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.

NVIDIA DGX A100

The universal system for AI infrastructure.

The World’s First AI System Built on NVIDIA A100

Part of the NVIDIA DGX™ platform, 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. Featuring the NVIDIA A100 Tensor Core GPU, DGX A100 enables 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

NVIDIA DGX A100 is the universal system for AI infrastructure, packing 5 petaFLOPS of AI performance into a 6U form factor, replacing legacy infrastructure silos with one platform for every AI workload.

Integrated Access to AI Expertise

Included with every DGX is access to NVIDIA DGXperts, a global team of 20,000+ 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

Integrating eight A100 GPUs with 320GB or 640GB of GPU memory, the system provides unprecedented acceleration, is built on NVIDIA Base Command™ software, and includes NVIDIA AI Enterprise for a fully optimized experience.

Unmatched Scalability

NVIDIA DGX A100 features NVIDIA® ConnectX®-7 InfiniBand/Ethernet network adapters with 500 gigabytes per second (GB/s) of peak bidirectional bandwidth. DGX A100 is a foundational building block for NVIDIA DGX SuperPOD™, the enterprise blueprint for scalable AI infrastructure.

The DGX Experience—in the Cloud

The fastest way to get started using the DGX platform is NVIDIA DGX Cloud, a multi-node AI-training-as-a-service solution with integrated DGX infrastructure that’s optimized for the unique demands of enterprise AI.

Learn More

What Customers Are Saying About DGX A100

Our DrAid AI assistant is now deployed in over 100 hospitals and used daily by more than 600 radiologists. With over 100X faster training on DGX A100 compared to the CPU only, we’ve significantly shortened the turnaround time for model development.

- Steven Truong, CEO, VinBrain

Using DGX systems to train models for AI-based automated optical inspection (AOI) enables Wistron to improve inspection accuracy by 50 percent and reduce false inspection calls by 30 percent, shortening the time to target yield and increasing factory capacity.

- William Lin, President of the Enterprise Business and Network Group, Wistron Corp

Accelerate Outcomes Across the Enterprise With AI

For Data Scientists
For IT Decision-Makers
For Business Leaders

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

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

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.

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

8x NVIDIA A100 GPUs with up to 640GB total GPU memory
12 NVIDIA NVLinks® per GPU, 600GB/s of GPU-to-GPU bidirectional bandwidth
6x NVIDIA NVSwitches™
4.8TB/s of bidirectional bandwidth, 2X more than previous-generation NVSwitch
10x NVIDIA ConnectX-7 200Gb/s network interface
500GB/s of peak bidirectional bandwidth
Dual 64-CORE AMD CPUs and 2TB system memory
3.2X more cores to power the most intensive AI jobs
30TB Gen4 NVMe SSD
50GB/s of peak bandwidth, 2X faster than Gen3 NVMe SSDs

Take a deeper dive into NVIDIA DGX A100.

Download Whitepaper

The Technology Inside NVIDIA DGX A100

A100 GPU
Multi-Instance GPU
NVLink & NVSwitch
ConnectX-7
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

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

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

NVIDIA ConnectX-7 200Gb/s InfiniBand/Ethernet

DGX A100 features the NVIDIA ConnectX-7 InfiniBand and VPI (Infiniband or Ethernet) adapters, each running at 200 gigabits per second (Gb/s) to create a high-speed fabric for large-scale AI workloads. DGX A100 systems are also available with ConnectX-6 adapters.

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

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.

Hear more about NVIDIA DGX A100 from our DGXperts at GTC

Watch on Demand

Learn about enterprise-grade support for NVIDIA DGX systems.

Learn More

NVIDIA Enterprise Support Services for the DGX Platform

Maximize the Value of the DGX Platform

NVIDIA Enterprise Services provide support, education, and professional services for your DGX infrastructure. With NVIDIA experts available at every step of your AI journey, Enterprise Services can help you get your projects up and running quickly and successfully.

Learn More About Enterprise Services

NVIDIA DGX SuperPOD

Leadership-Class AI Infrastructure

Learn More

Get the NVIDIA DGX Platform

Get DGX

Learn About the NVIDIA DGX Platform

Learn More

NVIDIA DGX A100

The World’s First AI System Built on NVIDIA A100

Essential Building Block of the AI Data Center

The Universal System for Every AI Workload

Integrated Access to AI Expertise

Fastest Time To Solution

Unmatched Scalability

The DGX Experience—in the Cloud

What Customers Are Saying About DGX A100

Accelerate Outcomes Across the Enterprise With AI

Solve Bigger, More Complex Data Science Problems Faster

Benefits

Deploy Infrastructure and Operationalize AI at Scale

Benefits

Shorten Time to Insights and Accelerate ROI of AI

Benefits

Game-Changing Performance

Training

Inference

Data Analytics

Explore the Powerful Components of DGX A100

The Technology Inside NVIDIA DGX A100

NVIDIA A100 Tensor Core GPU

Multi-Instance GPU (MIG)

Next-Generation NVLink and NVSwitch

NVIDIA ConnectX-7 200Gb/s InfiniBand/Ethernet

Optimized Software Stack

Built-In Security

Hear more about NVIDIA DGX A100 from our DGXperts at GTC

Maximize the Value of the DGX Platform

NVIDIA DGX SuperPOD

Get the NVIDIA DGX Platform

Learn About the NVIDIA DGX Platform

Contact Us To Learn More About DGX