Abstract

Edge computing, in a nutshell, brings compute power close to the source of the data. As Internet of Things (IoT) endpoints and other devices generate more and more time-sensitive data, edge computing becomes increasingly important. Machine Learning (ML) and Artificial Intelligence (AI) applications are particularly suitable for edge computing deployments. The environmental conditions for edge computing are typically vastly different than those at centralized data centers. Edge computing sites might, at best, consist of little more than a telecommunications closet with minimal or no HVAC. Thus, rugged, short-depth, small form factor servers are ideal for such deployments. The Dell PowerEdge XR4000 Server checks all of those boxes.

Dell Technologies commissioned Tolly to evaluate the ML performance of Dell’s XR4000 using the industry standard MLPerf™ Inference v2.0 benchmarking suite and compare that to a prior-generation Dell PowerEdge server and competing servers from Supermicro and Lenovo. The tasks and scenarios will be explained in detail later in this paper. The tables below provide a summary of the ML/AI advantages of the Dell PowerEdge XR4000 over both competing systems and prior-generation Dell systems. The Dell PowerEdge XR4000 outperformed competing systems and prior-generation Dell technology by up to 12% in single stream, multi stream and offline tests across image classification, object detection, medical imaging and natural language processing ML inference v2.0 workload test scenarios.