trip Records Jianting Zhang1,2.
Graphics Processing Unit
Jianting Zhang1,2 Simin You2, Le Gruenwald3
6- General Purpose GPU Programming
Jianting Zhang1,2,4, Le Gruenwald3
Presentation transcript:

Jianting Zhang City College of New York jzhang@cs.ccny.cuny.edu Indexing Large-Scale Raster Geospatial Data Using Massively Parallel GPGPU Computing Jianting Zhang City College of New York jzhang@cs.ccny.cuny.edu Simin You CUNY Graduate Center syou@gc.cuny.edu Le Gruenwald University of Oklahoma ggruenwald@ou.edu Advances in remote sensing technologies and environmental modeling have and will generated huge amount of large-scale raster geospatial data. For example, the GOES-R geostationary operational environmental satellite to be lunched in 2015 has a spatial resolution of 2 kilomters and temporal resolution of 5 minutes. This translates to nearly a quarter of a billion raster cells in each of the 288 global coverages daily for a single band.

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? In spatial database applications, we construct indices to speed up query processing. Traditionally database indexing is considered expensive and requires considerable computing resources. On the other hand, thanks to millions of game lovers, current commodity GPU devices have provided tremedious computing power at very inexpensive prices. Many of the current generation GPU devices support general purpose computing. The basic idea in this research is to investigate the feasibility of using GPU to index large-scale raster geospatial data for interactive visual explorations. GPGPU technologies are for both gamers and scientists!

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 We have designed a Cache Conscious quadtree data structure and a set of algorithms to construct tree indices on GPUs. The construction algorithms utilize a set of pyramids but do not use pointers which are suitable for GPUs. Experiments using a three years old Nvidia Quadro Fx3700 card with 112 cores have shown 23 times speed up when compared to an Intel CPU core, even though the clock rate of the CPU core is four times faster than the GPU cores. While the index construction process shown in this slide might look complicated, we hope to convince you that planting a tree out of silicon is far more easier than growing a tree in your backyard. So please do come to our poster and we will show you how. Come to our poster and we will show you how to grow trees out of matrices on GPUs!