High-performance AI computer features innovative cooling
Two PCIe slots are available to record Nvidia Tesla T4s used for fast calculation of interferences. The platform can achieve up to 8.1 TFLOPS in the FP32 benchmark and 130 TOPs in the INT8 benchmark for real time calculations that are based on a trained neuronal network model. The Nuvo-7166GC can accommodate an 8th and 9th generation Intel processors (6/8 cores) and 64 GB DDR4-2666 RAM to provide a rugged industrial AI inference platform with a good balance relationship between the CPU, GPU and memory performance.
Inference in the context of the platform means applications that are trained for specific tasks using AI neuronal networks. Basic learning is not important, but facts or insights derived based on existing data. This makes the Nuvo-7166GC ideal for practical application in automated systems. In this case, the inference system applies existing data from the computer and software to a current situation in order to be able to react autonomously. A high-performance system, such as the Nuvo-7166GC is able to monitor a large number of machines simultaneously and without human intervention. The device can also be used for applications that include autonomous driving, the evaluation of weather data or inferring user behaviour for marketing purposes.
Six gigabit Ethernet interfaces are available, with three of these being capable of PoE with an overall output of 100 W. Four USB- 3.1 Gen 2 connections (10 Gbps) and 3.1 Gen 1 (5 Gbps), as well as several serial interfaces supporting fast data communication with additional peripherals. Two internal SATA ports (2.5“ SSD/HDD) with RAID support can host hard drives, and an M.2 slot can be used for NVMe-SSD or Intel Optane memory.
Application-specific I/O functions can be added through optional Mezzanine cards (MezIO modules with serial interfaces, digital I/O interfaces, LVDS output, CAN bus, DTIO or memory extension). In addition to the common DVI-D and VGA graphics outputs, a universal port exists, supporting 4K2K resolutions up to 4096 × 2304 pixels.
More information
Related news
Avnet SmartEdge Agile device in stock at Farnell element14
Low-cost IoT gateway is based on Raspberry Pi technology
New technology notes, tools and products help integrate AI solutions
Rugged and fanless IPC for edge AI computing
