Edge AI starter development kit combining ZIA C3 SoM, a platform for developing edge devices equipped with AI functions, and a carrier board with interfaces such as USB and Ether.

DMP’s AI processor IP ZIA DV720 is implemented in Xilinx® Zynq® MPSoC FPGA. The computing unit supporting FP16-precision※1FP16 precision
In general, using a small floating number has the advantage of reducing processing time and power consumption, but decreases precision. floating point arithmetic as standard, it can be used without re-training AI models trained on PCs and cloud servers. Maintaining high inference precision, this AI FPGA module is suitable for AI systems that require high reliability such as autonomous driving and robotics.

The DV700 series provide development environment (SDK / Tool) accompanying the IP core. The development environment (SDK / Tool) supports the standard AI development framework (Caffe、Keras、TensorFlow), customers can easily perform AI and deep learning inference processing with the DV700 series by preparing a model that supports the AI development framework.

* Please refer to GitHubfor details of development environment (SDK / Tool).

ZIA C3 is designed with industrial specifications for key components and temperature assurance range. Equipped with an FPGA that has a proven track record of supplying industrial equipment, it supports long-term stable supply.

ZIA C3 SoM carries a Xilinx® FPGA whose hardware logic can be rewritten, which makes it possible to mount the latest DMP AI processor. Being able to follow the latest AI technology, which is rapidly evolving, from the hardware level including AI processors, users can enjoy a long-term use.

In general, using a small floating number has the advantage of reducing processing time and power consumption, but decreases precision.