NVIDIA DGX Station A100

The NVIDIA DGX Station A100 is the next generation of the most powerful workstation for machine learning and artificial intelligence. The only professional solution in the world with 320GB of GPU memory, for which you do not need a server room or a complex IT infrastructure. NVIDIA DGX Station A100 is a system specially designed for demanding calculations and which you can easily run in your office.

27 648

CUDA cores

1 728

Tensor cores

CPU cores

512 GB

DDR4 RAM

up to 320 GB

GPU memory

1,92 TB

NVMe for OS

7,68 TB

NVMe for data

multiple instances

Hardware

Parameter	NVIDIA DGX Station A100 160 GB	NVIDIA DGX Station A100 320 GB
GPU	4× NVIDIA A100 SXM4 40 GB	4× NVIDIA A100 SXM4 80 GB
Performance (tensor operations)	2,5 PetaFLOPS	2,5 PetaFLOPS
GPU memory	160 GB total	320 GB total
CPU	1× AMD Epyc 7742, 64 cores 3.6GHz	1× AMD Epyc 7742, 64 cores 3.6GHz
# CUDA cores	27 648	27 648
# Tensor cores	1 728	1 728
Multi-instantce GPU	28 instances	28 instances
RAM	512 GB DDR4	512 GB DDR4
HDD	OS: 1× 1,92 TB NVMe data: 1x 7,68 TB U.2 NVMe	OS: 1× 1,92 TB NVMe data: 1x 7,68 TB U.2 NVMe
Network	2x 10 Gb/s Ethernet 1x 1 Gb/s Ethernet (BMC management)	2x 10 Gb/s Ethernet 1x 1 Gb/s Ethernet (BMC management)
Graphics outputs	4x Mini DisplayPort 4GB GPU memory	4x Mini DisplayPort 4GB GPU memory
Max. power consumption	1,5 kW	1,5 kW
Form factor	Tower, water cooling	Tower, water cooling
	Datasheet	Datasheet

Software

But what is much more interesting is the aforementioned software features of the offered NVIDIA machines. They all offer pre-installed and especially performance-tuned machine learning environments (e.g. Caffe, or Cafe 2, Theano, TensorFlow, Torch, or MXNet) or intuitive data analytics environments (NVIDIA Digits). All neatly packaged in Docker containers, freely downloadable on the NVIDIA GPU Cloud (NGC). Such a tuned environment provides 30% more power for machine learning applications against applications deployed purely on NVIDIA hardware. The main advantage of the pre-installed environment is the deployment speed, which is in units of hours.

NVIDIA GPU Cloud (NGC)

NVIDIA GPU Cloud (NGC) represents the repository of the most used frameworks for machine learning and deep learning applications, HPC applications, or NVIDIA GPU cards accelerated visualization. Deploying these applications is a question minutes — copying a link of the appropriate Docker image from the NGC repository, moving it on the DGX system, and downloading and running the Docker container. The individual development environments – versions of all included libraries and frameworks, settings of environment parameters – are updated and optimized by NVIDIA for deployment on DGX systems. https://ngc.nvidia.com/

NVIDIA offers special programs for DGX systems and Tesla accelerators for EDU organizations or start-up companies. Thanks to the international collaboration between NVIDIA and IBM Global Financing, preferential financing in the form of operating leases is available for DGX models.

Get a quote

Support

The strength of the NVIDIA solution is to support the entire system. Hardware support (in case of failure of any of the components) is a matter of course. Software support for the entire environment is critical if something does not work as intended. The customer has hundreds of developers ready to help. Support is part of NVIDIA DGX purchase. It is available for 3 or 5 years and can be extended after this period.

NVIDIA support covers:

Dispatch a customer engineer onsite for field replacement unit (FRU) replacement
Run onboard diagnostic tools (from remote) to troubleshoot system issues
Remote software support
Access to the latest software updates and upgrades
Direct communication with NVIDIA support experts
A private NGC container repository for accessing NVIDIA-optimized AI software with powerful sharing and collaboration features for your organization
A searchable knowledge base with how-to articles, application notes, and product documentation
Rapid response and timely issue resolution through a support portal and 24×7 phone access
Lifecycle support for NVIDIA DGX systems’ AI software
Replacement of defective HW components by the next working day
DGX Systems Appliance Support Services Terms and Conditions
End-user license agreement (EULA)

Through a combination of tuned hardware, software and NVIDIA support, NVIDIA DGX delivers significantly higher performance and acceleration in the learning phase of machine learning applications:

Applications performance comparison

GPU vs. CPU: Data analysis

A100 vs. V100: Model training

Díky kombinaci vyladěného hardwaru, softwaru a podpory NVIDIA přináší systémy DGX výrazně vyšší výkon a zrychlení ve fázi učení aplikací strojového učení:

M Computers represents NVIDIA on the Czech market in the Enterprise area of computing accelerators and AI systems.

Last year, it was the first company in Central and Eastern Europe to receive the highest ELITE PARTNER status, as well as two NVIDIA AI Innovator and NVIDIA AI Champion awards.

NVIDIA Deep Learning Institute

The NVIDIA Deep Learning Institute (DLI) offers both online and hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning and accelerated computing.

More information

Testing

To test the performance and especially the speed of deployment of ML and AI applications, we have the NVIDIA DGX Station available via NVIDIA Tesla Test Drive program as well as 2× NVIDIA Tesla V100 and NVIDIA Tesla T4. If you are interested in our testing offer, please fill out this form.

Kamila Jeřábková

Product manager

M: +420 734 161 516
<a href="mailto:kamila.jerabkova@mcomputers.cz">kamila.jerabkova@mcomputers.cz</a>

NVIDIA DGX Station A100

Hardware

Software

NVIDIA GPU Cloud (NGC)

NVIDIA offers special programs for DGX systems and Tesla accelerators for EDU organizations or start-up companies. Thanks to the international collaboration between NVIDIA and IBM Global Financing, preferential financing in the form of operating leases is available for DGX models.

Support

NVIDIA support covers:

Applications performance comparison

GPU vs. CPU: Data analysis

A100 vs. V100: Model training

M Computers represents NVIDIA on the Czech market in the Enterprise area of computing accelerators and AI systems.

NVIDIA Deep Learning Institute

Testing

Kamila Jeřábková

References

NVIDIA GTC 2024 Watch

Barbecue event with a portion of news from HPC and AI – presentation for download

Ansys User Conference 2023

Masaryk University operates the most advanced AI computing system

AI DAYS 2022

Hopper architecture and other news from NVIDIA GTC22

Researchers from the University of Ostrava train AI on the NVIDIA system

NVIDIA DGX Station A100 unboxing

We’ve joined Brno.AI

Experience NVIDIA GTC 2021

Fall GTC 2020 Announcements

Invitation: NVIDIA’s GPU Technology Conference

Our solution is part of the international RICAIP project

NVIDIA Ampere announcement

NVIDIA AI & HPC Academy 2020

About us

NVIDIA products

Intel and AMD products

Contact