Home > Servers > Rack and Tower Servers > Intel > White Papers > Run compute-intensive Apache Hadoop big data workloads faster with Dell EMC PowerEdge R640 servers > Introduction
A Hadoop cluster of PowerEdge R640 servers powered by 2nd Generation Intel Xeon Scalable processors completed three compute-heavy big data workloads in less time than previous-generation Dell EMC R630 servers by processing more data per second
Your organization likely generates large volumes of data from numerous sources continuously. This data can range from how long users are on a web page to the length of routine sales team video calls. Extracting insight from this disparate information often requires running complex, compute-intensive workloads quickly on multiple data sets.
Aging servers typically cannot deliver the speed that newer servers can offer for these compute-intensive workloads. Current-generation servers can deliver a performance improvement that helps your organization now and allows you to continue accumulating and using data effectively. Faster servers can process and analyze data more quickly, so marketing teams, for example, can more quickly determine who to target for their next email campaign.
In our data center, an Apache Spark™ cluster of current-generation Dell EMC™ PowerEdge™ R640 servers featuring 2nd Generation Intel® Xeon® Scalable processors outperformed a cluster of previous-generation Dell EMC PowerEdge R630 servers in three compute-intensive, big data workloads. The workloads identified topics in a large document, classified information to make a prediction, and counted words in a data set. Moving these workloads to new PowerEdge R640 servers and getting better performance can help your organization can meet today’s demands and offer the computing power necessary to face the challenges of tomorrow.
In addition to newer, faster Intel processors to run queries and algorithms, the PowerEdge R640 servers had more drive bays than their predecessors. More drive bays allow you to add more storage to each server and store more data, which could help prevent server bottlenecks and promote speedy access to databases.