Aetina launches its AIB-MR1A-A1 AI Inference Platform

“The demand for flexible and energy-efficient ARM edge devices with AI accelerators is rapidly escalating. The AIB-MR1A-A1 addresses this demand.”

by

Aetina has unveiled its AIB-MR1A-A1 Artificial Intelligence (AI) Inference Platform, which forms part of its DeviceEdge Series. This solution will be the first of an ARM-based architecture that features an AI module.

Powered by a Rockchip RK3588 ARM processor, combined with an M.2 228- AI accelerator, the solution can manage up to 32 live or pre-recorded video streams. Applications including the monitoring of security at large venues are perfect for this solution as it offers improved cost-effectiveness, flexibility, and enhanced performance.

“The demand for flexible and energy-efficient ARM edge devices with AI accelerators is rapidly escalating,” said Jackal Chen, Senior Product Manager at Aetina. “The AIB-MR1A-A1 addresses this demand by providing a market-ready industrial-grade AI platform and customised services that depart from traditional x86 architectures, enabling diverse edge AI computing applications.”

Key features of the AIB-MR1A-A1 AI Inference Platform:

  • Incorporates the Rockchip 8-core 64-bit ARM processor RK3588 with a PCIe Gen3 x4 M.2 2280 M-Key slot, supporting its AI accelerators.
  • Ability to manage 32 live video streams at 1080P, 30 FPS.
  • Enhanced energy efficiency in video and image processing, including real-time video analytics and 8K video encoding and decoding.
  • Boasts AI inference performance up to 26 TOPS by integrating an AI accelerator.
  • Offers comprehensive customisation services from chip-down design, BSP customisation and thermal design to wide temperature testing and software integration.

The edge AI solutions provider collaborates with AI processor partners DEEPX and Hailo, to provide a selection of M.2 AI accelerator options. This allows developers to easily switch the AI module without having to modify the hardware platform.