DDN Supports Nvidia DGX A100 Systems in A3I Solutions
Combination of A3I AI storage solutions and DGX A100 AI and deep learning infrastructure to optimize performance of analytics, training and inference workloads
This is a Press Release edited by StorageNewsletter.com on May 22, 2020 at 2:24 pmDDN (DataDirect Networks, Inc.) announced support for Nvidia Corp.‘s DGX A100 systems in its A3I solutions.
DGX A100 is a 5-petaflops AI system that consolidates the power and capabilities of an entire data center into a single flexible platform. A3I combines the company’s storage, DGX A100 systems and Nvidia Mellanox high-speed networking to supply optimized compute and I/O based on common principles of parallelism, performance and scale.
A variety of organizations with different use cases, sizes and technical skill levels are looking to data-intensive applications and data science to differentiate, innovate and speed time-to-market for their products. By creating solutions that are powerful, scalable and easy to deploy, the company makes performance AI and analytics accessible to anyone with these requirements. Llife sciences, autonomous vehicle, pharmaceutical and manufacturing organizations have already taken advantage of the firm’s A3I solutions. This next gen will make innovation that much faster and easier.
The A3I solutions, specifically the AI400X, are deployed in Nvidia’s data center to provide performance and scalable shared file access for its own DGX A100-based SuperPOD.
“We’re seeing powerful results in testing NVIDIA’s DGX A100,” said James Coomer, VP, products, DDN. “Together, we strive to make high-performance AI and analytics engines more accessible to more innovators.“
The A3I with DGX systems are for companies that need flexible resources to address multiple workflows, projects or departments. With support for secure multi-tenancy, the company’s storage systems can supply performance access to shared infrastructure for projects under organizational or regulatory requirements for complete data separation. This makes A3I for hyperscale, multidisciplinary or pharmaceutical resea, use cases.
“The NVIDIA DGX A100 delivers the flexibility to power AI training, inference and data science workloads,” said Tony Paikeday, director product marketing, AI and deep learning, Nvidia. “With DDN and NVIDIA technology, customers have simple access to world-class supercomputing infrastructure that delivers leading performance and scalability to accelerate the world’s biggest AI workloads.“
To help customers scope and design their own A3I powered data center, the company and Nvidia plan to release reference architectures based on A3I and DGX A100 DDN A3I is available for purchase from its network of certified partners around the world.
Read also:
DDN Works With Nvidia to Ease Deployment and Set Boundaries in Performance for Data-Intensive AI and HPC
Combine power of DGX SuperPOD systems with A3I data management system so customers can deploy HPC infrastructure with minimal complexity and reduced timelines.
November 29, 2019 | Press Release