Special GPU servers that accelerate Machine Learning, Deep Learning and Artificial Intelligence
Artificial Intelligence (AI) is no longer a purely academic topic, but is already being used in many practical ways, for example in face recognition, robotics, analytics, health care or smart city applications.
Scientific progress requires accelerating machine learning (ML) and deep learning (DL).
With the SHARK A.I. series, BRESSNER now has high performance GPU servers in their portfolio that have been specifically developed for such requirements.
Flexible framework for various AI applications
"High-performance computer systems for accelerating GPUs are a critical factor for specific solutions that need to optimize high performance computing (HPC) applications and remote virtualization," said Josef Bressner, CEO of Bressner Technology GmbH.
The GPU server SHARK A.I. is freely configurable as an edge platform and can significantly increase flexibility and agility in the cloud. The server supports multiple topologies and bandwidths. It offers the possibility to implement different head nodes and to freely choose the number of GPUs per virtual machine (VM).
The SHARK A.I. supports both single and dual root complexes for various AI applications. For deep learning applications, a single-root complex can use all GPU clusters to focus on large learning processes and the CPU for smaller tasks. For machine-learning, a dual-root complex can assign more tasks to the CPUs and arrange less distributed learning between GPUs.
As the various applications in Edge High Performance Computing require individual platform solutions, BRESSNER supports users with customer-specific developments and adjusts the CPU, RAM and GPU to their respective needs. Before delivery, the devices are subjected to a 24-hour burn-in stress test in the laboratory.
All possible systems support both NVIDIA and AMD graphics cards, depending on the model up to 10 slots are possible.
Features of the SHARK A.I. series
- Up to 10x PCIe x16 Gen3 GPU slots
- Single or dual socket XEON® scalable processor
- Up to 384 GB or 3 TB DDR4 RAM
- 2 x OnBoard 10 GBase-T LAN ports
- 1U to 4U rack mount
- Hot-swappable drive bays
- Redundant fan modules and redundant power supplies
First contact for the product area GPU Server is Benjamin Nigl, Account Manager at BRESSNER Technology.