Enabling Intelligence in battery-powered IoT Devices
Intelligent devices that last for years on a battery
GreenWaves’ pioneering GAP8 IoT application processor enables the cost-effective development, deployment and autonomous operation of intelligent devices that capture, analyze, classify and act on the fusion of rich data sources such as images, sounds, radar, infra-red or vibrations for years on a battery. GAP8 delivers the computational and power agility necessary to integrate sophisticated signal processing and artificial intelligence into small, battery operated devices living on the very edge of the network.
GAP8 – best-in-class for AI on battery-operated devices
GAP8 is uniquely optimized to execute a large spectrum of image and audio algorithms including convolutional neural network (CNN), with extreme energy efficiency, thanks to an integrated 8-core computational cluster combined with a convolution hardware accelerator.
Vector units, intrinsics and proprietary instruction set extensions help the 8 cluster cores execute faster than traditional parallel processor architecture without writing a single line of assembly code.
Fully programmable, RISC-V based PULP parallel architecture enables to cope with the rapidly evolving state-of-the-art in machine learning algorithms.
People / Object counting
GAP8 is uniquely designed to adapt the power consumption to the needs of the application. GAP8 incorporates state of the art dynamic voltage and frequency scaling and automatic clock gating keeping awake only the elements of the component necessary to service the current workload. GAP8 has an extremely low standby power consumption and ultra-fast wake up and power state transitions enabling it to consume energy only when required.
Consuming energy only when required
Ultra-fast wake up
Low stand-by power consumption
Dynamically adjustable frequency and voltage
Absolute low compute point
All the components of GAP8 are designed to consume as low as possible power and to be powered off or clock gated while not in use. This means that GAP8 delivers significant compute ability at absolute low energy usage. GAP8 enables to execute machine learning algorithms at power consumption levels compatible with years of battery-powered operation.
Profiler A visualization tool for profiling and debugging GAP applications https://youtu.be/6NgVRBZkyF4 Profiler is a part of our GAP SDK and used with GVSOC, our Full System SoC Simulator. Profiler [...]