Latest news with #SupercomputingAsia2025
Yahoo
20-03-2025
- Business
- Yahoo
ASUS Presents Next-Generation Infrastructure Solutions at SCA25
ASUS unveils an extensive lineup of servers to accelerate the future of AI KEY POINTS ASUS at Supercomputing Asia 2025: Comprehensive AI server lineup to accelerate the future of AI Accelerated servers: ESC 8000A-E13P and ESC N8-E11V empower peak performance for generative AI applications Unleashing data for HPC: RS720A-E12-RS24U and RS920Q-E12-RS16 offer peak performance, while RS520QA-E13-RS8U provides effortless scalability SINGAPORE, March 20, 2025 /PRNewswire/ -- ASUS showcased an extensive lineup of next-generation infrastructure solutions at Booth B3 during Supercomputing Asia 2025 (SCA25) conference from March 10 to 13 at the Marina Bay Sands Expo and Convention Centre, Singapore. GPU servers ESC 8000A-E13P: Turbocharge generative AI and LLM workloads Leading the lineup is the ESC 8000A-E13P, a HPC server that's fully compliant with NVIDIA MGX modular architecture, and able to deploy quickly at a large scale. It offers high-density GPUs for diverse applications, and supports up to eight NVIDIA H200 NVL dual-slot cards of 600 watts each. ESC8000A-E13P also benefits from an optimized a server configuration, with five PCIe® 5.0 slots for high-bandwidth NVIDIA BlueField-3 and NVIDIA ConnectX-8SuperNICs to enhance east-west traffic, and NVIDIA BlueField-3 DPUs for line-rate processing of software-defined networking, storage, and cybersecurity. ESC N8-E11V with NVIDIA HGX™ H200: The best choice for heavy AI workloads For generative AI applications, ASUS highlighted advanced solutions like ESC N8-E11V with the NVIDIA HGX™ H200 platform designed to offer scalable performance for data-intensive tasks like AI, machine learning, and HPC applications. As the expert in AI supercomputing, ASUS has placed a strong emphasis on power efficiency and optimized thermal design within ESC N8-E11V. This powerful AI server supports both air-cooling and D2C (direct-to-chip) liquid-cooling solutions, coupled with dedicated CPU and GPU airflow tunnels, allowing heat to be expelled into the surrounding ambient air ― resulting in greater energy efficiency and overall system power savings. This ensures that the server operates at peak performance, even under the most demanding conditions. Rack Servers RS520QA-E13-RS8U: Maximizing efficiency for HPC workloads ASUS also showcased the RS520QA-E13-RS8U, a cutting-edge multi-node server ideal for HPC, EDA, and cloud computing. Equipped with one AMD EPYC™ 9005 processor, it supports up to 20 DIMM slots per node with advanced CXL memory expansion module, PCIe® 5.0, and OCP 3.0 for robust performance, scalability, and efficiency in demanding workloads. RS720A-E12-RS24U: New Generation, High Performance 2U Server ASUS RS720A-E12-RS24U is designed to accelerate application performance leveraging accelerator cards and storage scalability. With the CPU and memory configured in a front parallel design that enables efficient airflow for excellent thermal performance, the RS720A-E12-RS24U is optimized for rack placement. RS920Q-E12-RS16: Unleashing data for HPC ASUS RS920Q-E12-RS16 leverages Intel Xeon® 6 processors to provide the density and performance needed to elevate HPC workloads. With direct-to-chip liquid-cooling technology to maintain optimal performance and prevent overheating, the multi-node server offers great scalability and reliability in demanding operational environments such as HPC, cloud computing and more. Storage server VS320D-RS26: Optimize price and performance for SMB workloads ASUS VS320D-RS26 (2.5-inch 2U 26-bay) is a high-density hybrid flash-storage system. It offers 8% more capacity than the common 2U 24-bay products on the market. This can further lower the cost per TB, minimize IT rack space and generate a greener footprint. It delivers outstanding performance ideal for modern enterprise applications store such as virtualization, database, mail server and VDI. Furthermore, ASUS launched a proof of concept (POC) for the groundbreaking ASUS AI POD, accelerated by NVIDIA Blackwell architecture. Other highlights at the ASUS booth include SoftServe's Jade, a virtual assistant powered by Generative AI, which enhances customer service with human-like interactions and personalized responses. Additionally, special guest speakers Mr. Peter Wu, CEO of TWSC, Taiwan AI Cloud and Dr. Robby Tan, Chief Scientist of ASUS Intelligent Cloud Services (AICS) shared their insights on supercomputing and AI. The former delved into Taiwan's cutting-edge advancements in AI infrastructure, especially in AI cluster design, innovative services and workload optimization to meet diverse workloads. The latter shared insights on using clinical and administrative AI agents in healthcare to enhance decision-making and administrative efficiency, to help providers focus on patient care. Availability & Pricing ASUS servers are available worldwide. Please visit for more ASUS data-center solutions or please contact your local ASUS representative for further information. For more information on Softserve's Jade, a virtual assistant powered by Generative AI, please visit: About ASUS ASUS is a global technology leader that provides the world's most innovative and intuitive devices, components, and solutions to deliver incredible experiences that enhance the lives of people everywhere. With its team of 5,000 in-house R&D experts, the company is world-renowned for continuously reimagining today's technologies. Consistently ranked as one of Fortune's World's Most Admired Companies, ASUS is also committed to sustaining an incredible future. The goal is to create a net zero enterprise that helps drive the shift towards a circular economy, with a responsible supply chain creating shared value for every one of us. View original content to download multimedia: SOURCE ASUS Sign in to access your portfolio
