arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.03338cs.DB
收藏

WarpFlow:探索PB级时空数据

WarpFlow: Exploring Petabytes of Space-Time Data

Catalin Popescu, Deepak Merugu, Giao Nguyen, Shiva Shivakumar

摘要:

WarpFlow是一个快速,交互式的数据查询和处理系统,专注于PB级时空数据集和Tesseract查询。随着智能手机和移动导航服务的快速增长,我们现在有机会从根本上改善城市移动性,减少人们和包裹在全球每分钟英里移动的摩擦。WarpFlow加速了数据工程师在这些数据集上工作的三个关键指标--获得第一个结果的时间,获得全尺寸结果的时间和机器学习训练模型的时间。

英文摘要:

WarpFlow is a fast, interactive data querying and processing system with a focus on petabyte-scale spatiotemporal datasets and Tesseract queries. With the rapid growth in smartphones and mobile navigation services, we now have an opportunity to radically improve urban mobility and reduce friction in how people and packages move globally every minute-mile, with data. WarpFlow speeds up three key metrics for data engineers working on such datasets -- time-to-first-result, time-to-full-scale-result, and time-to-trained-model for machine learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