Vendor: Imagination Technologies Group Ltd. Category: GPU

Advanced graphics and compute acceleration on power constrained devices

Designed for efficiency.

Contact Provider Request Datasheet

Overview

Designed for efficiency. Programmed for performance.

Artificial Intelligence is transforming smartphones, bringing one-click photo enhancements, intelligent writing tools, and smart assistants into everyday use. But seamless AI integration shouldn’t come at the cost of great gaming, responsive interfaces, or battery life.

Imagination DXTP redefines graphics and compute acceleration for smartphones and other power-constrained devices. Designed for exceptional efficiency, it delivers the performance needed to run AI, gaming, and user interfaces smoothly and continuously, all day long.

The ultimate D-Series product

Imagination DXTP is the ultimate product in D-Series, combining many of the PowerVR architecture’s latest graphics, compute and efficiency features into one single offering. Graphics performance is boosted by fragment shading rate and 2D Dual-Rate Texturing, and AI tasks run faster thanks to better scheduling and more local memory.

On top of this, Imagination DXTP adds a wide array of micro-architectural improvements that together boost power efficiency by up to 20% over its D-Series predecessor, IMG DXT.

Asynchronous multitasking

As the most advanced parallel processing architecture for power-constrained devices, Imagination GPUs can be deployed to accelerate either graphics or AI tasks – or both at the same time!

Imagination DXTP’s asynchronous processing of different task types – like rendering the smartphone’s UI and accelerating an LLM – makes it a very flexible silicon investment.

Unlock real performance

Highly optimised OpenCL compute libraries (imgNN, imgFFT, imgBLAS) that help software developers achieve up to 80% GPU utilisation for common compute workloads are available for use with Imagination DXTP and ship alongside reference kits that accelerate the porting of existing code onto Imagination-based hardware.

A developer's dream

Imagination DXTP is supported by Imagination’s well-established software ecosystem and award-winning developer tools. Through the PowerVR Developer Portal, programmers can download low-level performance, analysis, debugging and trace capturing tools along with guides and examples, and access expert support through the developer forum.

Key features

  • Next Level Efficiency: Microarchitectural changes deliver 50% more geometry performance and better sustained performance compared to its predecessor, IMG DXT. Overall performance efficiency is boosted 20%.
  • Optimised for Compute: With a memory structure configured for super-fast compute processing coupled with accelerated scheduling of compute workloads, Imagination DXTP is optimised for AI.
  • Compute Software: Imagination DXTP ships with a set of highly optimised OpenCL Compute Libraries (imgNN, imgBLAS, imgFFT) that boost performance up to 4x compared to open source libraries and integrate into popular open AI programming frameworks.
  • Hardware-based Virtualisation: Imagination's hardware based virtualisation solution supports up to eight separate operating systems on a single GPU, each fully isolated in memory, for secure multitasking – including mixed criticality workloads.

Benefits

  • Headline features
    • Dual-Rate FP16
    • OpenCL Compute Libraries
    • Fragment Shading Rate
    • 2D Dual-Rate Texturing
    • Pipelined Data Masters
    • RISC-V Firmware
    • ASTC HDR Support
    • HyperLane Virtualisation
  • API Support
    • Vulkan 1.4 (support coming in 2025)
    • OpenGL 4.6 via Zink
    • OpenGL ES 3.x/2.0/1.1 + Extensions
    • OpenCL 3.0 FP
  • OS Support
    • 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
    • 2,048 FP32 FLOPs/Clock
    • 4,096 FP16 FLOPs/Clock
    • 8,192 DOT8 NN Ops/Clock
  • Pixels per Clock
    • 64 ppc Bilinear 3D Textured
    • Up to 128 ppc 2D Dual Rate Mode

Applications

  • Desktop PC: Popular gaming titles and general productivity workloads on mainstream 1080p PCIe devices.
  • Flagship mobile: Performance-centric devices that deliver intricate mobile game graphics and intelligent content creation without any compromise.
  • Laptop: Efficiency focused general productivity and casual gaming on portable PCs and professional tablets.
  • Premium mobile: Efficient devices that handle popular graphics intensive applications while maintaining a focus on battery management.

Files

Product Sheet Download

Note: some files may require an NDA depending on provider policy.

Specifications

Identity

Part Number
IMAGINATION DXTP-64-2048 GPU
Vendor
Imagination Technologies Group Ltd.

Provider

Imagination Technologies Group Ltd.
HQ: UK
At Imagination, we create and license a range of multimedia and communications processors needed to create SoCs (Systems on Chips) that power mobile, consumer, automotive, enterprise, infrastructure, IoT and embedded electronics. We are a strong, independent IP company, owned by Canyon Bridge, a Silicon Valley-based private equity firm. We pride ourselves on our consistent focus on creating win-win products in conjunction with our customers. Our powerful, cutting-edge designs are driving the digital revolution forward by enabling our partners to build world-changing electronics.
Contact Imagination Technologies Group Ltd.

Learn more about GPU IP core

Tape-out Risk in the Age of Edge AI: The Case for GPU IP

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.

What Does a GPU Have to Do With Automotive Security?

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.

How Alternate Geometry Processing Enables Better Multi-Core GPU Scaling

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.

NVIDIA GPU Confidential Computing Demystified

In this paper, the authors aim to demystify the implementation of NVIDIA GPU-CC system by piecing together the fragmented and incomplete information disclosed from various sources.

Frequently asked questions about GPU IP cores

What is Advanced graphics and compute acceleration on power constrained devices?

Advanced graphics and compute acceleration on power constrained devices is a GPU IP core from Imagination Technologies Group Ltd. listed on Semi IP Hub.

How should engineers evaluate this GPU?

Engineers should review the overview, key features, supported foundries and nodes, maturity, deliverables, and provider information before shortlisting this GPU IP.

Can this semiconductor IP be compared with similar products?

Yes. Buyers can compare this product with similar semiconductor IP cores or IP families based on category, provider, process options, and structured technical specifications.

×
Semiconductor IP