中国农业科学院农业信息研究所 中国农学会
Agricultural Information Institute of CAAS China Association of Agricultural Science Societies
En
Ch
中国农业科学院农业信息研究所 中国农学会 主办

AI检索

订阅

返回顶部
当前位置: 首页 > 文章 > 基于GPU的生态环境遥感评价模型并行化研究 农业机械学报 2017 (5) 135-141
Position: Home > Articles > Parallelization on Model of Ecological Environment Remote Sensing Evaluation Based on GPU Transactions of the Chinese Society for Agricultural Machinery 2017 (5) 135-141

基于GPU的生态环境遥感评价模型并行化研究

作  者：
李林;顾进锋;宋安捷;郑海宁;曹津;朱德海
单  位：
中国农业大学信息与电气工程学院;谢菲尔德大学计算机学院
关键词：
生态环境评价;遥感;并行化处理;GPU;CUDA
摘  要：
通过基于GPU的生态环境遥感评价模型并行化研究,在深入分析CPU+GPU异构通用计算平台数据传输瓶颈的基础上,设计了数据分片、异步传输的GPU图像处理框架。在此基础上,将碳固定量、草地退化指数和生态环境指数3个计算模型基于CUDA进行并行化实现,并通过实验验证了该技术方法的有效性,随着数据规模的变大,碳固定量计算模型的加速比达到了8.04倍,草地退化指数计算模型的加速比达到了12.21倍,生态环境指数计算模型的加速比达到了7.45倍。
译  名：
Parallelization on Model of Ecological Environment Remote Sensing Evaluation Based on GPU
作  者：
LI Lin;GU Jinfeng;SONG Anjie;ZHENG Haining;CAO Jin;ZHU Dehai;College of Information and Electrical Engineering,China Agricultural University;Department of Computer Science,University of Sheffield;
关键词：
ecological environment evaluation;;remote sensing;;parallel processing;;GPU;;CUDA
摘  要：
In order to solve the problem of the model's slowly processing speed of ecological environment remote sensing evaluation currently,a framework about GPU image processing was designed with data partitioning and scheduling asynchronous transmission which was based on the in-depth analysis about the data transmission bottleneck of heterogeneous CPU + GPU general computing platform. It included the carbon fixed quantity and grassland degradation index, whose intrinsic parallelism met the GPU computing features. For the above models,it was put forward based on CUDA parallel implementation.The core link of indexes for evaluation of ecological environment of remote sensing data standardization and weighted fusion of CUDA parallel module were implemented. Finally,the effectiveness of technical methods was verified through experiments,as the scale of data became larger,the parallel execution speed of three business models became faster,the speedup ratio of the fixed amount of carbon achieved a8. 04 times execution rate lift; the speedup ratio of the index of grassland degradation achieved a 12. 21 times execution rate lift; and the speedup ratio of the index of ecological environment achieved a 7. 45 times execution rate lift. At the same time,the speedup ratio was decreased as the number of input data files increased,equipment between I/O was still the main factor which restricted the running efficiency of the algorithm.

相似文章

导出引用
计量
文章访问数: 13
HTML全文浏览量: 0
PDF下载量: 1

所属期刊

推荐期刊

友情链接Friendly link
农业信息研究所Agricultural information institute 农业智能知识服务平台Agricultural intelligent knowledge service platform 农业学术服务平台Agricultural Knowledge Service System 中国知网CNKI 维普网VIP 万方WANFANG DATA
联系我们Contact us

电话Tell：010-82109652-808

邮箱E-mail：agrijournal@caas.cn

服务Service
关于我们About us 意见建议Opinions and suggest
版权说明Copyright
单位：中国农业科学院农业信息研究所 中国农学会 © 2017中国农业科学院农业信息研究所 ICP备案号：京ICP备09089781号-46