Imagination Blog

Turning Conv2D into a Practical GPU Compute Pattern

AI GPU

5 min read

Convolution is one of the foundational operations in modern machine learning, but it is also a...

From Prototype to Performance: Optimizing OpenCV Resize on Volcanic GPUs

AI GPU

6 min read

This is a practitioner-oriented prototype case study. It focuses on implementation and optimization...

voice assistant on phone

LLM Performance and Acceleration on PowerVR - Part 2

AI GPU

3 min read

Part 2: Recap Welcome to the second part of this two-part blog series about how to accelerate large...

From graphics to AI, and back again

GPU

4 min read

Forty-five years ago, my father was studying radio engineering in the Soviet Union. The transistors...

Running OpenCode with llama.cpp and Qwen 3.5 on E-Series

AI Software

5 min read

Edge AI gets more interesting when a model does more than answer prompts. It plans, calls tools,...

Imagination & Chiplets: Scaling System Design Beyond the Monolithic SoC

Automotive GPU

4 min read

For many years, improvements in SoC performance came from process scaling and integrating more...

How To Scale AI Arithmetic Efficiently

AI GPU

2 min read

AI workloads feature matrix multiplications in a variety of number formats, such as INT8, FP4, FP8,...

Scaling the open-source PowerVR Vulkan driver to new GPU architectures

GPU Developers Open source

4 min read

This article summarizes the foundational work we’ve been doing to support multiple GPU...

Unlocking GPU Performance: An Introduction to PVRTune

Developers

2 min read

Watch: An Introduction to PVRTune (13 mins) When you start analysing performance on real hardware,...