(Information sent by the signatory company)

- Supermicro Expands Rack-Scale GPU and AI Solutions with Support for AMD Instinct MI300 Series Accelerators

New 8-GPU systems powered by AMD Instinct™ MI300X accelerators with breakthrough AI and HPC performance for large-scale AI training and LLM deployments now available

SAN JOSE, California, Dec. 7, 2023 /PRNewswire/ -- Supermicro, Inc. (NASDAQ: SMCI), a maker of total IT solutions for AI, cloud, storage and 5G/Edge, announces three new additions to its H13 generation of AMD-based GPU servers, optimized for cutting-edge performance and efficiency, powered by the new AMD Instinct MI300 Series accelerators. Supermicro's powerful rack-scale solutions with 8-GPU servers with AMD Instinct MI300X OAM configuration are ideal for large model training.

New 2U liquid-cooled and 4U air-cooled servers with AMD Instinct MI300A Accelerated Processing Units (APUs) are available, improving data center efficiency and powering the complex, fast-growing demands in AI, LLM and HPC. The new systems contain quad APUs for scalable applications. Supermicro can supply complete liquid-cooled racks for large-scale environments with up to 1,728 TFlops of FP64 performance per rack. Supermicro's manufacturing facilities around the world expedite the delivery of these new servers for the convergence of AI and HPC.

"We are excited to expand our rack-scale Total IT Solutions for AI training with the latest generation of AMD Instinct accelerators, delivering up to 3.4x performance improvement compared to previous generations," said Charles Liang. , president and CEO of Supermicro. "With our ability to supply 4,000 liquid-cooled racks per month from our manufacturing facilities around the world, we can offer the latest H13 GPU solutions with the AMD Instinct MI300X accelerator or the AMD Instinct MI300A APU. Our proven architecture Enables a dedicated 1:1 400G network for each GPU designed for large-scale AI and supercomputing clusters capable of fully integrated liquid cooling solutions, giving customers a competitive advantage for performance and superior efficiency with ease of implementation".

Learn more about Supermicro servers with AMD Accelerators

The LLM-optimized AS –8125GS-TNMR2 system is based on Supermicro's block architecture, a proven design for high-performance AI systems with air- and liquid-cooled rack-scale designs. The balanced system design partners a GPU with a 1:1 network to provide a large pool of high-bandwidth memory across nodes and racks to accommodate today's largest language models with up to trillions of parameters, maximizing parallel computing and minimizing training time and inference latency. The 8U system with the MI300X OAM accelerator delivers the raw acceleration power of 8-GPU with AMD Infinity Fabric™ links, enabling up to 896GB/s of maximum theoretical P2P I/O bandwidth on the open standard platform with industry-leading 1.5TB HBM3 GPU memory in a single system, as well as native sparse array support, designed to save power, reduce compute cycles, and reduce memory usage for AI workloads. Each server features dual-socket AMD EPYC™ 9004 series processors with up to 256 cores. At rack scale, more than 1,000 CPU cores, 24TB of DDR5 memory, 6,144TB of HBM3 memory, and 9,728 Compute Units are available for the most demanding AI environments. The use of the OCP Accelerator Module (OAM), with which Supermicro has significant experience in 8U configurations, allows a fully configured server to be brought to market faster than a custom design, reducing costs and delivery time.

Supermicro also introduces a 2U liquid-cooled, density-optimized server, the AS –2145GH-TNMR, and a 4U air-cooled server, the AS –4145GH-TNMR, each with 4 AMD Instinct™ MI300A accelerators. The new servers are designed for HPC and AI applications, which require extremely fast communication between the CPU and GPU. The APU eliminates redundant memory copies by combining AMD's highest-performance CPU, GPU, and HBM3 memory on a single chip. Each server contains leading x86 "Zen4" CPU cores for application scaling. Additionally, each server includes 512 GB of HBM3 memory. In a full rack solution (48U) consisting of 21 2U systems, more than 10 TB of HBM3 memory is available, as well as 19,152 Compute Units. HBM3 memory bandwidth to CPU is 5.3TB/second.

Both systems feature dual AIOMs with support for 400G Ethernet and expanded networking options designed to improve footprint, scalability and efficiency for high-performance computing. The 2U direct-to-chip liquid cooling system offers excellent total cost of ownership with over 35% savings in power consumption based on 21-rack solutions of 2U systems producing 61,780 watts per rack versus 95,256 watts per rack. an air-cooled rack, as well as a 70% reduction in the number of fans compared to an air-cooled system.

"AMD Instinct MI300 Series accelerators deliver leading performance for both long-running high-performance accelerated computing applications and the rapidly growing demand for generative AI," said Forrest Norrod, executive vice president and general manager, Data Center. Solutions Business Group, AMD. "We continue to work closely with Supermicro to bring to market cutting-edge total AI and HPC solutions based on the MI300 series accelerators and leveraging Supermicro's expertise in data center and system design."

Learn more from Supermicro and AMD experts. Watch this webinar live or on demand.

For more information visit:

Supermicro AMD Accelerator Site

AS -8125GS-TNMR2 (8U w/ MI300x)

AS -2145GH-TNMR (2U LC w/ MI300A)

AS -4145GH-TNMR (4U AC w/ MI300A)

About Super Micro Computer, Inc.

Supermicro (NASDAQ: SMCI) is a global leader in application-optimized total IT solutions. Founded and operating in San Jose, California, Supermicro is committed to delivering first-to-market innovation for enterprise, cloud, AI, and 5G Telco/Edge IT infrastructure. We are a manufacturer of Total IT Solutions with servers, AI, storage, IoT, switching systems, software and support services. Supermicro's motherboard, power and chassis design expertise further enables our development and production, enabling next-generation innovation from cloud to edge for our global customers. Our products are designed and manufactured in-house (in the United States, Taiwan and the Netherlands), leveraging global operations for scale and efficiency, and optimized to improve total cost of ownership and reduce environmental impact (green computing). The award-winning Server Building Block Solutions® portfolio enables customers to optimize for their exact workload and application by selecting from a broad family of systems built from our flexible, reusable building blocks that support a broad set of performance factors. form, processors, memory, GPU, storage, networking, power and cooling solutions (with air conditioning, free air cooling or liquid cooling).

Supermicro, Server Building Block Solutions and We Keep IT Green are trademarks and/or registered trademarks of Super Micro Computer, Inc.

AMD, the AMD arrow logo, AMD Instinct, EPYC and combinations thereof are trademarks of Advanced Micro Devices.

All other brands, names and registered trademarks are the property of their respective owners.

Photo - https://mma.prnewswire.com/media/2294523...Logo - https://mma.prnewswire.com/media/1443241...