Technical Profile
Autonomous Driving
- With the rise of advanced technology, the appearances of cutting-edge vehicles have been sprung up recently. Out of all the burgeoning vehicles, driverless vehicles have gone viral the most. Autonomous Vehicles (AV) could contribute to making future mobility more efficient, safer and cleaner. However, the road to the success is not always effortless for driverless vehicles; it requires the support of lots of technologies. Artificial Intelligence (AI) and Machine Learning (ML) is the backbone of the success of driverless vehicles, also with sensors and the computing unit that handles the main control for the self-driving vehicles, such as converting throttle input to torque requests, safety system monitoring, control loops, and power limiting. To satisfy the rapid increase in the operation speed of the sensors and the accumulated data, powerful GPGPU brings high speed, low latency, and more complex performance. Plus, while driving on uneven terrain, the system must be anti-vibration to protect the machine from damage. 7Starlake uses MXM mezzanine type structure to enhance the strength of ruggedness. Moreover, IV320RH also equips 10GbE Uplink network which is wide bandwidth and can support for high-resolution video processing, to deliver low latency transmission.
- Design to Meet EN50155 Rolling Stock
EN 50155 is a regional standard covering electronic equipment used on rolling stock for railway applications. The standard covers aspects of this electronic equipment, including temperature, humidity, shock, vibration, and other parameters. IV320RH is design to comply with EN50155 standard that can provide reliable performance under variety of power supply conditions, such as voltage variations, power interruptions, and power supply changeover.
Full IP65 Sealed Enclosure
The dirt, dust, and moisture in the outdoor environment can damage the system, and as the air moves from high humidity or dusty environments, it might lead to the failure of system operation. IV320RH is full IP65 sealed enclosures which are designed to meet the various requirements of engineers when designing electrical and electronic systems which have to be protected. And protect against low pressure water jets from any direction, as well as condensation and water spray. It’s suitable for most outdoor enclosures.
Ready for IoT
Wide 2.5 Gigabit Data Uplink Bandwidth Ideal for IoT
Artificial Intelligence and Machine Learning request large amount of data and fast data transmission, 2.5GbE uplink can support wide bandwidth for AI edge computing and led to less bottlenecks and low latency and improve work efficiency, ensuring peak network efficiency and performance for autonomous driving.
Flexible I/O Port and Expansion Slot
AI edge computer focuses on easy deployment for great variety applications; IV320RH is equipped with extensive I/O ports including 1x DVI, 2X Giga LAN, 2x USB, 1x COM port, especially the I/O is installed with M12 waterproof connector, ready for harsh environment. Furthermore, IV320RH is equipped with 2x Full-size mini PCIe and 1x 2280 M key expansion slot that enable the installation for the connectivity of data transmission of diverse data-intensive applications.
MXM Mezzanine Type Structure to Withstand Uneven Terrain
- Accordion content 2.
While driving on uneven terrain, the system should be anti-vibration to protect the machine from damage; 7Starlake uses MXM mezzanine type to make the ruggedized structure for harsh environment. IV320RH is driven by NVIDIA® Quadro RTX A4500/A1000 MXM GPU with 5888/2,560 CUDA Cores 16GB/4GB/8GB GDDR6 high memory configurations. The GPU is arranged with MXM 3.1 module providing efficient GPU performance. With five channel outputs, including 4x DisplayPort 1.4a, 1x DVI, IV320RH supports various application, 4K at 120Hz or 8K at 60Hz with 10-bit color depth. RTX A2000 MXM GPU improves data-transfer speeds from CPU memory for data-intensive tasks with support for PCI Express Gen 4.
Intel CPU Features
To realize Edge AI technology, IV320RH is driven by Intel® 13th generation Raptor Lake which builds upon by increasing core count (primarily E-Cores), expanding L2 cache memory, and raising clock speeds to ultimately enhance processor performance. This results in an impressive configuration of up to 8 P-Cores and 16 E-Cores, culminating in a total of 24 cores within flagship offerings.
The x86 hybrid architecture consists of the following two core types, with the CPU activating different cores based on various usage applications to achieve high efficiency and low power consumption:
P-Core: Adopts the Golden Cove architecture which is suitable for high-performance and gaming applications.
E-Core: Adopts the Gracemont architecture which is suitable for low-power and multitasking applications.
