Support servers capable of efficiently processing demanding workloads are expected to be provided using the latest acceleration technologies from Intel and Intel Habana.

Super Micro Computer (hereinafter referred to as Supermicro) announced on the 17th that it will support two new Intel-based accelerators, the 'Arctic Sound-M' and 'Gaudi2'. This will allow customers to efficiently process demanding workloads such as cloud gaming, media transfer, artificial intelligence (AI), and machine learning (ML) using the latest acceleration technologies from Intel and Intel Habana.

Supermicro systems featuring Arctic Sound-M GPUs are said to address demanding requirements such as cloud gaming, media transcoding and streaming, virtual desktop infrastructure (VDI), simulation and visualization, machine learning, and content creation. Featuring a hardware AV-1 encoder and an open-source media software stack, Intel Arctic Sound-M significantly improves performance over software-only video transcoding and transmission solutions and provides acceleration for VDI environments.

Intel Arctic Sound-M GPUs are currently available in a 2U 2-node single-processor Intel system with three GPUs per node, a 4U 10-GPU system, and a CloudDC server, the company explained. Additional systems are expected to be announced later this year. The new Supermicro AI training server features dual Intel 3rd Generation Intel Xeon Scalable processors and eight Habana Gaudi 2 accelerators for high-performance AI training environments.

“We are working closely with Intel and Habana Labs to provide a range of server solutions supporting Arctic Sound-M and Gaudi2 that address our customers’ demanding requirements for efficient media transport and AI training,” said Charles Liang, CEO of Supermicro.

“We continue to work with leading technology vendors to deliver application-optimized total system solutions to support complex workloads,” he added.

Supermicro brings cutting-edge technologies to market by designing new systems using a building block solutions approach. This approach allows for easy integration of new GPU and acceleration technologies into existing designs, and in some cases, allows for rapid adaptation of existing designs when higher-performance components are needed, he noted.

“Supermicro is helping to deliver advanced AI and media processing with systems leveraging Intel’s latest Arctic Sound-M and Gaudi2 accelerators,” said Sandra Rivera, senior vice president at Intel. “Supermicro’s recent Gaudi AI training server will accelerate deep learning training for some of the fastest-growing workloads in data centers.”