Inspur's Edge Servers Boast Nvidia EGX, NGC-Ready Certification

Inspur today announced that its edge computing servers, first unveiled at GTC China in 2019, support Nvidia’s EGX cloud-native platform and have obtained NGC-Ready for Edge certification. Inspur today announced that its edge computing servers, first unveiled at GTC China in 2019, support Nvidia’s EGX cloud-native platform and have obtained NGC-Ready for Edge certification. According to Inspur, this certification, in combination with the Nvidia EGX stack, will allow customers to deploy and run artificial intelligence (AI) workloads in edge and micro data centers. Nvidia’s EGX processor, which was announced at MWC Los Angeles 2019, is designed to offer a cloud-native edge supercomputing platform powered by the Cuda Tensor Core graphics processing units (GPU), which the company claimed could process 15 teraflops of data per second and up to 140 simultaneous high definition video streams. “All of this processing basically translates to one single node [that] is equivalent to hundreds of nodes in a data center,” Nvidia CEO Jensen Huang said during his keynote at the event. Inspur is one of many vendors now offering EGX compatible systems. Other vendors include H3C, Lenovo, Dell Technologies, Mellanox, Cisco, and VMware. The two servers, the NE5260M5 and NF5280M5 have been designed to perform in edge deployments, with capabilities for AI computing, edge computing, and container clouds, according to Inspur. The imaginatively named NE5260M5 features a low profile chassis design that is half the size of a traditional 2U server and can also be wall-mounted. It supports up to six Nvidia Tesla T4 GPUs. The NE5260M5 is already being deployed by the China Mobile Research Institute in large-scale applications as part of an edge computing pilot announced in early December. The pilot includes the use of Nvidia’s GPUs and the EGX platform to develop new educational tools and improve response and real-time monitoring of natural disasters and emergency medical services. The operator is using Nvidia’s GPUs in its burgeoning 5G network to equip first responders and doctors with AI-powered tools that can remotely diagnose patients and transmit footage from drones at the scene of an unfolding disaster. The larger NF5280M5 features Inspur’s propriety spacial layering technology, which is designed to enable more flexible configurations, according to the vendor. The server features I/O expansion modules and can be equipped with up to eight Tesla T4 GPUs. Inspur is aiming the NF5280M5 at complex, compute-intensive AI workloads at the edge of networks.