Big DataCloudData StorageGreen-ITInnovationWorkspace

IBM Expands PureSystems Integrated Mainframes For Big Data

Peter Judge has been involved with tech B2B publishing in the UK for many years, working at Ziff-Davis, ZDNet, IDG and Reed. His main interests are networking security, mobility and cloud

IBM Converged mainframes now available for Big Data analysis

IBM has extended its PureSystems range of converged mainframes, which launched in April, adding specific versions for Big Data applications, and announcing a PureSystems customer.

PureSystems combine servers using IBM’s Power RISC processors with Intel-based servers, and are intended to provide a platform for quick development of applications, enabling in-house systems to get the benefits that normally go with cloud development.

Big Data, big problems?

The new PureData System units are designed to analyse data to support jobs such as marketing and sales, helping companies reduce customer churn and produce better marketing campaigns. They come in three models for transactions, analytics on warehoused data, and “operational analytics” which covers analysis of transactions in real time for tasks such as fraud detection and prevention. .


The PureSystems strategy is based on converged “Pure”  hardware with simplified management; above that is PureFlex, layers of software to provide an in-house cloud  platform for application building, and Pure Apps use middleware on top of that, and are based on “patterns” that can be either developed in house or shared amongst partners.

“It’s like an appliance,” IBM senior server consultant Tikiri Wandaragula told TechWeekEurope. “The biggest problem with an appliance is it can date very quickly. Breaking it down in this fashion lets you have an appliance which can regenerate itself as the technology keeps evolving.”

The Big Data systems can be up and running in 24 hours, and can run complex analytics fast, handling up to 100 databases on a single system, IBM said.

The PureSystems family has had little media exposure since its launch in April, because there has been little to talk about, but today also sees the long-awaited announcement of a customer. The US-based Premier healthcare alliance is using a PureData System to analyse a large  database of clinical, financial and outcomes data covering four patient discharges from 2700 hospitals and 90,000 iother health providers – a pile of data amounting to 2.5 million real-time clinical transactions a day and representing a turnover of $43 billion a year.

“One of our biggest challenges has been the ability to quickly acquire and analyse big data, then place the insights from that data directly into the hands of caregivers,” said Todd Wilkes, vice president of development at Premier. The PureData box lets him analyse data with sub-second response time, and share it with business partners, so he can see better what is going on in those hospitals.

Other partners putting their names on the PureSystems dance card include DynaFront Systems and PCCW Solutions, whieh have both put PureSystems in their own data centres, to run services for their clients. IBM also has a list of around 50 software vendors who signed up at the launch of the family.

Do you know cloud computing? Try our quiz!