Large Scale Query Analysis on HPC and Cloud Systems
M. Lewis, EVL
Participants: Michael Lewis
EVL PhD candidate Michael Lewis presents his preliminary research on large scale query systems, and query complexity with regards to query pre-processing and memory usage within a tightly coupled high performance computing environment and within a cloud environment.
Wednesday, June 15, 2016
1:00 PM - 2:00 PM
EVL Cyber-Commons, 2032 ERF
From spreadsheets to database and Cloud services, data management software and systems use query based features for focused data inquiry and to examine results inquired from connected relationships among its components. Today’s data-management systems are able to perform queries on SQL, NoSQL and semantic based structures for a scalable range of data. Partitioning techniques, network reduction algorithms, and memory based indexing schemes have been heavily researched and integrated into different data management products, in order to produce faster and scalable query results. However, there has been little to no research in using memory management and join pre-processing within a distributed environment to create scalable queries and to understand scale, based on query complexity.
Date: June 15, 2016