E-Series GPU IP

Overview

E-Series GPU IP delivers fast and flexible parallel compute that scales from wearables to the cloud.

E-Series GPU IP breaks through the throughput, memory and power barriers that surrounded AI at the edge.

The capabilities of E-Series will trigger a rethink in edge system design. Artificial intelligence is pervasive but compute-intensive, and its algorithms remain mercurial. Over-investment in specialist accelerators limits hardware’s ability to adapt to the future. E-Series delivers the performance required for next-generation AI applications across mobile, automotive, desktop and consumer markets, all while retaining the flexibility and programmability synonymous with GPU acceleration.

FROM 2 TO 200 TOPS AI PERFORMANCE

E-Series represents a new era of GPU IP with the introduction of a lot of dense, deeply integrated acceleration for power-efficient AI operations – up to 4x more than Imagination D-Series GPU IP.

This transforms the classic Imagination GPU Core into a highly capable Neural Core that scales in performance up to 200 TOPS (INT8/FP8) and transforms the face of edge intelligence.

Key Features

  • ULTIMATE EFFICIENCY: E-Series GPUs boost graphics and AI power efficiency by 35% over the previous generation via Imagination’s new Burst Processors technology.
  • AI FOR EVERYONE: E-Series Neural Cores can scale from 2 – 200 TOPS (INT8) while retaining the area efficiency needed for cost-effective AI at the edge.
  • MADE FOR DEVS: The full performance of E-Series can be unlocked via an easy-to-use software stack with compute libraries, highly optimised graph compilation and advanced developer tooling.

Benefits

  • SMARTER, LEANER, MORE EFFICIENT: E-Series new Burst Processors technology works with Imagination’s graphics and AI pipelines to lower average GPU power consumption by 35% compared to D-Series. The technology reduces data movement within the GPU, which in turn lowers power consumption and boosts GPU utilisation, as it frees up memory to keep the compute units fed.
  • BUILT FOR PROGRAMMABILITY:  Imagination’s software stack provides developers with an easy-to-use solution based on open standards for porting their code to Imagination-based hardware and optimising performance. Highly optimised OpenCL compute libraries and compilers enhance GPU efficiency, and our advanced tooling gives developers clear insights into application performance.
  • FLEXIBLE BY DESIGN: E-Series has the flexibility to run advanced graphics workloads, AI workloads, or both at the same time – ideal for multi-domain controllers or the complex processors inside today’s smartphones. Imagination’s hardware-based virtualisation technology supports up to sixteen virtual machines on E-Series GPUs.

Block Diagram

E-Series GPU IP Block Diagram

Video

E-Series: Why are GPUs perfect for AI?

Dennis Laudick, VP of Segment and Marketing at Imagination discusses why Imagination GPUs are essential for AI. Imagination’s E-Series GPU IP shatters performance, memory, and power barriers for AI at the edge. Designed to handle the demands of next-gen AI across mobile, automotive, desktop, and consumer markets, E-Series enables flexible, future-proof edge system design without over-reliance on fixed-function accelerators.

Applications

  • Computing & Desktop
  • Automotive Solutions
  • Smartphone & Mobile
  • Consumer Electronics

Technical Specifications

Availability
Available from Autumn 2025.
×
Semiconductor IP