Overview
The XS family of GPUs, part of our PowerVR Automotive offerings, are a new class of cores for ADAS acceleration and safety-critical graphics workloads – the industry’s first ISO 26262-capable GPU IP. Derived from a new safety architecture they feature unique mechanisms for secure execution of compute and graphics.
XS GPUs cover a wide of performance points, from the smallest failsafe safety-render core to the highest performance solutions for the rapid execution of ADAS algorithms. They are created to deliver a tailored configuration aligned to automotive market needs, with enhanced performance for key workloads and applications, alongside bespoke features for the automotive market.
The cores feature a toolbox of safety mechanisms for compute and graphics and offer a range of solutions for transient and permanent fault detection. These include active mechanisms to secure the correct execution of workloads and ensure the secure delivery of data throughout an SoC, such as our patented Tile Region Protection.
Learn more about GPU IP core
Imagination GPU Driver 26.1 introduces key Vulkan advancements, including support for Android 17, enhancing performance and developer capabilities for modern graphics workloads.
Explore how the SpacemiT K3 processor combines RISC-V CPUs and GPUs to revolutionize high-performance SoCs for AI-driven applications. Discover the future of computing.
A full SoC tape-out at 5nm approaches $400M in fully loaded, non-recurring engineering and mask costs. At 3nm, estimates push past $600M. Every IP block on that die is a commitment to a set of assumptions about what the silicon will need to do. In AI, those assumptions have a shorter shelf life than they used to.
Discover why the future of edge GPU design focuses on power efficiency over area, driven by thermal constraints at sub-2nm nodes. Learn about architectural shifts and Imagination's innovative solutions.
The automotive industry is undergoing the most significant transformation since the advent of electronics in cars. Vehicles are becoming software-defined, connected, AI-driven, and continuously updated. This evolution brings extraordinary new capability – but it also brings greater levels of cybersecurity and functional-safety risks.
Scaling GPU performance across multiple cores sounds simple in theory: add more cores, get more performance. In practice, it’s one of the toughest challenges in graphics architecture. While some workloads scale well thanks to their independent nature, some workloads, especially geometry processing, introduce order dependencies that make linear performance scaling a tricky problem to solve for every GPU architecture in the industry.