Massive performance boost for deep learning
Our GPU expansions and hardware systems can add hundreds or even thousands of cores to a server in a 4U device. The GPU expansions or compute accelerators are well suited to collaborate with IBM Power8 S822L or S824L servers, using NVIDIA® Tesla GPUs among others. The GPU appliances were specifically developed for HPC applications such as deep learning, data centers or oil and gas exploration.
Features
“AI on the Fly” – Training and inferencing on a local platform
Rapid technological advances, groundbreaking innovations and an actual need from an economic perspective ensure that artificial intelligence is no longer restricted to research laboratories and supercomputers. Artificial intelligence is the technological driver for the future and is now at the forefront of the further development of companies and entire industries.
AI-based content generation is already available, including for e-commerce platforms and multidimensional pattern recognition based on camera and sensor data. Although edge and cloud computing have been proven advantageous for such appliances and scalable concepts have already been implemented, there are fields of applications that rely on even lower latency.
Support for brandnew GPU cards
Depending on the server rack unit, you can choose between various GPUs: NVIDIA® GeForce RTX 3090, NVIDIA® Tesla, Intel Xeon Phi, AMD FirePro, GeForce GTX 1080, NVIDIA® Quadro M6000 or Nallatech FPGAs. In addition to the standard server chassis versions, we also offer desktop versions for applications outside of server control cabins. Selected GPU expansions even offer several PCIe x16 Gen4 or Gen3 host connections for best connectivity while also supporting peer-to-peer transfer.
SUBSCRIBE TO NEWSLETTER
As a newsletter customer, you get access to exclusive content such as:
- Information about new products and company news
- Special discount promotions
- Trade fair and event participations
- Current webinars on trend topics