This site requires Javascript in order to view all its content. Please enable Javascript in order to access all the functionality of this web site. Here are the instructions how to enable JavaScript in your web browser.

AI Leadership with NVIDIA DGX

Unbeatable AI Performance at Scale

Driving AI Innovation Across Industries

AI projects at the forefront of innovation, shattering world records, are built on NVIDIA DGX^™ systems. Leading organizations across industries use DGX to power their AI initiatives and change the world.

9

of the top 10 U.S. Government Institutions

8

of the top 10 U.S. National
Universities

7

of the top 10 U.S.
Hospitals

7

of the top 10 Global Car
Manufacturers

Performance Matters

The New Standard In Backtesting

NVIDIA DGX-2 with accelerated Python processed 20 million trading simulations and set a new standard in the latest STAC-A3 backtesting benchmark report.

LEARN MORE

Shattering World Records

NVIDIA DGX systems continue to set AI performance records in MLPerf ¹—a set of benchmarks that measure machine learning training performance across a diverse set of usages.

READ MORE

1 See mlperf.org for more info.

Raising the Bar for AI Infrastructure

NVIDIA’s new DGX SuperPOD, named “Selene,” built based on the DGX SuperPOD reference design, ranks No. 5 in the world and No. 5 on the new Green500 list of the world’s most energy-efficient systems.

LEARN MORE

1 MLPerf 0.6 submission information: Per-accelerator comparison using reported performance for NVIDIA DGX-2H servers (16 NVIDIA V100 Tensor Core GPUs) compared to other submissions at the same scale except for MiniGo where the NVIDIA DGX-1 servers (8 V100 GPUs) submission was used. | MLPerf ID Max Scale: Mask R-CNN: 0.6-23, GNMT: 0.6-26, MiniGo: 0.6-11 | MLPerf ID Per Accelerator: Mask R-CNN, SSD, GNMT, Transformer: all use 0.6-20, MiniGo: 0.6-10. See mlperf.org.

NVIDIA DGX Systems Power the World’s Most Powerful Supercomputers

Eight of the world’s most powerful supercomputers in the TOP500 are built on NVIDIA DGX. These enterprises have used DGX to scale up massive supercomputing infrastructure in just weeks

Building World-Class Supercomputing has never been Easier

Build Leadership-Class AI Infrastructure

Building world-class, scalable AI infrastructure used to be complex, taking months or even years to do. With NVIDIA DGX SuperPOD, you get a first-of-its-kind AI supercomputing infrastructure that delivers groundbreaking performance. Deployable in weeks as a fully integrated system, DGX SuperPOD is architected to solve the world’s more challenging AI problems.

DGX SuperPOD is composed of DGX systems, which are specifically designed to meet the unique demands of enterprise-grade AI.

WATCH VIDEO

Future-Proof Your AI Data Center

NVIDIA DGX SuperPOD with NVIDIA DGX A100 is now available to tackle your most complex AI challenges. Built using the world’s first universal AI platform, it supports training, inference, and analytics workloads on one future-proofed AI infrastructure.

LEARN MORE

DGX SATURNV Powers NVIDIA

Use our experience building the world’s largest AI data centers and thousands of leading-edge accelerated compute nodes. Our NVIDIA DGX™ SATURNV powers our most important work, providing a tested and proven infrastructure designed to meet the rigorous demands of AI.

Learn More

View Infographic

View Case Study