Globe and Mail
11-03-2025
- Business
- Globe and Mail
MiTAC Computing Showcases Cutting-Edge AI and HPC Servers at Supercomputing Asia 2025
G4520G6 and TN85-B8261 Servers Deliver Unparalleled Performance for AI, ML, and HPC Workloads. SINGAPORE , March 11, 2025 /CNW/ -- MiTAC Computing Technology Corp., a subsidiary of MiTAC Holdings Corp. (TSE:3706) and a global leader in server design and manufacturing, will showcase its latest AI and HPC innovations at Supercomputing Asia 2025, taking place from March 11 at Booth #B10. The event highlights MiTAC's commitment to delivering cutting-edge technology with the introduction of the G4520G6 AI server and the TN85-B8261 HPC server—both engineered to meet the growing demands of artificial intelligence, machine learning, and high-performance computing (HPC) applications. G4520G6 AI Server: Performance, Scalability, and Efficiency Redefined The G4520G6 AI server redefines computing performance with an advanced architecture tailored for intensive workloads. Key features include: Exceptional Compute Power – Supports dual Intel® Xeon® 6 Processors with TDP up to 350W, delivering high-performance multi-core processing for AI-driven applications. Enhanced Memory Performance – Equipped with 32 DDR5 DIMM slots (16 per CPU) and 8 memory channels, supporting up to 8,192GB DDR5 RDIMM/3DS RDIMM at 6400 MT/s for superior memory bandwidth. Unmatched GPU Support – Supports up to eight full-height, dual-slot NVIDIA H200 NVL, NVIDIA H100 NVL, or NVIDIA L40S for scale-out AI training, ML, and rendering applications. Featuring the NVIDIA H200 GPU with 141GB of HBM3e memory and nearly 27 petaflops of FP8 deep learning compute, it accelerates AI and HPC workloads with exceptional speed and efficiency. Superior Connectivity – Equipped with three standard PCIe 5.0 x 16 expansion slots and three OCP v3.0 mezzanine slots, the MiTAC G4520G6 platform enables high-performance network connectivity, such as NVIDIA ConnectX NICs, BlueField-3 SuperNICs and DPUs, for clustered computing. Advanced Cooling & Power Efficiency – Engineered for superior thermal management, it includes eight hot-swap system fans and four external hot-swap fan modules. Four hot-swap CRPS power supplies provide (3+1) redundancy, delivering up to 9,600W with 80+ Titanium efficiency. TN85-B8261: Versatile 2U Server for HPC and AI Workloads The TN85-B8261 is a versatile 2U server designed to deliver exceptional performance for high-performance computing and AI applications. Key highlights include: Powerful Dual-Socket Performance – Supports AMD EPYC 9005 / 9004 processors, delivering exceptional computing power for AI and HPC workloads. Scalable Memory Architecture – Features (12+12) DDR5 DIMM slots, supporting up to 6,144GB DDR5-6000 RDIMM/LRDIMM for high-speed data processing. Flexible Expansion Capabilities – Supports up to four full-height, dual-slot enterprise H100 NVL and L40S GPUs for scalable AI training, machine learning, and rendering applications. Additionally, two half-height, half-length PCIe 5.0 x16 slots enable high-performance cluster networking deployment. Optimized Connectivity & Management – Dual 10GBase-T LAN ports for high-bandwidth networking and an AST2600 BMC with IPMI 2.0 & Redfish support for remote server management. Reliable Power Efficiency – (1+1) redundant 2,700W hot-swap CRPS power supplies with 80+ Titanium efficiency, delivering sustainable energy and operational reliability. Driving Innovation in AI and HPC MiTAC Computing is dedicated to pushing the boundaries of AI and HPC technology. The G4520G6 and TN85-B8261 servers are designed to empower enterprises and research institutions with exceptional compute power, scalability, and energy efficiency, ensuring optimal performance for next-generation workloads. Visit MiTAC Computing at Supercomputing Asia 2025 MiTAC Computing invites attendees to experience the power of the G4520G6 AI Server and TN85-B8261 HPC Server firsthand at Supercomputing Asia 2025. Visit our booth #B10 to explore how our latest innovations can accelerate AI and HPC applications. For more information, please visit the links below: G4520G6 product page: TN85-B8261: About MiTAC Computing Technology Corporation MiTAC Computing Technology Corp., a subsidiary of MiTAC Holdings, delivers comprehensive, energy-efficient server solutions backed by industry expertise dating back to the 1990s. Specializing in AI, HPC, cloud, and edge computing, MiTAC Computing employs rigorous methods to ensure uncompromising quality not just at the barebone level but, more importantly, at the system and rack levels—where true performance and integration matter most. This commitment to quality at every level sets MiTAC Computing apart from others in the industry. The company provides tailored platforms for hyperscale data centers, HPC, and AI applications, guaranteeing optimal performance and scalability. With a global presence and end-to-end capabilities—from R&D and manufacturing to global support—MiTAC Computing offers flexible, high-quality solutions designed to meet unique business needs. Leveraging the latest advancements in AI and liquid cooling, along with the recent integration of Intel DSG and TYAN server products, MiTAC Computing stands out for its innovation, efficiency, and reliability, empowering businesses to tackle future challenges.
