This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
AEWIN

Edge Computing Server
AEWIN Technologies Co., Ltd.
SCB-1932M





2U Rack-Mount Edge AI Server powered by Dual Intel® Ice Lake-SP Xeon® Scalable processors is designed for Smart Medical. Supporting DDR4 up to 2TB, 2x PCIe Gen4 x16 for Dual-width GPU Cards, 4 PCIe Gen4 x8 slot for expansion LAN modules, 2 x 2.5” swappable SATA SSD/HDD, IPMI, USB 3.0, 2x GbE, 1x Console, 2x M.2, CF/mSATA/miniPCIe, 1x PCIe, and Redundant PSU, Intel OpenFL (Open Federated Learning), Intel OpenVINO AI Toolkit
- Support dual Intel® Ice Lake-SP Xeon® scalable Processors, Socket P+ 4189pin
- Support up to 2TB DDR4 RDIMM/LRDIMM 3200MHz
- 4x PCIe Gen4 x 16 slots for NIC/NVMe/Accelerator cards + 2x dual-width PCIe Gen4 x16 slots for standard PCIe cards
- Intel OpenFL (Open Federated Learning) support ready
- Support Intel OpenVINO AI Toolkit
- Support BMC/IPMI
SCB-1932M is an Edge AI Server designed for Smart Medical application. With its short depth design (600mm), SCB-1932M can be easily deployed at the edge for time critical applications. Benefited from the extraordinary computing power and resources of dual Intel 3rd Gen Xeon Scalable processors, SCB-1932M is with excellent performance and high scalability for accelerators & network interface cards. The features make it capable of processing on-site big data in near real-time.
With up to 80 CPU cores, SCB-1932M is able to help smart medical to increase effectiveness with its outstanding processing power. The performant Edge AI Server can not only accomplish efficient machine vision inspection/analysis with the support of Intel OpenVINO AI Toolkit, but also enable AI model training to accumulation the experience and the value of clinal information.
SCB-1932M supports Intel Open Federated Leaning (OpenFL) for AI analytics. AI and machine learning require a lot of data for model training while it is extreme difficult to collect the high-quality data especially in Healthcare and Medical imaging because of privacy. Federated learning keeps the data local while ships the models from every edge device to the center (SCB-1932M) to train an aggregated model which can benefit every edge. It helps to improve the model while preserving data integrity and security through encryption with federated learning and Intel Software Guard Extensions (Intel SGX) technology.
Furthermore, SCB-1932M’s platform security has also been enhanced. TME (Total Memory Encryption, Crypto Acceleration, and Intel PFR (Platform Firmware Resilience) technologies are available to help harden the platform against malicious actions. The built-in security features of Intel chip help to protect medical data from hackers.
-- ECC & Registered RDIMM:DDR4 2933/3200 MHz memory, up to 128GB per DIMM
--LRDIMM:DDR4 2933/3200 MHz, up to 128GB per DIMM
2x PCIe Gen4 x16 slots for dual-width GPU card
2x M.2, 1x CF/mSATA/miniPCI-E,
2x SlimSAS 8i connector
1x PCIe x8 slot for Standard PCIe card
1x internal USB 3.0 pin header
2x internal pin header (COM2 & COM3)
1x HDD LED (Red)
2x Status LED (Green/Yellow via programmable GPIO)
non-condensing
2x power cord
1x Ethernet/Console cable
Manual, Quick Installation Guide, Utilities & Drivers