DEVELOP YOUR EDGe
Build better applications faster with the innovative PowerVR SDK
An extensive ecosystem of tools and support
PVR Tools
Create PowerVR applications for iOS, macOS®, Linux®, Windows®, WebGL™, and Android™. Use examples to learn or as a starting point for your own applications. Make use of the PowerVR Framework – a cross-platform and cross-API framework that acts as a scaffold for you to build your own rendering or game engine.
Documentation
Latest forum posts
The PowerVR developer forum is great place to start asking questions and getting answers from our PowerVR developer technology team and other like-minded developers.
| Topic | Users | Replies | Views | Activity |
|---|---|---|---|---|
| Zero-Copy v4l2 capture |   | 2 | 37 | Sep 15 |
| KTX to PNG is not working |    | 14 | 115 | Sep 14 |
| glClientWaitSync: sync is not the name of an existing Sync Object |  | 4 | 62 | Sep 11 |
| Converting KTX -> PNG |    | 3 | 212 | Sep 8 |
| How can i run for loop parallel in poverVR GPU |  | 10 | 108 | Aug 28 |
| PVRTexTool major flaws |    | 8 | 1218 | Aug 25 |
Develop neural network applications on PowerVR GPUs
Our neural network SDK for artificial intelligence makes it as easy and efficient for developers to create convolutional neural networks on our hardware. To that end, we have provided both an API and an CLDNN SDK, and also provided an image for flashing onto an Acer Chromebook R-13 for hardware development.
Related blog articles
What is PVRTune Complete?
PVR Tune Complete highlights exactly what the application is doing at the GPU level, helping to identify any bottlenecks in the compute stage, the renderer, and the tiler.
Vulkan synchronisation and graphics-compute-graphics hazards: Part 2
In this article, we are referring to the various problems we encountered when it comes to sandwiching compute tasks during graphics processing in Vulkan®. To find out exactly what we’re talking about be sure to read part one first.
Vulkan synchronisation and graphics-compute-graphics hazards: Part I
How do you mix and match rasterisation and compute in a modern GPU? In modern rendering environments, there are a lot of cases where a compute workload is used during a frame. Compute is generic (non-fixed function) parallel programming on the GPU, commonly used for techniques that are either challenging, outright impossible, or simply inefficient to implement with the standard graphics pipeline (vertex/geometry/tessellation/raster/fragment).
