NVIDIA DGX A100

The Universal System for AI Infrastructure

The World’s First AI System Built on NVIDIA A100

NVIDIA DGX™ A100 is the universal system for all AI workloads, offering unprecedented compute density, performance, and flexibility in the world’s first 5 petaFLOPS AI system. NVIDIA DGX A100 features the world’s most advanced accelerator, the NVIDIA A100 Tensor Core GPU, enabling enterprises to consolidate training, inference, and analytics into a unified, easy-to-deploy AI infrastructure that includes direct access to NVIDIA AI experts.

WATCH VIDEO
Download Datasheet
Download Infographic

Essential Building Block of the AI Data Center

The Universal System for Every AI Workload

The Universal System for Every AI Workload

NVIDIA DGX A100 is the universal system for all AI infrastructure, from analytics to training to inference. It sets a new bar for compute density, packing 5 petaFLOPS of AI performance into a 6U form factor, replacing legacy infrastructure silos with one platform for every AI workload.

DGXperts: Integrated Access to AI Expertise

DGXperts: Integrated Access to AI Expertise

NVIDIA DGXperts are a global team of 16,000+ AI-fluent professionals who have built a wealth of experience over the last decade to help you maximize the value of your DGX investment.

Fastest Time To Solution

Fastest Time To Solution

NVIDIA DGX A100 is the world’s first AI system built on the NVIDIA A100 Tensor Core GPU. Integrating eight A100 GPUs with up to 640GB of GPU memory, the system provides unprecedented acceleration and is fully optimized for NVIDIA CUDA-X™ software and the end-to-end NVIDIA data center solution stack.

data-center-dgx-a100-benefits-icon_unmatched-data

Unmatched Data Center Scalability

NVIDIA DGX A100 features Mellanox ConnectX-6 VPI HDR InfiniBand/Ethernet network adapters with 500 gigabytes per second (GB/s) of peak bi-directional bandwidth. This is one of the many features that make DGX A100 the foundational building block for large AI clusters such as NVIDIA DGX SuperPOD™, the enterprise blueprint for scalable AI infrastructure.

A Simpler and Faster Way to Tackle AI

A Simpler and Faster Way to Tackle AI

The NVIDIA AI Starter Kit provides everything your team needs—from a world-class AI platform, to optimized software and tools, to consultative services—to get your AI initiatives up and running quickly. Don't lose time and money building an AI platform. Plug in and power up in a day, get use cases defined in a week, and start productizing models sooner.

Learn More 
Order now 
  • For Developers
  • For IT Managers
  • For Business Leaders
Solve Bigger, More Complex Data Science Problems Faster

Solve Bigger, More Complex Data Science Problems Faster

Benefits

  • Eliminate tedious set up and testing with ready-to-run, optimized AI software.
  • Create better models faster with unmatched performance that enables more iterations.
  • Avoid time lost on systems integration and software engineering.
Deploy Infrastructure and Operationalize AI at Scale

Deploy Infrastructure and Operationalize AI at Scale

Benefits

  • Experience simplified infrastructure design and capacity planning with one system for all AI workloads.
  • Achieve the highest compute density and performance in the smallest footprint.
  • Take advantage of built-in security at every layer.

 

Shorten Time to Insights and Accelerate ROI of AI

Shorten Time to Insights and Accelerate ROI of AI

Benefits

  • Increase data scientist productivity and eliminate non-value-added effort.
  • Accelerate the development cycle, from concept to production.
  • Remove roadblocks with advice from DGXperts.

    •  

Learn more about NVIDIA DGX A100 systems

CONTACT US

Game Changing Performance

Training

DLRM Training

Up to 3X Higher Throughput
for AI Training on Largest Models

DLRM on HugeCTR framework, precision = FP16 | 1x ​DGX A100 640GB batch size = 48 | 2x DGX A100 320GB batch size = 32 | 1x DGX-2 (16x V100 32GB) batch size = 32. Speedups Normalized to Number of GPUs.

