ASRock Rack Inc., a leading innovative server company, today announces its presence at SC24, held at the Georgia World Congress Center in Atlanta from November 18-21. At booth #3609, ASRock Rack will showcase a comprehensive high-performance portfolio of server boards, systems, and rack solutions with NVIDIA accelerated computing platforms, helping address the needs of enterprises, organizations, and data centers.

Artificial intelligence (AI) and high-performance computing (HPC) continue to reshape technology. ASRock Rack is presenting a complete suite of solutions spanning edge, on-premise, and cloud environments, engineered to meet the demand of AI and HPC. The 2U short-depth MECAI, incorporating the NVIDIA GH200 Grace Hopper Superchip, is developed to supercharge accelerated computing and generative AI in space-constrained environments. The 4U10G-TURIN2 and 4UXGM-GNR2, supporting ten and eight NVIDIA H200 NVL PCIe GPUs respectively, are aiming to help enterprises and researchers tackle every AI and HPC challenge with enhanced performance and greater energy efficiency. NVIDIA H200 NVL is ideal for lower-power, air-cooled enterprise rack designs that require flexible configurations, delivering acceleration for AI and HPC workloads regardless of size.

Giga Computing, a subsidiary of GIGABYTE and an industry leader in generative AI servers and advanced cooling technologies, shows off at SC24 how the GIGABYTE enterprise portfolio provides solutions for all applications, from cloud computing to AI to enterprise IT, including energy-efficient liquid-cooling technologies. This portfolio is made more complete by long-term collaborations with leading technology companies and emerging industry leaders, which will be showcased at GIGABYTE booth #3123 at SC24 (Nov. 19-21) in Atlanta. The booth is sectioned to put the spotlight on strategic technology collaborations, as well as direct liquid cooling partners.

The GIGABYTE booth will showcase an array of NVIDIA platforms built to keep up with the diversity of workloads and degrees of demands in applications of AI & HPC hardware. For a rack-scale AI solution using the NVIDIA GB200 NVL72 design, GIGABYTE displays how seventy-two GPUs can be in one rack with eighteen GIGABYTE servers each housing two NVIDIA Grace CPUs and four NVIDIA Blackwell GPUs. Another platform at the GIGABYTE booth is the NVIDIA HGX H200 platform. GIGABYTE exhibits both its liquid-cooling G4L3-SD1 server and an air-cooled version, G593-SD1.

Giga Computing, a subsidiary of GIGABYTE and an industry leader in servers for x86 and ARM platforms as well as advanced cooling technologies, today announced its initial wave of GIGABYTE servers that support the full stack of AmpereOne family of processors. Last year, AmpereOne processors were announced and there were GIGABYTE servers in support of the platform available for select customers. Now, GIGABYTE servers have general availability with single and dual socket servers already in production, and more coming in late Q4. GIGABYTE servers for Ampere Altra and AmpereOne processors will be showcased at the GIGABYTE booth and Ampere pavilion at Yotta 2024 in Las Vegas on Oct. 7-9.

The AmpereOne family of processors, designed for cloud-native computing, features up to 192 custom designed Ampere cores, DDR5 memory, and 128 lanes of PCIe Gen 5 per socket. Overall, this line of processors target cloud instances with incredible VM density to boot, all while excelling at performance per watt. Delivering more cores, more IO, more memory, more performance, and more cloud features, this full stack of CPUs has additional applications in AI inference, data analytics, and more.

Ampere has announced a significant update to its product roadmap, highlighting the upcoming 512-core AmpereOne Aurora processor. This new chip is specifically designed to address the growing demands of cloud-native AI computing.

The newly announced AmpereOne Aurora 512 cores processor integrates AI acceleration and on-chip High Bandwidth Memory (HBM), promising three times the performance per rack compared to current AmpereOne processors. Aurora is designed to handle both AI training and inference workloads, indicating Ampere's commitment to becoming a major player in the AI computing space.

Ampere Computing today released its annual update on upcoming products and milestones, highlighting the company's continued innovation and invention around sustainable, power efficient computing for the Cloud and AI. The company also announced that they are working with Qualcomm Technologies, Inc. to develop a joint solution for AI inferencing using Qualcomm Technologies' high-performance, low power Qualcomm Cloud AI 100 inference solutions and Ampere CPUs.

Semiconductor industry veteran and Ampere CEO Renee James said the increasing power requirements and energy challenge of AI is bringing Ampere's silicon design approach around performance and efficiency into focus more than ever. "We started down this path six years ago because it is clear it is the right path," James said. "Low power used to be synonymous with low performance. Ampere has proven that isn't true. We have pioneered the efficiency frontier of computing and delivered performance beyond legacy CPUs in an efficient computing envelope."

GIGABYTE Technology, Giga Computing, a subsidiary of GIGABYTE and an industry leader in high-performance servers, server motherboards, and workstations, today announced four new GIGABYTE R-series servers for AmpereOne Family of processors for cloud-native computing where high compute density per rack and power-efficiency matter.

For cloud-native computing, hyperscalers or cloud service providers (CSPs) rely on predictable high-performance, scalable infrastructure, and power efficient nodes. GIGABYTE servers running the AmpereOne Family platform achieve those expectations, but this is not the first time GIGABYTE has worked with Ampere Computing. The partnership first started in 2020 with the launch of the Ampere Altra platform. And this new family of AmpereOne processors will not supersede the Altra platform, rather it is an extension of what Arm architecture is capable of by Ampere Computing. For instance, the CPU core count goes beyond 128 cores in Altra to 136-192 cores in AmpereOne for new levels of performance and VM density. On top of that, the private L2 cache per core has doubled and there is support for DDR5 memory and PCIe Gen 5.