AEWIN’s state-of-the-art low-profile rack-mounted computing server integrated with a double-wide GPU improves performance and reliability

0

The SCB-1932C and SCB-1937C high-performance edge computing servers. 1 credit

The emergence of 5G, Artificial Intelligence (AI) and Internet of Things (IoT) technologies can unlock digital transformation to meet the needs of various industries such as manufacturing, healthcare, urban infrastructure, etc. As cloud solutions become a must-have technology, challenges around performance, privacy, and system complexity are driving connected technology innovation for Edge Computing. AEWIN provides innovative hardware to handle changing edge computing needs to stay ahead of the competition. The latest versions of the SCB-1932C and SCB-1937C specialty servers add speed, flexibility, reliability, and maximum computing power to support various multi-access Edge Computing (MEC) and AIoT applications.

AEWIN’s solutions provide better data security and efficient control of the continuous operation of AI-based applications such as embedded systems, facial recognition and manufacturing equipment. The distance between system computing units and the edge should be as close as possible to reduce delays caused by excessive load on the upper layer computing platform and middle layer network bandwidth. However, the physical space inside edge devices is limited, which means that the dimensions of the boards and components must be considerably reduced. Additionally, cooling issues can also impact the performance of compute units. These factors have caused problems in product development. The SCB-1932C and SCB-1937C solved these issues with smaller footprints and double-wide GPU designs.

In terms of dimensions, the SCB-1932C and SCB-1937C are 600mm long, just 3/4 of the 800mm units commonly found in other servers. The small footprint makes better use of space while providing expandability, achieving an excellent balance between flexibility and performance. Additionally, the front access design has 2 key benefits:

* No need to disassemble the whole case for maintenance, increasing convenience.
*Increased product reliability thanks to the cooling facilitated by the frontal configurations of the network ports and the accelerator cards.

The double-wide GPU dramatically increases AI performance for edge computing. Compared to current single-width GPUs used to perform AI inference on edge equipment, double-width GPUs provide both inference and training functions. Once enough data has been captured for a period of operation, double-wide GPUs can retrain models in real time and continuously improve the AI ​​accuracy of edge gear.

Nevertheless, AEWIN offers both Intel and AMD processor options as integration advantages to match users’ selections.

*SCB-1932C integrates with 3rd Generation Intel Xeon Scalable processors. which has been on the market for some time; it claims a high market share in the high performance computing market along with full support for peripheral technologies.
*SCB-1937C integrates with AMD EPYC 7002/7003 series processors; it promotes advanced manufacturing processes and an aggressive pricing strategy.

These two great brands bring advantages to the table with different key competitive positioning. Ultimately, users’ needs will determine which brand of CPU is right for them considering budget and applications.

SCB-1932C and SCB-1937C can be applied in MEC, network equipment and AIoT systems; AEWIN also provides comprehensive services to support these applications. We offer industry-leading designs in system architecture, platform support, accelerator card modules, and NVMe modules focused on network applications. AEWIN’s BIOS, firmware and mechanism designs are customizable to meet the requirements and needs of different customers.

In an increasingly competitive market environment, product availability and timing are becoming critical factors that impact competitiveness. However, manufacturers/customers only discover that their products perform below expectations during the development phase. This results in a prolonged development phase of projects or the launch of poorly performing products. An out-of-the-box solution (OTS) offered by AEWIN can alleviate the problem by allowing customers to perform tests before selecting the model and solution. By checking the products in advance, the products can be marketed on time successfully with controlled quality. Besides the advantages, OTS can also be combined with AEWIN’s customization services to develop into a series of products. While other OEM/ODM-designed manufacturers offer value-added services, they may not accept low-volume, high-diversity projects because orders must meet a minimum quantity threshold. AEWIN provides OTS customizable firmware, hardware and mechanisms to meet customization requirements and release schedule expectations, thereby enhancing product competitiveness and leveraging new business opportunities in edge computing and computing markets. the AI.

Share.

About Author

Comments are closed.