Questions? Feedback? powered by Olark live chat software
Return to News Room

Press Release

Hazelcast 3.5 Brings Efficiencies of Web Scale In‐memory Computing to the Enterprise

New Performance Increases and Dev Ops Improvements Accelerate Application Speed and Agility.

News highlights:

  • Hazelcast High Density Memory Store now provides 100’s of GB of near cached data to clients for massive application scalability.
  • Extensive, across‐the‐board increases in performance mean applications operate in real‐time regardless of data center and client location.
  • Enterprise‐class operation capabilities ensure low costs and economies of scale formerly only accessible to cloud service providers.

LONDON, UK, and Palo Alto, Calif., 17 June 2015Hazelcast, the leading provider of operational in‐memory computing with over 8,000 company deployments, today announced the general availability of Hazelcast 3.5. With this new version, Hazelcast High‐Density Memory Store is now available to the Hazelcast client as a near cache providing access to hundreds of gigabytes of in‐memory data on a single application server. All that data available in local application memory means an Instant, massive increase in data access speed on fewer application server instances to power the same total throughput. This vastly increases application performance while reducing hardware footprint and management complexity.

Already fast, Hazelcast’s performance engineers have streamlined the operation of every subsystem yielding across‐the board performance increases of 20% ‐ 100%. Parallel query performance has been increased by an order of magnitude. Latency variability of distributed operations have been shaved to less than 5%, meaning smoother, more predictable operation under any load. For a complete report of the performance benchmark testing of Hazelcast 3.5 compared with 3.4, please visit

Big applications often mean big headaches for operations teams. The 3.5 release introduces a host of new tools and features to make running an operational in‐memory computing platform more manageable. New push‐button deployment options make short work of provisioning a new cluster, reducing it to an easily reproducible process that completes in minutes. Robust new WAN replication capabilities now push data to multiple data centers for fast, local access to data for satellite installations. Predictable latency and expanded monitoring capabilities make Hazelcast even more stable and easier to visualize out‐of‐tolerance events that may require action.

“Hazelcast 3.5 is our best release yet, with a full set of enterprise management features and remarkable performance increases. The Hazelcast community is growing rapidly and we are now established as a trusted, enterprise‐class platform for mission critical applications. It is widely recognized that we have a compelling and proven business case for companies who are looking to upgrade to in‐memory for breakthrough application speed and scale,” said Greg Luck, CEO of Hazelcast.

Hazelcast 3.5 open source is available today for download at and pricing information for service and support, as well as information on Hazelcast Enteprise’s advanced features for large scale data center deployments, is available at

About Hazelcast, Inc.

Hazelcast is the leading provider of operational in-memory computing with tens of thousands of installed clusters and over 16 million server starts per month. The Hazelcast operational in-memory computing platform helps leading companies, like Capital One, Chicago Board Options Exchange, Deutsche Bank, Ellie Mae, and Mizuho Securities USA, manage their data and distribute processing using in-memory storage and parallel execution for breakthrough application speed and scale.

Hazelcast’s developer-friendly approach makes it easy to modernize existing applications while providing a platform for building new innovative solutions. Hazelcast is headquartered in Silicon Valley’s Palo Alto, with offices in Ankara, Istanbul, London, and New York City. For more information, visit or follow us on Twitter @Hazelcast