In-Memory Computing: Delivering Real-Time BI to the Enterprise

Seismic shifts can happen in nature – and every once in a while, they happen in technology.  Examples include personal computing, mobile computing, the Internet, and more recently cloud computing and Big Data.

In-memory computing, one of the latest significant technology advancements, is the alignment of new, complementary technologies that can revolutionize how businesses use and manage data and redefine competitive landscapes in many industries. The move to in-memory computing is not an alternative to traditional solutions, it will become the way computing is done. When and how companies move to in-memory computing is becoming a critical business decision.

In-memory computing represents the synthesis of multiple technology innovations that work together to deliver real-time, data-driven business intelligence to the enterprise. These include:

Keeping memory local

Analyzing vast data sets for business insights is beyond the bounds of traditional database and analytics solutions that rely on mechanical data storage and access. However, the availability of affordable memory modules has hastened the development of in-memory computing models in which all relevant data is maintained in the main memory of the computing system, rather than in remote bulk storage systems.  In-memory systems can render data for analysis as soon as it is generated, with data-driven business insights available almost instantly.

Moving beyond relational databases.

Several leading database providers have re-architected their legacy database technologies to better meet the challenges of big data. New database solutions combine the features of traditional row store processing with columnar data processing and in-memory columnar compression, a set of technologies that vastly speeds the scanning of immense data sets and analytical querying. It all adds up to speed-of-thought analytics and more cost-effective memory and storage systems.

Harnessing Big Data.

Apache Hadoop* has become the de facto standard for storing and analyzing huge, unstructured data sets. The Intel® Distribution of Apache Hadoop* software (Intel® Distribution) is a software platform that provides distributed processing and data management for enterprise applications that analyze massive amounts of diverse data. The Intel Distribution provides enterprise–class management tools and data security as part of a cost-effective solution for ingesting, preparing, and storing warm data for inclusion in in-memory computing and real-time analytics environments.

Optimizing server platforms for in-memory computing.

The Intel® Xeon® processor E7 v2 family powers a new generation of servers that are specifically optimized for in-memory computing, delivering up to 2x higher performance than previous generation servers[1] and providing up to 3x higher memory scalability[2]. These new server platforms are ideal for the data-intensive, mission-critical demands of in-memory computing solutions.

Supporting these ground-breaking compute solutions at enterprise scale requires optimized servers with massive memory capacity, parallel execution resources, high system bandwidth, and advanced built-in reliability. To address the heavyweight demands of in-memory computing, the Intel® Xeon® processor E7 v2 product family unlocks the potential of big data and delivers large scale in-memory analytics for data-driven decision making and improved competitive advantage. Learn more about computing power of the Intel Xeon processor E7 v2 family.

Get the details about in-memory computing and on-demand business intelligence in the white paper "Changing the Way Businesses Compute…and Compete.”

[1]Source: Intel internal measurements November 2013. Configurations: Baseline 1.0x: Intel® E7505 Chipset using four Intel® Xeon® processors E7-4870 (4P/10C/20T, 2.4GHz) with 256GB DDR3-1066 memory scoring 110,061 queries per hour. Source: Intel Technical Report #1347. New Generation 2x: Intel® C606J Chipset using four Intel® Xeon® processors E7-4890 v2 (4P/15C/30T, 2.8GHz) with 512GB DDR3-1333 (running 2:1 VMSE) memory scoring 218,406 queries per hour. Source: Intel Technical Report #1347.

[2] On a 4-socket natively-connected platform: Intel® Xeon® processor E7 family supports 64DIMMS, max memory per DIMM of 32 GB RDIMM; Intel® Xeon® processor E7 v2 family supports 96DIMMs, max memory per DIMM of 64 GB RDIMM. This enables a 3x increase in memory.