Taipei, Taiwan, October 14, 2024—ASUS is excited to participate in the 2024 OCP Global Summit, taking place from October 15-17 at the San Jose Convention Center, at booth #A31. With nearly 30 years of experience in the server industry, ASUS has a rich history of collaboration with cloud-service providers, beginning in 2008 with the design of server motherboards for leading cloud data centers. Building on this strong foundation in motherboard expertise, ASUS has developed a comprehensive lineup of AI servers that will be showcased at the summit, underscoring our commitment to advancing AI and data center technologies.
Elevate AI with AMD EPYC 9005 and Instinct MI325X accelerators
ASUS is debuting its latest models powered by AMD EPYC™ 9005 processors.
Leading the lineup is the
ASUS ESC A8A-E12U, a 7U server equipped with dual AMD EPYC 9005 processors and eight AMD Instinct™ MI325X accelerators. The MI325X offers an industry-leading 256GB of high-bandwidth memory (HBM) capacity and up to 6TB/s HBM bandwidth, making it perfectly suited for inference and fine-tuning of large AI models and HPC workloads. Additionally, it supports direct GPU-to-GPU interconnects and a one-GPU-to-one-NIC topology, with up to eight 400G NICs for exceptional performance and scalability.
We’ll also be showcasing
ASUS 8000A-E13P, a 4U server powered by dual AMD EPYC 9005 processors, supporting up to eight double-slot GPU cards (up to 600W) with the flexibility to accommodate a full range of GPUs for various AI applications. Fully compliant with the NVIDIA® MGXTM architecture, it is designed for rapid deployment in large-scale enterprise AI infrastructures. Configured with an NVIDIA 2-8-5 topology (CPU-GPU-DPU/NIC) and four high-bandwidth PCIe® NICs, it enhances east-west traffic and overall system performance.
We’re also introducing ASUS RS520QA-E13, a 2U four-node, high-density server specifically designed for the cloud and the electronic design automation (EDA) segment. Each node is equipped with an AMD EPYC 9005 processor and two Compute Express Link (CXL) memory expansion modules, offering a total of 12 + 8 DIMM expandability for high memory capacity and speed. With exceptional thermal performance supporting up to 400W TDP through efficient air-cooling, the RS520QA-E13 ensures optimal operation. Its all-front-access layout simplifies maintenance, enhancing user convenience.
Expanding AI horizons with Intel Xeon 6 and Gaudi 3 accelerators
ASUS will also highlight its powerful Intel®-based solutions.
ASUS RS720-E12, a 2U server powered by Intel Xeon 6 processors, features the OCP DC-MHS modular architecture, offering flexibility and efficiency for diverse data center needs. Its GPU-optimized design supports up to three dual-slot GPUs, making it ideal for AI workloads and machine learning tasks.
For high-end AI applications, ASUS ESC I8-E11 is robust 7U server powered by dual 5th Gen Intel Xeon Scalable processors and capable of accommodating eight Intel Gaudi 3 accelerators. This powerhouse delivers exceptional performance for the most demanding workloads, including generative AI, deep learning, machine learning, data analysis, and scientific research. Its modular design minimizes cable usage, reducing assembly time and enhancing thermal optimization for improved overall efficiency.
Join the ASUS 2024 OCP Global Summit session on modular server architecture
Don't miss the 15-minute ASUS session at the 2024 OCP Global Summit on October 16 from 10:20 to 10:35, where we will explore the future of modular server architecture with an introduction of Data Center Modular Hardware System (DC-MHS) developed by OCP. Discover how this innovative architecture is transforming server design, offering unprecedented flexibility, simplified maintenance and efficient scalability for modern data centers.