Fit for AI applications

The digital transformation demands ever shorter innovation cycles from science and research, as well as from technology providers, and also new top performances in hardware and software, since AI applications can only be realized on the basis of data- and computation-intensive processes.

Graphics Processing Units (GPUs) offer the required computing power

Powerful hardware and software components are essential for AI solutions to fulfill their role as system-critical applications in any industry. The systems have to analyze terabytes of data in a short period of time. The computing power required for parallel processing is provided by multicore CPUs based on neural chips. Above all, however, it comes from the graphics processing units (GPUs). GPUs are the processors that today provide the necessary power for deep learning, machine learning and inferencing. Since July 2019, Kontron has been NVIDIA Preferred Partner and uses their GPUs for its AI platforms and applications. Kontron benefits from the know-how and engineering expertise of NVIDIA's specialists, and can therefore create innovative solutions for AI-based applications. NVIDIA GPUs are part of the currently most powerful Kontron rackmount server KISS V3 4U SKX-AI. The scalable server is equipped with two powerful processors of the Intel^® Xeon^® SP series, which can be expanded by twelve DIMM DDR4-2666 modules and up to 768 GB RAM with ECC support.
Up to three double-width high-end GPU cards (e.g. NVIDIA^® TESLA^® V100, NVIDIA^® T4-GPU) ensure extremely high GPU performance, which is essential for AI applications. GPUs perform exactly the matrix mathematics required for rendering graphics.
Kontron's scalable systems are able to cover most levels in the field of inferencing, from Intel^® Single XEON^® CPU solutions to Intel^® Dual XEON^® solutions.