E-Series: The First Step Towards Converged Acceleration
The newly refreshed white paper on Imagination’s latest GPU IP.
E-Series, announced in 2025 and with first silicon expected by the end of 2026, marks a new era for edge system design. E-Series combines graphics, compute and AI on one flexible architecture and one programmable software stack. With up to 32 TOPS Int8 per core at 1GHz (4× the raw compute performance of D-Series) and the ability to run graphics and AI workloads concurrently, E-Series provides system designers with:
- Advanced graphics acceleration for the latest games and user interfaces.
- A flexible co-processor that can offload dedicated AI processors at peak times.
- A general-purpose accelerator that can be trusted to run the operators of the future as AI models evolve.
This paper includes chapters on:
- The convergence of edge processors.
- The E-Series GPU architecture.
- How E-Series delivers edge-level power efficiency.
- Real-world performance data for E-Series across gaming, neural rendering and language models.
- A look at the E-Series software stack.
Interested in E-Series? Try These…
WEBINAR: The Convergence of Edge Accelerators
Explore a new approach to processor design: a single architecture capable of accelerating graphics, compute and AI workloads on the same silicon, through a common software stack.
WEBINAR: Porting, Analysing & Optimising AI Models onto Edge GPUs
In this session, we’ll walk through the end-to-end process of porting, analysing and optimising modern AI models for edge GPUs, using Qwen 3.5 as a practical example.
WEBINAR: Creating A Hardware-Optimised Neural Rendering Solution
In this session, we’ll explore how hardware and software can be co-designed to create more efficient neural rendering solutions.
