In-Memory Computing Goes Open Source

In-memory computing specialist GridGain Systems Inc. said Nov. 3 that its data fabric code has been accepted by the Apache Software Foundation’s incubator program under the name “Apache Ignite.”

GridGain, Foster City, Calif., said the move is intended to promote adoption of its in-memory data fabric technology while enabling a new class of “fast data” transactional, analytic and hybrid real-time framework applications.

In a blog post, GridGain Founder and CTO Nikita Ivanov argued that in-memory computing is emerging as “the only practical way to scale to today’s computing demands.” The falling cost of RAM should also enable enterprises running commodity hardware to tap into in-memory computing, Ivanov added.

Moreover, he argued that the growing demands of big data, software-as-a-service, mobile computing, Internet scaling along with falling RAM prices have spawned a range of new applications accessing and processing data in memory.

Contributing its in-memory data fabric intellectual property to the Apache incubator is intended to help the technology become a industry standard, Ivanov asserted. He added that GridGain would continue contributing to the Apache Ignite code base while adding new features to its commercial product.

Meanwhile, the non-profit Apache Software Foundation will manage the platform’s core code, GridGain said. The open source in-memory data fabric technology is distributed under the Apache 2.0 license.

GridGain shifted to an open source model earlier this year through an Apache 2.0 license. “We wanted to introduce [in-memory computing] to the mass market in a way that would give developers maximum freedom to experiment with it,” said Ivanov.

Making in-memory computing code available on open source platforms like GitHub resulted in a more than 2,000 percent increase in downloads over several months, the company claimed.

The ultimate goal, Ivanov added, is broad adoption of open source in-memory data fabric technology to enable a new class of transactional and analytical applications based on Apache Ignite.

“Apache Ignite has all the right ingredients to become for the fast data world of the future what Hadoop is for big data today,” claimed Ivanov.

Among the potential applications for in-memory data fabric technology is speeding new drug discovery, GridGain noted. The British biotech company e-Therapeutics recently started using GridGain’s in-memory data grid. The data fabric is used to handle the fast data processing involved in parallelizing e-Therapeutics’ code. The code is written mostly in Java.

The biotech firm said GridGain’s 20-node cluster delivered as much as a 20-fold increase in the execution of its algorithms. Its proprietary algorithms running on a graph analytics database are housed in an in-memory cluster and are used to identify key proteins linked to the development of diseases like cancer.

Other proponents of in-memory computing note that GridGain’s approach leverages current developer skills while accelerating existing Hadoop applications. That, proponents argue, will help ease the transition to in-memory computing.

Recent items:

How a Facebook-Like Graph Powers Drug Discovery

In-Memory Computing is Key to Real-Time Analytics