IBM Announces New PureData System for Hadoop

Bookmark and Share

New technologies designed to help companies and governments tackle big data have been unveiled by IBM. The new technologies include the new IBM PureData System for Hadoop, designed to make it easier and faster to deploy Hadoop in the enterprise, and "BLU Acceleration," which is aimed at improving analytical performance in data management systems.

All of the announcements are aimed at accelerating big data insight for customers, Bernie Spang, director, Strategy, Database Software & Systems, IBM Information Management, tells 5 Minute Briefing. Noting that IBM CEO Ginni Rometty has talked about big data being the next natural resources,  Spang observed that the value of big data to  IBM clients is enabled by having the ability to mine this resource and refine it through analytics to deliver value at the point of impact across the business. “And that value is greater insights from being able to process more data than ever before - so you can detect patterns, trends and have better answers faster than ever before. The impact that we have been talking about - better analytics delivering better answers than ever before - is to help our clients uncover opportunities to grow new revenue, to better serve their customers, patients or citizens, and to identify and reduce - ideally eliminate - risk and threat and fraud,” explains Spang.

IBM PureData System for Hadoop is a step forward in IBM’s strategy to deliver a family of systems with built-in expertise that helps organizations lower the cost and complexity associated with information technology. This new system integrates IBM InfoSphere BigInsights, which helps  companies to cost-effectively manage and analyze data and add administrative, workflow, provisioning and security features, along with analytical capabilities from IBM Research.

BLU Acceleration is intended to help users to have faster access to key information, to achieve better decision-making.  The software extends the capabilities of traditional in-memory systems - which allows data to be loaded into Random Access Memory instead of hard disks for faster performance - by providing in-memory performance even when data sets exceed the size of the memory. During testing, some queries in a typical analytics workload were more than 1000 times faster when using the combined innovations of BLU Acceleration. Innovations in BLU Acceleration include "data skipping," which  provides the ability to skip over data that doesn't need to be analyzed, such as duplicate information; the ability to analyze data in parallel across different processors; and greater ability to analyze data transparently to the application, without the need to develop a separate layer of data modeling. Another industry-first advance in BLU Acceleration, according to IBM, is called "actionable compression," where data no longer has to be decompressed to be analyzed.

BLU Acceleration, Spang noted, is being included in a new release of DB2 that IBM is delivering to market this quarter, and elements of the technology are in a new version of Informix that includes TimeSeries Acceleration for operational reporting and analytics on smart meter and sensor data.

IBM also introduced a new version of InfoSphere BigInsights, IBM’s enterprise-ready Hadoop offering, which makes it simpler to develop applications using existing SQL skills, compliance security and high availability features vital for enterprise applications. BigInsights offers three entry points: free download, enterprise software and now the new expert integrated system - IBM PureData System for Hadoop.

There is also a new version of InfoSphere Streams, “stream computing” software that enables massive amounts of data in motion to be analyzed in real-time, with performance improvements, and simplified application development and deployment.

All offerings are available in Q2, except the PureData System for Hadoop, which will start shipping to customers in the second half 2013.

For more information, visit, and