AI is everywhere, in everything, all at once
Whether you require smartness residing in the palm of your hand, under your TV, or in the industrial robots in your factory, we can help you achieve your vision. We enable this with our PowerVR neural network accelerators (NNAs) and graphics processing units (GPUs).
Our Neural Compute-SDK enables seamless deployment of AI acceleration on our hardware IP, either in isolation or combined. Our NNA provides maximum efficiency with a scalable architecture to enable a wide range of smart edge and end-point devices, from high-efficiency IoT products to high-performance robotaxis.
Driving the AI revolution
Embedded intelligence at low power
For markets such as security, autonomous systems and retail, our AI cores are enabling intelligence as close to the edge as possible – at low power and low cost. Engineered to accelerate specific neural network applications, the PowerVR NNA delivers unmatched efficiency and performance.
IMG Series4 is a groundbreaking neural network accelerator (NNA) that offers high performance at ultra-low latency, architectural efficiency, and safety features. This makes it ideal for large-scale commercial implementation and is already silicon-proven in the automotive industry enabling next-generation ADAS and autonomous driving.
PowerVR Series3NX is a fast, power-efficient embedded solution for hardware acceleration of neural networks. Series3NX is a family of scalable cores performing up to 10 tera operations per second (TOPS). Thanks to key architectural enhancements Series3NX benefits from a 40% performance boost over the previous generation.
The power of AI processing
AI in action
See a demo of what Imagination is doing with AI technology.
Explore more with Imagination
For more on AI, visit the Imagination blog where we apply our world-renowned engineering expertise to the latest news and insights.
Get in touch
Find out how PowerVR GPU and NNA solutions can boost innovation and user experiences for your products.