IMAGINATION

EXD-8-256 GPU

Graphics, compute and AI all on one processor, with one software stack

Key Features

4x Matrix Acceleration

Significant performance gains for compute and AI workloads using new hardware that is embedded alongside the arithmetic logic units, sharing the same register storage.

Low Precision Number Format Support

Capable of running edge-friendly AI models using FP32, FP16, BF16, INT8, FP8, MXFP8, FP4, MXFP4 data formats.

Power Efficiency Boost

The new Burst Processors pipeline guarantees the execution of blocks of operations and stores intermediary data inside the local registers, reducing unnecessary data traffic and boosting battery life.

Neural Rendering

The new Matrix Accelerator can be applied to graphics workloads in support of popular neural techniques like upsampling and denoising. A new Neural Super Resolution model is available for efficient upscaling.

HMI – Entry Level

Intuitive in-car experiences centred on a smooth and responsive graphical user interfaces on a 1080p screen.

Mobile – Mainstream

Casual gaming, internet browsing and social media applications on competitive devices that keep performing all day long.

Set top box

Highly efficient content streaming experiences for screens from 1080p to beyond 4K.

Smart home

Devices to provide comfort and efficiency in the home through streamlining tasks and enhancing convenience.

Full Features & Specs

Headline features
  • Matrix Accelerator
  • Burst Processors
  • Low precision number format support
  • Neural Super Resolution
  • Compute SDK
  • DirectX 12 FL11_0
  • Up to 16 VMs using HyperLane
  • Multi-core scaling available
  • Ray tracing optional

API Support

  • Vulkan 1.4
  • OpenGL 4.6 via Zink
  • OpenGL ES 3.x/2.0/1.1 + Extensions
  • OpenCL 3.0 FP
  • DirectX 12 FL11_0

OS Support

  • Windows 11
  • Linux Consumer
  • Linux X.org
  • Android

Bus Interface

  • AXI
  • ACE-Lite

Compression

  • PVRIC5 Lossless and Lossy Framebuffer Compression
  • ETC and ASTC LDR and HDR Support

Performance

  • 256 FP32 FLOPs/Clock
  • 512 FP16 FLOPs/Clock
  • 4,096 DOT8 NN Ops/Clock

Pixels per Clock

  • 8 ppc Bilinear 3D Textured
  • Up to 16 ppc 2D Dual Rate Mode

INTERESTED?

Book a meeting with our sales team to work with us and learn more about our GPU IP.

Contact our sales team