Inference

RNN-T Inference: Single Stream

Up to 1.25X Higher Throughput
for AI Inference

MLPerf 0.7 RNN-T measured with (1/7) MIG slices. Framework: TensorRT 7.2, dataset = LibriSpeech, precision = FP16. ​

Data Analytics

Big Data Analytics Benchmark

Up to 83X Higher Throughput than CPU,
2X Higher Throughput than DGX A100 320GB

Big data analytics benchmark |  30 analytical retail queries, ETL, ML, NLP on 10TB dataset | CPU: 19x Intel Xeon Gold 6252 2.10 GHz, Hadoop | 16x DGX-1 (8x V100 32GB each), RAPIDS/Dask | 12x DGX A100 320GB and 6x DGX A100 640GB, RAPIDS/Dask/BlazingSQL​. Speedups Normalized to Number of GPUs

Explore the Powerful Components of DGX A100

1 8x NVIDIA A100 GPUs with up to 640 GB Total GPU Memory
12 NVLinks/GPU, 600 GB/s GPU-to-GPU Bi-directonal Bandwidth

2 6x NVIDIA NVSwitches
4.8 TB/s Bi-directional Bandwidth, 2X More than Previous Generation NVSwitch

3 10X MELLANOX CONNECTX-6 200 Gb/s NETWORK INTERFACE
500 GB/s Peak Bi-directional Bandwidth

4 Dual 64-Core AMD CPUs and 2 TB System Memory
3.2X More Cores to Power the Most Intensive AI Jobs

5 30 TB Gen4 NVME SSD
50 GB/s Peak Bandwidth, 2X Faster than Gen3 NVME SSDs

Data Center

Take a deep dive into the new NVIDIA DGX A100.

Download Whitepaper

The Technology Inside NVIDIA DGX A100

  • A100 GPU
  • Multi-Instance GPU
  • NVLink & NVSwitch
  • Mellanox ConnectX-6
  • Optimized Software Stack
  • Security

NVIDIA A100 Tensor Core GPU

The NVIDIA A100 Tensor Core GPU delivers unprecedented acceleration for AI, data analytics, and high-performance computing (HPC) to tackle the world’s toughest computing challenges. With third-generation NVIDIA Tensor Cores providing a huge performance boost, the A100 GPU can efficiently scale up to the thousands or, with Multi-Instance GPU, be allocated as seven smaller, dedicated instances to accelerate workloads of all sizes.

Learn More 
NVIDIA A100 Tensor Core GPU

Multi-Instance GPU (MIG)

With MIG, the eight A100 GPUs in DGX A100 can be configured into as many as 56 GPU instances, each fully isolated with their own high-bandwidth memory, cache, and compute cores. This allows administrators to right-size GPUs with guaranteed quality of service (QoS) for multiple workloads.

Learn More 
Multi Instance GPU

Next-Generation NVLink and NVSwitch

The third generation of NVIDIA® NVLink™ in DGX A100 doubles the GPU-to-GPU direct bandwidth to 600 gigabytes per second (GB/s), almost 10X higher than PCIe Gen4. DGX A100 also features next-generation NVIDIA NVSwitch™, which is 2X times faster than the previous generation.

Learn More 
Next-Generation NVLink and NVSwitch

Mellanox ConnectX-6 VPI HDR InfiniBand

DGX A100 features the latest Mellanox ConnectX-6 VPI HDR InfiniBand/Ethernet adapters, each running at 200 gigabits per second (Gb/s) to create a high-speed fabric for large-scale AI workloads.

Mellanox ConnectX-6 VPI HDR InfiniBand

Optimized Software Stack

DGX A100 integrates a tested and optimized DGX software stack, including an AI-tuned base operating system, all necessary system software, and GPU-accelerated applications, pre-trained models, and more from NGC™.

Learn More 
DGX Software Stack

Built-In Security

DGX A100 delivers the most robust security posture for AI deployments, with a multi-layered approach stretching across the baseboard management controller (BMC), CPU board, GPU board, self-encrypted drives, and secure boot.

Built-In Security

Learn about enterprise-grade support for NVIDIA DGX systems.

Learn More

NVIDIA DGX SuperPOD

Leadership-Class AI Infrastructure

Learn More

Purchase NVIDIA DGX Today

Get Started

Learn About NVIDIA DGX Systems

CONTACT US

Contact Us To Learn More

  1. Section
Send me the latest enterprise news, announcements, and more from NVIDIA. I can unsubscribe at any time.

Privacy Policy

Products
Technologies
Software
Resources