Exploring Parallelization of Nearest Neighbor Search and Clustering in High-Dimensional Space on Emerging Parallel Architectures with Applications in Computer Vision

该奖项是根据2009年美国复苏和再投资法案（公法111-5）资助的。该项目将探索在新兴并行架构上的大规模数据密集型应用的替代并行化技术，包括使用多核和GPGPU处理器的分布式内存计算机集群。实验环境包括一个适合于地理信息系统的大尺度图像分类定位应用和系统。预计将为该项目提供各种各样的评估硬件。本研究的最终目标是利用大规模系统，特别是存储，以地理空间数据的形式为最终用户提供服务。拟议的研究将利用pi在CUDA和MPI编程应用方面的初步工作，并将展示这些技术在超大规模存储中的应用，可能会存储数tb的航空和卫星图像。

This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5). This project will explore alternative parallelization techniques for very largescale data intensiveapplications on emerging new parallel architectures, including distributed memory computerclusters using multicore and GPGPU processors. The experimental environment includes anapplication and system for large scale image classification and orientation suitable for use ingeographic information systems. A variety of evaluation hardware is expected to be availablefor the project. The ultimate goal of this research is to leverage large scale systems, especiallystorage, to provide services to end users in the form of geospatial data. The proposed researchwill leverage preliminary work by the PIs in the application of CUDA and MPI programming andwill demonstrate the application of these technologies to very large scale storage, potentiallyholding multiple terabytes of aerial and satellite imagery.