Aetina AI-MXM-H84A MXM module for edge AI available from Impulse Embedded
23 May 2023
AI-MXM-H84A – MXM Module with four Hailo-8 processors for edge AI available from Impulse Embedded
The AI-MXM-H84A from embedded solutions provider Aetina is now available from Impulse Embedded. The AI-MXM-H84A is an MXM embedded graphics accelerator for AI processing, to aid the development of deep learning and neural network processing at the edge.
Featuring four Hailo-8 edge AI processors, offering a substantial 104 tera-operations per second (TOPS) on a single embedded MXM graphics module, the AI-MXM-H84A is suitable for machine builders and AI solution architects targeting machine vision systems, autonomous vehicles and robotics.
What is Hailo-8?
Hailo-8 is the latest Application-Specific Integrated Circuit (ASIC) from Israeli AI hardware manufacturer Hailo.
The Hailo-8 Edge AI processor is the size of a penny and offers 26 TOPS AI inference performance with a typical power consumption of just 2.5W. ASICs, as the acronym suggests are manufactured for a specific application, this limitation of design flexibility is countered by lower production costs, lower power consumption and exceptional performance.
The architecture takes advantage of the core properties of neural networks, enabling edge devices to run deep learning applications and scale more efficiently and sustainably than similar AI solutions, whilst significantly lowering the overall cost.
What is MXM?
MXM, or Mobile PCI Express Module, was originally designed for use in laptops. It was intended to provide an industry-standard socket for graphics processors, which would allow the easy upgrade of GPU (Graphics Processing Unit) capabilities, without the need to upgrade the entire system or be tied to proprietary hardware for the lifetime of the device.
Aetina’s MXM modules are designed specifically for harsh environments. They are intended to be integrated into systems which themselves are tested and certified to handle vibration adequately. These modules are hardy and capable of being exposed to the impacts and tremors found in harsh, industrial environments at the edge. Due to its small-sized form factor, the high-performance MXM 3.1 Type B module can be easily integrated into a variety of embedded systems by developers and system integrators, to handle heavy AI inference workloads with low latency and without the increased power consumption of conventional discrete graphics cards.
More information available here.
Contact Details and Archive...