System on Chip (SoC)
Powerchip Group produces AI SoC processors powered by our proprietary technology that accelerates neural network models making possible applications such as face detection and recognition, body and object detection, and gesture control in embedded devices.
RISC-V or ARM Cortex M series CPUs can operate as a host or companion AI co-processor enabling edge AI on devices like smart locks, security cameras, drones, smart home appliances, and robotics.
Visual AI Solutions
Our DRAM based platform supports many visual recognition algorithms that can recognize human faces, bodies, gestures, objects, and scenes all “on-device”, to power applications such as secure payments, door security, facilities management, retail management, and traffic management.
The key to effective edge AI computing is balancing size, performance, and power usage. The advantage of DRAM is the structural simplicity of its memory cells: only one transistor and a capacitor are required per bit, compared to four or six transistors in SRAM. This allows DRAM to reach very high densities, making DRAM much cheaper per bit and capable of supporting larger size models in memory with extremely high I/O bandwidth.
Video Neural Network Accelerator (VNNA) Engine
One implementation of the AIM platform features a video neural network accelerator engine that has been designed for edge devices. This engine provides high computing performance with low power consumption and wide data bandwidth, achieving real-time semantic segmentation at 60fps.
This technology can be applied to automotive, smart home, smart surveillance, mobile, and other devices that have a high performance computing requirement at low power consumption.