The Universal System for AI Infrastructure
The next generation of DGX AI systems is here. NVIDIA DGX A100 is the new standard for AI infrastructure and features dramatic upgrades to performance for any workload. Advance to the bleeding edge of AI with up to 5 petaFLOPS of AI throughput.
The latest NVIDIA Ampere GPU architecture delivers advancement in computational throughput, GPU:GPU bandwidth, and GPU multi-tenancy. This DGX system includes 8 NVIDIA A100 Tensor Core GPUs interconnected with NVIDIA NVLink® and NVSwitch™ technology.
- NVIDIA A100 “Ampere” GPU architecture: built for dramatic gains in AI training, AI inference, and HPC performance
- Up to 5 PFLOPS of AI Performance per DGX A100 system
- Increased NVLink Bandwidth (600GB/s per NVIDIA A100 GPU): Each GPU now supports 12 NVIDIA NVLink bricks for up to 600GB/sec of total bandwidth
- Up to 10X the training and 56X the inference performance per system
- Multi Instance GPU: partition your NVIDIA A100 GPUs into slices for individual users or ideally sized segments for particular applications. Use Multi Instance GPU to share your DGX A100 deployment across a much larger pool of users, all with increased security (full isolation).
- Arrives with Microway Deployment services: Microway experts will integrate the DGX software stack on your DGX A100 system
- 8 NVIDIA A100 GPUs, each with 40GB (EOL) or 80GB of HBM2/HBM2e GPU memory
- Up to 5 PFLOPS of AI performance
- Total of 640GB or 320GB (EOL) of high-bandwidth GPU memory, interconnected with NVSwitch technology
- Two AMD EPYC 7002 Series 64-core CPUs
- 1TB DDR4 System Memory
- Eight NVIDIA ConnectX®-6 200Gbps HDR InfiniBand Adapters
- Additional 200Gb HDR InfiniBand Adapter for connection to storage
- 15TB of NVMe storage
- 6U Rackmount Form Factor
- Redundant, Hot-Swap power supplies
- Power Consumption: 6.5kW at full load
- Ubuntu Server Linux operating system
DGX A100 Services
DGX A100 deliveries are bundled with Microway services including:
DGX Site Planning
A Microway Solutions Architect will provide remote consultation to you in planning for the DGX A100’s unique power and cooling requirements. This includes rack diagramming with airflow and power cabling notation as well as answering queries from facilities staff about support requirements of the new DGX A100 hardware.
All DGX OS and container software will be installed, firmware upgraded to the latest versions, desired DGX-containers installed, and deep learning test jobs run. Customers may supply questions to our experts. In some cases, factory-trained Microway experts may travel to your datacenter.
Microway also offers optional DGX services including: container and/or job execution script creation, and partner-provided Deep Learning data preparation consultancy.
Container or Job Execution Script Creation
Creating an effective workflow is key to your success with any hardware resource. The unique container architecture of DGX systems mean proper container management and even job execution scripts are a necessity. Microway experts will assist you in creating: your default containers, scripts to orchestrate these containers for multiple users in your organization, and methods of dynamically allocating GPUs as required to containers. Experts will also help you plan profiles for the new Multi Instance GPU features.
Deep Learning Data Preparation
An overwhelming majority of the time in a deep learning project is spent on the preparation of data. At your option, Microway’s data-science consultant partners will engage with you to: to create a custom scope of work, determine the best means to prepare your data for deep learning, create the pre-processing algorithms, assist in the pre-process of the training data, and optionally determine effective means of measurement for the overall DL project. Additional services also available.
- Separate direct-attached high-speed flash data plane for smaller data sets
- DDN Parallel storage solutions for large datasets (up to multi-petabyte), scale-out user-bases, or ultra-high bandwidth requirements
NVIDIA DGX A100 Part Numbers
DGXA-2530A+P2CMI00 – NVIDIA DGX A100 System for Commercial or Government institutions (40GB GPUs)
DGXA-2530A+P2EDI00 – NVIDIA DGX A100 System for EDU (Educational institutions) (40GB GPUs)
DGXA-2530F+P2CMI00 – NVIDIA DGX A100 System for Commercial or Government institutions (80GB GPUs)
DGXA-2530F+P2EDI00 – NVIDIA DGX A100 System for EDU (Educational institutions) (80GB GPUs)
718-A10000+P2CMI36 – NVIDIA DGX A100 3 Year Warranty and Support Services (Commercial/Government, 40GB GPUs)
718-A10080+P2CMI36 – NVIDIA DGX A100 3 Year Warranty and Support Services (Commercial/Government, 80GB GPUs)
718-A10000+P2EDI36 – NVIDIA DGX A100 3 Year Warranty and Support Services (EDU, 40GB GPUs)
718-A10000+P2EDI36 – NVIDIA DGX A100 3 Year Warranty and Support Services (EDU, 80GB GPUs)
Continuing to renew your Support services ensures you receive the latest DGX software updates (including frameworks) and retain the DGX A100 system’s outstanding SLA commitments.
NVIDIA DGX support provides you with comprehensive system support and access to NVIDIA’s cloud management portal. The portal facilitates deep learning experimentation via: containerized application management, job execution, status monitoring, software updates, and validated containers in the NVIDIA GPU Cloud.
|NVIDIA DGX A100 Support|
|NVIDIA Cloud Management||✔|
|NVIDIA DGX A100 Software Upgrades||✔|
|NVIDIA DGX A100 Driver Updates||✔|
|NVIDIA DGX A100 Firmware Updates||✔|
|Hardware Support||3 or 5 year subscription|
|Hardware SLA (replacement parts shipped)||1 business day|
|Online Access||NVIDIA Enterprise Support Portal|
What’s Included in NVIDIA DGX A100 Support
- Access to the latest software updates and upgrades
- Direct communication with NVIDIA technical experts (DGXperts)
- NVIDIA cloud management: container repository, container management, job scheduling, and system performance monitoring and new software updates
- NVIDIA knowledge base with how-to articles, application notes and product documentation
- Rapid response and timely issue resolution through support portal and 24×7 phone access
- Lifecycle support for NVIDIA DGX A100 Deep Learning software
- Hardware support, firmware upgrades, diagnostics and remote and onsite resolution of hardware issues
- Next day shipment for replacement parts
Contact us for pricing
Final pricing depends upon configuration and any applicable discounts, including education or NVIDIA Inception. Request a custom quotation to receive your applicable discounts.
NVIDIA requires all DGX purchases to include a support services contract. Ensure all quotes you receive include this mandatory DGX support.