Lenovo unveils first all-AMD AI 'supercomputer' flanked with up to 1.5TB of HBM memory and promises drop-in support for the future AMD EPYC CPU — new ThinkSystem has dual EPYC CPUs and 8 Instinct MI300X GPUs

ThinkSystem SR685a V3 8GPU server
(Image credit: Lenovo)

Lenovo has taken the wraps off its ThinkSystem SR685a V3 server, which it says is an optimal solution for both enterprise private on-prem AI as well as for public AI cloud service providers.

Crafted in tandem with AMD, the server has been specifically engineered to handle the demanding compute needs associated with GenAI and Large Language Models. With fast acceleration, large memory capacity and I/O bandwidth, the new powerhouse can manage sizable data sets used in industries from healthcare and energy to financial services and climate science.

The AI supercomputer is powered by two top-tier 4th Generation AMD EPYC processors, each delivering up to 400W of output, coupled with eight AMD Instinct MI300X GPUs. Fully interconnected with AMD Infinity Fabric, it provides 1.5TB of high-bandwidth (HBM3) memory capacity and up to 1TB/s peak aggregate theoretical GPU I/O bandwidth performance.

Up to 16 NVMe SSDs

ThinkSystem SR685a V3 supports up to 3TB RAM, made up of 24 DDR5 DIMMs, and as an alternative to the eight AMD Instinct MI300X GPUs with Infinity Fabric interconnects at 896GB/s, it can handle eight Nvidia H100/H200/B100 GPUs with NVLink interconnects at 900GB/s.

The 8U2S rack server allows for up to 10x PCIe Gen5 x16 FHHL adapters (eight at the front connected to the PCIe switch for GPU connectivity, and two at the rear linked directly to the main CPU). It supports up to sixteen 2.5-inch hot-swappable NVMe SSDs, as well as up to two M.2 drives for boot, with RAID support. In terms of power, eight hot-swappable PSUs allow for full N+N redundancy, while things are kept at an acceptable temperature via air cooling with an N+1 hot-swappable fan.

Management is handled by an XClarity Controller2 (XCC2), that offers high-level service-processor control as well as monitoring and alerting functions.

The ThinkSystem SR685a V3 is compatible with a variety of operating systems including RHEL, Ubuntu, Alma Linux, Rocky Linux, and ESXi.

“Together with Lenovo, we are accelerating AI transformation for the enterprise in multiple manners – helping guide customers through this monumental shift in computing, while providing robust end-to-end solutions at scale,” said Forrest Norrod, executive vice president and general manager, Data Center Solutions Group, AMD. “We have a proven track record of bringing amazing solutions, jointly, to the market and are excited to add AMD Instinct MI300X to Lenovo’s portfolio, helping enterprises to rapidly adopt AI.”

With applications spanning multiple sectors, this new system can accelerate most compute demanding AI workloads, and Lenovo singles out its benefits to the world of financial services in particular, where it can help detect and prevent fraud, and streamline KYC (know your customer) initiatives.

The Lenovo ThinkSystem SR685a V3 server can be ordered now, with pricing available on request.

More from TechRadar Pro

Wayne Williams
Editor

Wayne Williams is a freelancer writing news for TechRadar Pro. He has been writing about computers, technology, and the web for 30 years. In that time he wrote for most of the UK’s PC magazines, and launched, edited and published a number of them too.

TOPICS