The embedded MXM graphics module enables high-performance, energy-efficient GPU computing to accelerate time sensitive and mission critical edge industrial applications.


● Linghua technology egx-mxm-a1000, egx-mxm-a2000 and egx-mxm-a4500 are the first embedded GPU modules using NVIDIA ampere architecture.

● Linghua technology embedded MXM graphics module has a compact and energy-efficient MXM shape design, which can realize high-performance GPU acceleration, so that many vertical markets such as medical treatment, manufacturing and transportation can adopt edge computing and embedded AI.

● rugged design to withstand extreme temperatures, shock and vibration, and corrosion under severe conditions.

Shanghai, China – November 10, 2021

Linghua technology, the world’s leading provider of edge computing solutions, today released the industry’s first embedded MXM graphics module based on NVIDIA ampere architecture, which is designed for edge accelerated computing and AI workload. The new embedded graphics module adopts a compact mobile PCI Express (MXM) shape design, which can realize real-world timeline tracking, AI accelerated graphics and energy-efficient AI reasoning acceleration. These modules can improve responsiveness, accuracy and reliability for mission critical and timeliness applications in medical, manufacturing, transportation and other fields.

Cai Yuli, product director of embedded platform and module division of Linghua technology platform product center, said: “Computing and AI workloads are shifting from the cloud to edge devices. In addition to shortening response time, increasing security and reducing communication costs, the edge needs to process more and more data, and the performance requirements for edge devices are gradually improved, but the power budget has not been adjusted. NVIDIA ampere architecture provides a major breakthrough in efficiency and energy efficiency, driving the edge The device has a higher level in general computing, image processing and reconstruction, and AI reasoning. “

Scott Fitzpatrick, vice president of product marketing at NVIDIA, said: “NVIDIA ampere architecture can provide breakthrough performance and functions, integrating the latest generation of RT core, tensor core, CUDA core, PCIe Gen 4 and NVIDIA video codec. With the wide application of rendering and Simulation in all walks of life, NVIDIA’s latest embedded solution can provide up to 2x rendering performance, 2x fp32 throughput and hardware accelerated video coding and decoding Code to cope with a significant increase in graphics and computing workloads. “

Linghua technology’s embedded MXM GPU module is based on NVIDIA ampere architecture, equipped with up to 5120 CUDA cores, 160 tensor cores and 40 RT cores, supports PCIe Gen 4 and up to 16GB gddr6 memory, and TGP up to 115W. These modules can meet the requirements of computing intensive, high graphics and high memory applications. It is one-fifth the size of a full height, full-length PCI Express graphics card, and is more robust, resistant to extreme temperature, impact and vibration, and corrosion, suitable for edge environments with limited size, weight and power. These embedded graphics modules provide five-year service life support. Developers, solution architects and system integrators can trust the stable supply in the product life cycle and innovate around new solutions.

Applications of embedded MXM graphics modules include:

● medical health: accelerate image reconstruction of mobile X-ray, ultrasonic and endoscopic systems

● transportation: real time object detection on railway or airport runway to improve transportation safety

● retail and logistics: navigation and route planning for autonomous UAVs and mobile robots (AMRS) to assist in the last step, last mile delivery

● aerospace and defense: time sensitive and mission critical command, control, communications, computer (C4) intelligence, surveillance and reconnaissance (ISR) applications

Leave a Reply

Your email address will not be published. Required fields are marked *