NVIDIA DGX SuperPOD

Unified for AI training, inference acceleration & data analytics

The NVIDIA DGX SuperPOD™ is an AI supercomputing infrastructure that delivers groundbreaking performance, deploys in weeks as a fully integrated system, and is designed to solve the world’s most challenging AI problems.

superpod-improve-productivity-workflow

Improve productivity & workflow

superpod-faster-simplified-deployment

Faster, simplified deployment

superpod-trusted-expertise-support

Trusted expertise & support

Scalable Unit Racks

The basic building block of the SuperPOD is an SU capable of 48 AI PFLOPS, which consists of 20 NVIDIA DGX™ A100 systems. This size optimizes both performance and cost while still minimizing system bottlenecks so that complex workloads are well supported. Capable of scaling from hundreds to thousands of nodes while maximizing Deep Learning performance.

Compute: Scalable Unit

Compute Fabric & Management Rack

NVIDIA SuperPOD Scalable Unit Racks - Compute Fabric & Management Spine Rack

Storage Rack

NVIDIA SuperPOD Scalable Unit Racks - Storage Rack

Storage Options Optimized for the NVIDIA DGX A100

Committed to the highest level of AI computing

From large-scale clusters to servers to workstations, AMAX offers unparalleled expertise in application optimized solutions to meet your GPU computing needs at any scale.