A new GPU edge computing solution with NVIDIA L4 GPU NVQual validation, the MIC-770 V3 Modular IPC with MIC-75M20 expansion i-Module, is compatible with the NVIDIA L4 Tensor Core GPU, boasts 7,424 CUDA cores and 24GB GDDR6 GPU memory; and consumes only 72W of power.

When paired with the efficiency of the NVIDIA L4 GPU, the high-performance highly scalable compact design of this IPC creates an excellent AIoT solution for diverse deep learning and edge inference applications in factory automation, autonomous vehicles, automated optical inspection (AOI), and AI prediction in medical equipment, as well as smart city video surveillance and transportation.

Key features

• NVIDIA Qualified system with NVIDIA L4 Tensor Core GPU
• Delivers 7,424 CUDA cores and 30.3 TFLOPS with 24GB GDDR6 GPU memory in 72W power envelope for edge AI and graphics applications
• 12th Gen Intel Core i9/i7/i5/i3 processors (LGA 1700)
• High-performance solution with compact ruggedized design & Flex I/O/iDoor expansions
• Supports Advantech iBMC 1.2 Remote Management Solution on WISE-DeviceOn
• Accommodates wide operating temperature and space-limited environments

High-performance compact design with flexible expandability

Powered by the latest 12th Gen Intel Core i processor, MIC-770 V3 is designed as a high-performance open-source x86 platform capable of enabling the quick development of GPU-accelerated solutions.

By Adopting MIC-75M20, a 2-slot expansion i-Module, this integrated solution is compatible with the NVIDIA L4 Tensor Core GPU with its small, energy-efficient, single-slot, low-profile 72W form factor.

These features make it ideal for AI-based edge computing and inference. It delivers energy-efficient universal acceleration for AI inference, video, and graphics applications; and is ideal for global deployment in enterprise, cloud, and edge applications with limited space.

Modular design enables diverse industry applications

MIC-770 V3 features a modular design that delivers enhanced functionality and flexibility for PCIe expansion via Advantech i-Modules and Flex I/O in the front panel. Adding a PCIE-1674 vision frame grabber card enables the connection of 4 x cameras when used in autonomous vehicles.

Likewise, adding 4 x GbE Flex I/O (98910770301) enables this controller to connect to LiDAR systems, thus enabling it to detect distances and shapes in its environment then pass on data to the NVIDIA L4 GPU for the rendering of 3D models based on graphics analysis.

Remote management for seamless Edge AI computing

MIC-770 V3 supports the iBMC 1.2 Edge Intelligent Solution to simplify remote systems and edge device management. Indeed, by leveraging iBMC hardware-based out-of-band management technology, this WISE-DeviceOn solution can serve as both an in-band and out-of-band management system, enabling the comprehensive access, configuration, monitoring, and analysis & control of IoT network assets on a centralized platform.

In addition, Enterprise IT and OT managers can remotely control the power (via reset/forced shutdown/power on/power off), conduct remote system recovery via Acronis or hardware, trigger SSD recovery, and check operating statuses — even during software or OS failures. These features address 90% of system failures without requiring users to dispatch maintenance crews to the site, thus drastically reducing system downtime and operational costs.

Thermal Design offers stable and reliable GPU computing

The MIC-770 V3 leverages an NVIDIA L4 GPU and supports wide operating temperatures (0 ~ 40 °C) when used in harsh environments. It features a dedicated server-grade air duct design that improves the thermal management of the GPU. This cooling solution maintains a GPU IC operating temperature below 70.5°C in environmental conditions up to 40°C to deliver superior performance and clock frequency residency. In sum, MIC-770 V3 leverages its advanced thermal design to deliver 30.3 TFLOPs computing power with 72 watts of power consumption.

Advantech