AMAX.AI Launches [SMART]Rack AI Machine Learning Cluster

FREMONT, Calif., Sept. 27, 2017 — AMAX.AI, a division of AMAX Information Technologies, Inc., specializing in high-performance platforms for AI and Deep Learning development, will be launching the [SMART]Rack AI Machine Learning cluster at the AI Summit 2017 (Booth #G27), to be held in the Regency Center, San Francisco, California on Sept. 27th and 28th.

The [SMART]Rack AI solution is an extension of AMAX.AI’s MATRIX GPU Cloud product line which includes powerful dev workstations, high-compute density servers and now a turnkey Machine Learning cluster in [SMART]Rack AI. The all-inclusive rackscale platform is maximized for performance featuring up to 96x NVIDIA Tesla P40, P100 or V100 GPU cards, providing well over 1 PetaFLOP of compute power per rack. The solution is fully-loaded with features designed to accelerate compute as well as data-transfer performance while offering the ultimate in manageability. Solution components include: an All-Flash storage appliance for an ultra-fast in-rack data repository; 25G high-speed network; [SMART]DC HPC-optimized DCIM to remotely monitor, manage and orchestrate GPU-based Machine Learning hardware where real-time temperature, power and system health monitoring are critical for uninterrupted operation; and an in-rack battery for graceful shutdowns in the event of a power loss scenario. The [SMART]Rack AI can serve as a powerful standalone platform or as a scalable Machine-Learning-at-scale building block, and is the perfect platform in which to build on-premise AI Cloud and Deep-Learning-as-a-Service infrastructure.

“The [SMART]Rack AI is revolutionary to Deep Learning data centers,” said Dr. Rene Meyer, VP of Technology, AMAX. “Because it not only provides the most powerful application-based computing power, but it expedites DL model training cycles by improving efficiency and manageability through integrated management, network, battery and cooling all in one enclosure.”

The MATRIX product line also features powerful DL dev workstations ideal for start-ups, incubators and individual researchers to set up Deep Learning labs, and highly-compute dense yet ultra-compact Machine Learning servers that can easily be scaled within a rack to increase compute power on demand.

All MATRIX solutions come pre-loaded with an end-to-end Deep Learning software, powered by Bitfusion Flex, geared towards accelerating GPU development while dynamically managing GPU resource and workflow management. The software features preloaded environments containing the latest frameworks to quickly begin building models for training within minutes, and GPU over Fabrics technology to enable the sharing & scaling of large numbers of local and remote GPUs across any MATRIX systems for multi-tenancy and highly-customizable self-service features.

AMAX will be holding live demos of the MATRIX GPU Cloud solutions during exhibition hours at the AI Summit 2017. To learn more about fast-tracking AI with DL-in-a-Box Solutions, please visit Booth #G27 or schedule a demo here.

About AMAX

AMAX AI is a division of AMAX Information Technologies, Inc., specializing in award-winning high-performance platforms for AI and Deep Learning development. As a thought leader and early innovator in the burgeoning market for Deep Learning technology, AMAX AI works with cutting-edge startups, research universities and global corporations to give its customers access to early innovations and game-changing DL technology. From high-compute density GPU servers and supercharged dev workstations, to DGX supercomputers and turnkey rackscale platforms used to power on-premise AI Clouds or DL-as-a-Service, AMAX AI enables companies to build out the Deep Learning infrastructures they need to handle the rigors of development, training, and inference at any scale. To learn more, please visit www.amax.ai.

Source: AMAX