Aster Data Systems Presenting on MapReduce and High-Concurrency Data Warehousing at Prestigious VLDB Conference

VLDB09 Conference, Lyon, France - August 24, 2009 - Aster Data Systems, a proven leader dedicated to providing the best data analytics and management platform for ‘Big Data’ applications, is proud to announce that Aster engineers will be presenting two research papers on MapReduce and high-concurrency query processing at the 35th International Conference on Very Large Data Bases (VLDB). MapReduce is a programming model that was popularized by Google in 2004 to process large unstructured data sets distributed across thousands of nodes; Aster Data has further standardized MapReduce by integrating MapReduce with SQL to deliver SQL/MapReduce, an easy-to-use framework for enterprises developing and managing Big Data applications. The annual VLDB Conference is the premier international venue for database researchers, vendors, practitioners, application developers, and users, organized every year by the VLDB Endowment.

“SQL/MapReduce: A Practical Approach to Self-Describing, Polymorphic, and Parallelizable User-Defined Functions,” was written by Eric Friedman, Peter Pawlowski, and John Cieslewicz, all of Aster. The paper presents Aster nCluster’s SQL/MapReduce (SQL/MR) framework and a description of the programming model, query processing semantics, and implementation. Aster is the only MapReduce vendor presenting as part of the MapReduce industrial session. The other MapReduce session presenters are from Google and Yahoo! Research. The paper can be seen at http://www.asterdata.com/resources/downloads/whitepapers/sqlmr.pdf.

“A Scalable, Predictable Join Operator for Highly Concurrent Data Warehouses,” was written by Aster co-founder and chief scientist George Candea, Neoklis Polyzotis of UC Santa Cruz, and Radek Vingralek of Aster. This paper describes a new way of processing concurrent queries in massively-parallel data warehouses that improves query throughput by up to two orders of magnitude; in classic query engines, concurrent queries typically cause performance to plummet. The paper shows how this new approach scales gracefully to provide predictable execution times and reduce contention. The paper is available at http://dslab.epfl.ch/pubs/cjoin.

"We firmly believe that our commercial success has been and will continue to be driven by our emphasis on research and innovation. We take pride in coming up with revolutionary technology concepts and finding ways to deliver them in the marketplace. VLDB is one of the top forums where innovative ideas in data management are created and exchanged, and we're proud to be a contributor and participant," said Tasso Argyros, CTO for Aster.

Aster’s SQL/MR framework enables enterprises to harness the power of MapReduce while managing their data in Aster nCluster, a massively-parallel (MPP) relational database for frontline data warehousing and analytics. Aster nCluster was the first database system to offer enterprise-class MapReduce capabilities such as integration with BI and ETL tools, SQL support, backup and recovery, transactional data consistency, support for interactive as well as batch analysis, etc.

Find more information about SQL/MR, including sample use-cases and code at http://www.asterdata.com/mapreduce.

About Aster Data Systems
Aster Data Systems is a proven leader dedicated to providing the best data analytics and management platform for frontline data warehousing – the first DBMS to tightly integrate SQL with MapReduce - providing rich insights on data managed on clusters of inexpensive commodity hardware. The Aster nCluster database cost-effectively powers rich analytic applications for companies such as Coremetrics, MySpace, aCerno (an Akamai company), and ShareThis. Running on low-cost off-the-shelf hardware, and providing 'hands-free' administration, Aster enables enterprises to meet their data warehousing and analytics needs within their budget. Aster is headquartered in San Carlos, California and is backed by Sequoia Capital, JAFCO Ventures, IVP, Cambrian Ventures, and First Round Capital, as well as industry visionaries including David Cheriton and Ron Conway. For more information please visit http://www.asterdata.com, or call 650-232-4400.

Aster Data Systems, Aster nCluster and the Aster logo are registered trademarks of Aster Data Systems. All other brands and trademarks referenced herein are acknowledged to be trademarks or registered trademarks of their respective holders.

Press Contact:
Marlena Fernandez Berkowitz
ZAG Communications for Aster Data Systems

The Best Insights Possible
Whitepaper: A New Approach for Large-Scale Data Management and Data Analysis
Whitepaper: Deriving Deep Insights from Large Datasets
Research Report: MapReduce and the Data Scientist