In-Memory Computing Performance Benchmark

Print Friendly, PDF & Email

This article is the fourth in an editorial series that will provide direction for enterprise thought leaders on ways of leveraging in-memory computing to analyze data faster, improve the quality of business decisions, and use the insight to increase customer satisfaction and sales performance.

In last week’s article, we set the stage for in-memory computing technology in terms of its current state as well as its next stage of evolution.

insideBIGDATA_Guide_IMCPerformance Benchmark

It is becoming increasingly clear that the key to increasing the speed of processing of both transactional and analytical data, especially for growing workloads and data volumes, is to adopt the IMC paradigm. Building on fundamentally the same parallel computing architecture as supercomputers used in scientific applications, IMDGs run on a clustered set of servers to hold and analyze memory-based data. IMDGs keep access times constant, which is exactly the characteristic needed by applications which have to handle growing workloads. More significantly, IMDGs can host parallelized applications to manage and analyze data stored on the grid’s servers. This is the key to their ability to perform real-time analytics.

The practical benefits of IMC were examined in a research study conducted by Aberdeen Group— “In-Memory Computing: Lifting the Burden of Big Data.”2 The report compared companies that had fully implemented IMC solutions with companies that had not. 196 organizations world-wide, currently engaged with big data, were examined. These companies were chosen to represent a broad cross-section of industries and sizes. The companies dealt with data stores ranging in size from several terabytes to multiple petabytes. A relatively small segment of 33  companies indicated they’ve implement IMC.

The survey results revealed that companies adopting IMC technology outperformed their peers by two orders of magnitude. They were able to
process much more information, must faster and with greater efficiency. Respondents using IMC showed substantially better performance in dealing with the volume of their data. They successfully store large amounts and analyze more data at once, both in terms of size and the percentage of overall business data that could be processed. The real gains, however, came in the velocity category. Organizations with IMC reported an average of 42 seconds for their analytical system to respond to a query. This was over 100x faster than organizations without IMC—these companies saw an average response of an hour and fifteen minutes. The unique ability to analyze data in-memory allowed for rapid processing even with large-scale data sets.


In the table above, the IMC benefit also is determined for the volume of data being managed and analyzed. The impressive results show a clear
advantage for IMC where 2.1 times more data is managed (38TB versus 18TB) and 3.5 times more data is analyzed (14TB versus 4TB). These
results show that IMC tends to allow companies to manage an ever-increasing amount of data, faster than before.

Next week’s article will look at the new GridGain In-Memory Data Fabric. If you prefer the complete insideBIGDATA Guide to In-Memory Computing  is available for download in PDF from the insideBIGDATA White Paper Library, courtesy of GridGain.

Speak Your Mind