DGX A100 : Universal System for AI Infrastructure

Academic & Research institutes undergoing AI transformation require a platform for AI infrastructure that improves upon traditional approaches, which historically involved slow compute architectures siloed by analytics, training, and inference workloads. The old system created complexity, drove up costs, and constrained the speed of the scale. That's why NVIDIA created the NVIDIA DGX A100. The NVIDIA DGX A100 is the 3rd generation of the world's most advanced, purpose-built AI and data science system. Revolutionizing the enterprise data center with infrastructure that's designed to unify AI and data science workloads. The new, universal platform and architecture delivers:

• Game-changing performance built on the NVIDIA A100 GPU delivering the world’s first 5 PFLOPS AI system capable of running analytics, training, and inference workloads simultaneously with ease.
• Unrivaled flexibility with Multi-Instance GPU (MIG) innovation that allows 7X inference performance per GPU and the ability to assign resources that are right sized for specific workloads.
• Unparalleled TCO/ROI metrics with all the performance of a modern AI data center at 1/10th the cost, 1/25th the space and 1/20th the power