Summary of AAEON LAUNCHES M.2 AND MINI-PCIE BASED AI ACCELERATORS USING LOW-POWER KNERON NPU
Aaeon released three M.2 and mini-PCIe AI Edge Computing Modules based on Kneron’s low-power KL520 AI SoC (dual Cortex-M4 + NPU), offering 0.3 TOPS at ~0.5–0.9W. Targeted at IoT, smart home, security, and mobile devices, the modules (M2AI-2280-520, M2AI-2242-520, Mini-AI-520) provide USB host connectivity, UART and JTAG debug, support ONNX/TensorFlow/Keras/Caffe and models like YOLO, MobileNet, Vgg16, and operate 0–70°C for on-device inference to reduce latency and enhance privacy.
Parts used in the AI Edge Computing Modules:
- Kneron KL520 AI SoC (dual Cortex-M4 + NPU)
- M.2 B-Key 2280 form-factor module (M2AI-2280-520)
- M.2 2242 form-factor module (M2AI-2242-520)
- mini-PCIe form-factor module (Mini-AI-520)
- USB interface signals to host
- UART debug interface
- JTAG debug interface
- Power supply supporting 0.5W to 0.9W operation
Aaeon’s M.2 and mini-PCIe “AI Edge Computing Modules” are based on Kneron’s energy-efficient, dual Cortex-M4-enabled KL520 AI SoC, which offers 0.3 TOP NPU performance on only half a Watt. by Eric Brown @ linuxgizmos.com
Aaeon took an early interest in edge AI acceleration with Arm-based Nvidia Jetson TX2 based computers such as the Boxer-8170AI. More recently, it has been delivering M.2 and mini-PCIe form-factor AI Core accessories for its Boxer computers and UP boards equipped with Intel Movidius Myriad 2 and Myriad X Vision Processing Units (VPUs). Now, it has added another approach to AI acceleration by launching a line of M.2 and mini-PCIe AI acceleration cards built around Kneron’s new KL520 AI SoC.
Aaeon is taking orders for three KL520-based AI Edge Computing Modules cards aimed at IoT, smart home, security, and mobile devices:
- M2AI-2280-520 — M.2 B-Key 2280
- M2AI-2242-520 — M.2 2242
- Mini-AI-520 — mini-PCIe
Aaeon’s 0 to 70°C tolerant AI Edge Computing Modules operate at 0.5W to 0.9W. There do not appear to be any functional differences between the three modules, which all supply UART and JTAG debug interfaces and communicate with the host processor via USB signals. The modules support acceleration for ONNX, TensorFlow, Keras, Caffe frameworks with models including Vgg16, Resnet, GoogleNet, YOLO, Tiny YOLO, Lenet, MobileNet, and DenseNet.
The KL520 AI SoC combines dual Cortex-M4 MCUs with Kneron’s Neural Processing Unit (NPU) chip, which can be licensed separately. The power-efficient KL520 supports co-processor use, as deployed in Aaeon’s AI Edge Computing Modules, in scenarios that would typically connect to an embedded Linux computer. The SoC can also be used as a standalone, AI-enabled IoT node in applications such as smart door locks.
The KL520 AI SoC is designed to accelerate general AI models such as facial and object recognition, gesture detection, and driver behavior for AIoT applications including access control, automation, security, and surveillance. It can also be used to monitor consumer behavior in retail settings – a trend that could push even more customers to shop online. Aaeon notes, however, that the solution enhances privacy — and reduces latency — because edge AI devices do not require a cloud connection.
Read more: AAEON LAUNCHES M.2 AND MINI-PCIE BASED AI ACCELERATORS USING LOW-POWER KNERON NPU
- What SoC do the AI Edge Computing Modules use?
They use Kneron KL520 AI SoC with dual Cortex-M4 MCUs and an NPU. - Which module form factors are available?
Aaeon offers M2AI-2280-520 (M.2 B-Key 2280), M2AI-2242-520 (M.2 2242), and Mini-AI-520 (mini-PCIe). - How much power do the modules consume?
The modules operate at approximately 0.5W to 0.9W. - What temperature range do the modules support?
They support an operating range of 0 to 70°C. - How do the modules connect to a host processor?
They communicate with the host via USB signals and provide UART and JTAG debug interfaces. - Which AI frameworks and models are supported?
They support ONNX, TensorFlow, Keras, and Caffe frameworks and models including Vgg16, Resnet, GoogleNet, YOLO, Tiny YOLO, Lenet, MobileNet, and DenseNet. - What NPU performance does the KL520 offer?
The KL520 NPU offers about 0.3 TOPS performance while consuming roughly half a watt for the NPU. - Can the KL520 be used standalone?
Yes, the KL520 can be used as a standalone AI-enabled IoT node as well as a co-processor with an embedded Linux computer. - What application areas are targeted by these modules?
They target AIoT applications such as access control, automation, security, surveillance, gesture detection, driver behavior monitoring, and retail consumer behavior monitoring. - How does on-device inference benefit privacy and latency?
Edge AI devices reduce latency and enhance privacy because they do not require a cloud connection for inference.
