Flexible GPU IP solutions that scale from wearables to the cloud
Performance Without Compromise
Imagination’s D-Series takes GPU density, efficiency and performance to a new level and adds innovative extras that help our partners succeed in competitive markets – whether that’s enabling automotive chip designers to achieve ASIL-B functional safety without overhead, or halving the area penalty of mobile ray tracing.
Consisting of four GPUs in fifteen off-the-shelf configurations, with D-Series it is easy to find the perfect parallel processor for your upcoming project, from augmented reality in smartglasses all the way up to autonomous vehicles.
The right fit
Whatever your design requirements, one of the fifteen off-the-shelf D-Series configurations can be tuned to fit your needs.
Developer ready
Software development on D-Series is made easy by Imagination’s feature-rich developer resources, performance analysis and debug tools, compute libraries and AI toolkits.
Tailor-made
D-Series contains general purpose graphics and compute accelerators as well as market-specific products that are designed from the ground up for the automotive or desktop markets.
Graphics + AI = Imagination
The flexible parallelism of Imagination’s D-Series GPUs enables them to handle a large language model as easily as an intricate game scene or even do both at the same time. As a device’s AI capabilities become its main differentiator, D-Series GPUs offer hardware designers programmable accelerator that scales from wearables right up to servers.
Meet the D-Series Family
![GPU icon](data:image/svg+xml,%3Csvg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 0 0"%3E%3C/svg%3E)
Imagination DXTP GPU
Imagination DXS GPU
IMG DXD GPU
IMG DXT GPU
Explore our D-Series Configurations
IMG DXT-72-2304 RT3
Technology: GPU
Use Cases: Data Centre, Desktop PC, Flagship mobile, Laptop
Imagination DXTP-64-2048 GPU
Technology: GPU
Use Cases: Desktop PC, Flagship mobile, Laptop, Premium mobile
Scalable Ray Tracing
Distributed Safety Mechanisms
Compute Libraries
The software includes OpenCL compute libraries (imgBLAS, imgNN, imgFFT) that boost GPU utilisation up to 80% for common workloads. Imagination’s reference toolkits further enhance performance through oneAPI applications or TVM TensorGraph inferencing.
D-Series Key Markets
Desktop
Ambitious new companies are identifying opportunities to create specialist cards optimised for use cases spanning from Android cloud gaming to desktop productivity. A feature-rich, high-performance and energy-efficient IP, such as DXD, accelerates their time to market and enables their engineers to focus on the elements of differentiation which will truly help them stand out.
Automotive
Imagination is the leading supplier of GPU IP into automotive cockpit and infotainment units and our highly flexible and secure technology can be found in the world’s most popular cars. DXS is our latest automotive offering and one that revolutionises the industry’s approach to functionally safe processing.
Mobile
Imagination’s PowerVR GPU is the original tile-smartphone GPU product, designed to deliver the ultimate in performance density and power efficiency. Our technology paved the way for the mobile gaming revolution and today, backed by our thriving ecosystem, our D-Series GPUs continue to deliver everything our customers need to push the boundaries of mobile graphics and compute.
Consumer Devices
The performance-dense DXT GPU brings the latest graphics and compute capabilities to the consumer market. Whether it’s in digital TVs, set-top boxes, streaming media, or the increasing number of smart home appliances, Imagination IP can be found in consumer products that need feature-rich, cost-effective, low-power, low-area solutions.
DXTP GPU IP boosts performance while extending battery life on power-constrained devices
Read the full press release“Zelos is integrating the advanced, power-efficient compute of Imagination DXTP into our upcoming chip. Imagination’s GPUs combine the performance of ultra-parallel processing with the flexibility that comes from a highly programmable architecture, making them the ideal platform for accelerating our AI models.”
Technical Director
/
