Pub. Date:
Modern Accelerator Technologies for Geographic Information Science

Modern Accelerator Technologies for Geographic Information Science


View All Available Formats & Editions
Choose Expedited Shipping at checkout for delivery by Friday, October 1


This book explores the impact of augmenting novel architectural designs with hardware‐based application accelerators. The text covers comprehensive aspects of the applications in Geographic Information Science, remote sensing and deploying Modern Accelerator Technologies (MAT) for geospatial simulations and spatiotemporal analytics. MAT in GIS applications, MAT in remotely sensed data processing and analysis, heterogeneous processors,
many-core and highly multi-threaded processors and general purpose processors are also presented. This book includes case studies and closes with a chapter on future trends. Modern Accelerator Technologies for GIS is a reference book for practitioners and researchers working in geographical information systems and related fields. Advanced-level students in geography, computational science, computer science and engineering will also find this book useful.

Related collections and offers

Product Details

ISBN-13: 9781461487449
Publisher: Springer US
Publication date: 10/27/2013
Edition description: 2013
Pages: 251
Product dimensions: 6.10(w) x 9.25(h) x 0.02(d)

Table of Contents

Modern Accelerator Technologies for GIScience.- Introduction to GPGPU.- Intel® Xeon Phi™ Coprocessors.- Accelerating Geocomputation with Cloud Computing.- Parallel Primitives based Spatial Join of Geospatial Data on GPGPUs.- Utilizing CUDA-enabled GPUs to support 5D scientific geovisualization: a case study of simulating dust storm events.- A Parallel Algorithm to Solve Near-Shortest Path Problems on Raster Graphs.- CUDA-Accelerated HD-ODETLAP: Lossy High Dimensional Gridded Data Compression.- Accelerating Agent-Based Modeling Using Graphics Processing Units.- Large-Scale Pulse Compression for Costas Signal with GPGPU.- Parallelizing ISODATA Algorithm for Unsupervised Image Classification on GPU.- Accelerating Mean Shift Segmentation Algorithm on Hybrid CPU/GPU Platforms.- Simulation and analysis of cluster-based caching replacement based on temporal and spatial locality of tile access.- A High-Concurrency Web Map Tile Service Built with Open-Source Software.- Improved Parallel Optimal Choropleth Map Classification.- Pursuing Spatiotemporally Integrated Social Science using Cyberinfrastructure.- Opportunities and Challenges for Urban Land-use Change Modeling using High-performance Computing.- Modern Accelerator Technologies for Spatially-explicit Integrated Environmental Modeling.

Customer Reviews