Your Browser is Out of Date

Nytro.ai uses technology that works best in other browsers.
For a full experience use one of the browsers below
Harness the Power of Dell EMC PowerEdge R7525/R7515 Servers with NVIDIA GPUs for Machine Learning Inference
Abstract Introduction MLPerf Inference v0.7 Executing Inference workloads on Dell EMC PowerEdge servers Results Conclusion
Summary

Summary

Summary

  • As shown in the charts above, Dell EMC PowerEdge R7515 and R7525 performed well in a wide range of benchmark scenarios. The benchmarks that are discussed in this paper included diverse use cases; for instance, image dataset inferencing (Object Detection using SSD-Resnet34 model on COCO dataset), language processing (BERT model used on SQUAD v1.1 for machine comprehension of texts), and recommendation engine (DLRM model with Criteo 1 TB clicks dataset). 

    The results were produced by two hardware platforms (R7525 & R7515) that used AMDTM processors that were paired with different configurations of NVIDIA GPU accelerators (Tesla T4x4 and T4x8, Quadro RTX8000x3, A100x2, and A100x3). These results can serve as a guide to identifying the configuration that best matches the inference requirements of a real-world production environment.