This paper showcases two servers, the Dell EMC PowerEdge R7525 and R7515 from Dell Technologies that are powered by AMD™  processors and accelerated by NVIDIA GPUs (Tesla T4, Quadro RTX8000, and A100); and how they perform under various ML and DL workloads administered by the MLPerf™ Consortium (https://mlperf.org). 

MLPerf Inference is a benchmark suite for measuring how fast Machine Learning (ML) and Deep Learning (DL) systems can process inputs and produce results using a trained model. The benchmarks belong to a diversified set of ML use cases that are popular in the industry and provide a need for competitive hardware to perform ML-specific tasks. Furthermore, each of these benchmarks is further categorized under various run conditions in which a hardware platform may have to perform, like as an inference server in large-scale HPC computations or as an edge device handling multi-streaming data to perform inferencing off a trained model. Hence, good performance under these benchmarks signifies a hardware setup that is well optimized for real world ML inferencing use cases. The second iteration of the benchmark suite (v0.7) has evolved to represent relevant industry use cases in the data center and edge environments. Users can compare overall system performance in AI use cases of natural language processing, medical imaging, recommendation systems, and speech recognition as well as different use cases in computer vision.