Home > Servers > Rack and Tower Servers > AMD > White Papers > Finish machine learning preparation tasks on Kubernetes containers in less time with the PowerEdge R7525 > Overview
This Dell EMC solution did image processing work more quickly than a similarly priced server from HPE
At Principled Technologies, we configured two current-generation, dual-socket servers so that they each had a similar hardware price: a Dell EMC™ PowerEdge™ R7525 powered by AMD EPYC™ 7502 processors and an HPE ProLiant DL380 Gen10 powered by Intel® Xeon® Gold 6240 processors.
To test each server, we ran a synthetic, containerized workload on Kubernetes. We designed this workload to emulate simple image processing tasks that a company might run in the preparation phase of machine learning. The PowerEdge R7525 server required less time to process 3.3 million images, finishing in 11 minutes, 12 seconds compared to 25 minutes, 22 seconds for the ProLiant DL380 Gen10 server. On average, the Dell EMC server processed images at 2.26 times the rate of the HPE server—4,922 frames per second (FPS) versus just 2,173 FPS.
Because the Dell EMC server completed its work faster than the HPE solution and at a similar price, it presented 2.32 times the value in terms of image processing performance vs. hardware cost.