The high performance neural network inference accelerator
Neural networks are essential for complex signal processing and pattern recognition that lie behind many AI technologies. PowerVR Series3NX is a power-efficient embedded solution for hardware acceleration of neural networks. Thanks to key architectural enhancements the Series3NX benefits from a 40% performance boost over the previous generation, performing up to 10 tera operations per second (TOPS) from a single core.AI Processors
Bringing multi-core scalability to the embedded AI market
IMG B-Series GPU and PowerVR Series3NX NNA cores have been licensed for the latest RISC-V-based SoCs of Alibaba Group’s T-Head Semiconductor for AIoT applications.Learn More
Neural network acceleration for edge devices
Flexible bit-depth support
Lossless weight compression
Low power consumption
Putting the smart in smartphone
In mobile devices where a GPU is mandated, device manufacturers can pair a PowerVR Series9XE/XEP or 9XM/9XMP GPU with the Series3NX NNA in the same silicon footprint as a competing standalone GPU. Machine learning is now deployed in a wide variety of mobile applications, such as face recognition and verification, object recognition, image enhancement, style transfer and music tagging to name but a few. To support this, our Series3NX NNA cores deliver a paradigm shift in performance, while simultaneously reducing battery consumption over pure GPU solutions.
Security & surveillance
Augmented & Virtual reality
PowerVR Series3NX cores
The PowerVR Series3NX builds on our experience creating the groundbreaking PowerVR Series2NX neural network accelerator. The Series3NX range of cores, created from a single scalable architecture, delivers high-performance, low-power neural network acceleration in the most area efficient way, to meet a wide range of customer needs.
Download the PowerVR Series3NX overview
Find out how PowerVR GPU processors can boost innovation and user experiences for your products.