PowerVR GPU Compute
Imagination has been one of the early pioneers of mobile GPU compute, being the first mobile IP vendor to achieve OpenCL conformance on its PowerVR SGX GPU IP family. Our latest PowerVR ‘Rogue’ GPUs provide comprehensive support for compute APIs such as OpenCL 1.2, OpenGLES 3.1 Comptute Shaders and RenderScript. These APIs are revolutionizing the way OEMs and third-party software developers design mobile apps, enabling use cases that were not previously possible with a CPU alone in emerging areas such as computational photography, video and embedded computer vision.
To encourage wider adoption of GPU compute in mobile, Imagination is inviting GPU compute engineers to download tools and documentation that help enable efficient zero-copy heterogeneous computing on a number of selected devices.
Series of Articles on Heterogeneous Compute
You can use the following menu to help you navigate through every article published in this heterogeneous compute series:
- A primer on mobile systems used for heterogeneous computing
- A quick guide to writing OpenCL kernels for PowerVR Rogue GPUs
- Increasing performance and power efficiency in heterogeneous software
- The PowerVR Imaging Framework for Android
- Heterogeneous compute case study: image convolution filtering
- Deep dive: Implementing computer vision with PowerVR
- Supported zero-copy flows inside the PowerVR Imaging Framework
- The PowerVR Imaging Framework camera demo
- Measuring GPU compute performance
- Imagination’s smart, efficient approach to mobile compute
- The complete glossary to heterogeneous compute on PowerVR
Downloads for platforms that fully support the PowerVR Imaging Framework
The ASUS Zenfone 2 (ZE551ML) supports the PowerVR imaging framework Android. This framework enables the GPU to be deployed as a flexible and efficient compute engine for accelerating many computational photography and computer vision algorithms, while tightly integrated with hardware components such as an ISP (Image Signal Processor) for acquiring the image sensor data, a VDE (Video Decoder and Encoder) for codec acceleration, and a CPU for executing general-purpose code and high-level heuristics.
Downloads for other Series 6 platforms
The first Android tablets to be released with a PowerVR Series6 GPU are the Dell Venue 7 (Intel Atom Z3460) and Venu 8 (Intel Atom Z3480). Both of these Atom devices incorporate the PowerVR G6400 GPU.