SC25: ASUS Unveils Comprehensive Storage Solutions

At SC25, Asus (ASUSTeK Computer Inc.) announced an all-new lineup of enterprise and AI/HPC-optimized storage and infrastructure solutions.

Recognizing the escalating demands of scaling AI models and memory-intensive workloads, Asus storage solutions are now a strategic imperative, critical for sustaining efficient AI data processing and managing rapidly expanding datasets. This launch further solidifies the company’s position as a total infrastructure provider, delivering an integrated ecosystem spanning compute, storage, networking, and services. The company, through its global supply chain and logistical capabilities, ensures consistent, reliable product delivery, establishing itself as a trusted partner for organizations deploying resilient and scalable AI environments.

Comprehensive storage solutions
The company delivers a full spectrum of storage solutions across block, file, object, and software-defined systems – ensuring flexibility from edge to cloud, and from enterprise applications to AI and HPC workloads. The portfolio supports storage for Enterprise and AI/HPC needs, providing resilient data foundations and scalable performance for data-driven environments.

Block Storage – VS320D-RS12

Featuring active-active controller design with Intel Xeon processors, these systems provide enterprise-grade reliability, scalable capacity up to 7.1PB, and high throughput through SSD caching and auto-tiering — for virtualization and business-critical operations.

Unified Storage – VS320D- RS12U

Built for mixed enterprise workloads, this series supports multiple file and block protocols with advanced features such as SSD caching, auto-tiering , S3 cloud sync, DR site, and data reduction. Powered by Intel Xeon dual controller architecture, it ensures fast, efficient, and secure data access.

Object Storage – OJ340A-RS60

A scalable, AMD-based solution offering S3/Swift-compatible object storage on a Ceph framework. NVMe acceleration delivers predictable performance for AI data lakes, analytics, and long-term archiving at EB-scale.
 

JBOD Storage- VS320D-RS12J

Optimized for high-density capacity expansion, the Asus JBOD series provides up to 7.1PB of scalable storage with 78/12-bay configurations. It supports 12Gb/s SAS 3.0 interfaces, redundant power, and multipath connectivity, delivering flexible, reliable scalability for enterprise and data-center deployments.

AI/HPC Storage
Developed with Weka, IBM, Vast Data, and Hammerspace, this AMD EPYC powered platform provides high-performance, software-defined storage for GPU-accelerated AI and HPC environments, combining low latency with unified data management.

XA AM3A-E13 Powered by AMD Instinct MI355X Debuts for GenAI and HPC
Partnering with a broad ecosystem of technology leaders, a complete AI infrastructure lineup is being showcased at SC25. Within this comprehensive portfolio, Asus is unveiling the XA AM3A-E13, powered by 8 AMD Instinct MI355X GPUs and dual AMD EPYC 9005 processors, delivering efficiency for GenAI and HPC workloads. With support for expanded low-precision data types like FP4/FP6 and major gains in inference performance, the system enables ultra-fast AI inference alongside training. Built for efficiency and scalability, the system features HBM capacity (288GB) and up to 8TB/s memory bandwidth, enabling rapid training and simulation of large AI models. while a direct GPU-to-GPU interconnect and modular 10U design ensure high throughput, simplified deployment, and optimal thermal performance, engineered for efficient GenAI and large-model computing.

RS520QA-E13-RS8U

Beyond high-performance computing, Asus also showcases the RS520QA-E13-RS8U, a 2U 4-node high-density server supporting CXL 2.0 for shared memory and ultra-low-latency data access, for data-intensive HPC and AI factory environments. Completing the lineup, the RS720A-E13-RS8U and RS700A-E13-RS12U deliver balanced dual-socket performance, PCIe 5.0 expandability, and high memory capacity to meet the needs of virtualization, enterprise computing, and general-purpose AI deployments.

Comprehensive Xeon 6 platform for AI and enterprise scalability

The company also presents its Intel lineup tailored for versatile enterprise and AI workloads. Leading the portfolio, ESC8000-E12P AI server supports up to 8 dual-slot GPUs including Intel Gaudi 3 PCIe AI accelerators, paired with Intel Xeon 6 processors to deliver outstanding compute density and performance efficiency. Each Intel Gaudi 3 accelerator integrates 128GB of HBM2E memory and 3.7TB/s bandwidth, enabling sustained throughput for AI training, fine-tuning, and large-scale model execution. Featuring a PCIe 5.0 architecture with integrated Ethernet-based connectivity, the system provides optimized scale-out efficiency for enterprise AI infrastructures and RAG applications.

RS720-E12-RS24U
Click to enlarge

For general-purpose deployments, the RS720-E12-RS24U offers a 2U dual-socket Xeon 6 processors design optimized for balanced performance and expansion flexibility, while the RS700-E12-RS4U provides a compact, dual-socket Xeon 6 processors high-I/O-density platform ideal for enterprise and virtualization workloads.

AsusTech Talks highlight industry collaboration
Reinforcing its commitment to open collaboration, Asus is bringing together leading partners – including Intel, Vertiv, IBM, Micron, Western Digital, and Weka – for ASUS Tech Talks, a series of in-booth sessions where industry experts share insights on cooling, storage, and compute innovations for next-gen AI infrastructure. These joint sessions emphasize the company’s role at the center of a vibrant technology ecosystem driving efficiency, scalability, and sustainability across AI data centers.