Servers & Systems: The Right Compute

How server memory advances real-time analytics


Unlocking Big Data’s secrets with in-memory computing: Discover how server memory manages and processes massive datasets.

Blog_DDR4_inmemorycomputing.jpgBy now, Big Data—which, as you know, refers to the large amounts of complex information that organizations gather, retain and analyze to discover useful insights and trends—is not a new concept. Making this data and its secrets accessible through analysis gives our customers a competitive edge.

As data volumes increase, however, processing it in a timely manner can tax IT infrastructure. But with enough computing power, such as that provided by in-memory computing tools, your company can analyze vast quantities of structured, semi-structured, and unstructured data from a variety of sources.

Traditionally, data was placed in storage or drives. When needed, portions of the data were moved from the drives and accessed the server’s memory. All to often, the frequent accesses to drives caused a bottleneck that reduced processing speed.

The solution? In-memory computing to provide the computing power needed to unlock Big Data’s secrets

As we at HPE define it, in-memory computing stores data in RAM, rather than in databases hosted on disks. Because RAM-stored data is readily available, in-memory computing enables extremely fast processing response times and complex analyses on large datasets in minutes.

A few types of in-memory computing solutions are defined by how they use server memory:

  • Memory first: Captures transactions in memory and persists to disk.
  • Memory only: Processes all data in memory.
  • Memory after: Adds in-memory options to traditional databases.

Although each system has its benefits and drawbacks, the growth of Big Data and the related need to analyze that data in real time or near real time points to a memory first architecture as the best option. It uses server memory to enable processing speeds and capacities far greater than what a disk or SSD system can achieve alone, while using a combination of memory, disks, flash, or SSDs to store transactions, back up operations, and scale applications.

The use of server memory to manage and process massive datasets enhances companies’ ability to generate a broader, data-driven view of business operations.

Learn more about unlocking the business secrets contained in Big Data using in-memory computing.

Featured articles


0 Kudos
About the Author


Michael Pratt’s passion is helping customers go further. His job is making products that make servers go further. He spends his days connecting the two.