PowerVR GPU is first to pass OpenVX 1.1 conformance

19th December 2016

Enaie Azambuja

0 0

Imagination Technologies announces that a PowerVR GPU is the first to achieve Khronos OpenVX 1.1 conformance. With OpenVX, developers can run fully optimised vision algorithms on the highly parallel, power-efficient PowerVR GPUs that are at the heart of many of the world’s mobile, automotive and embedded devices. OpenVX is an open, royalty-free standard for cross platform acceleration of computer vision applications.

It enables performance and power-optimised computer vision processing, especially important in embedded and real-time use cases such as face, body and gesture tracking, smart video surveillance, advanced driver assistance systems (ADAS), object and scene reconstruction, augmented reality, visual inspection, robotics and more.

Chris Longstaff, Imagination’s senior director of product and technology marketing for PowerVR, says: “Imagination supports OpenVX including the Neural Network Extension across our PowerVR GPUs and vision IP offerings.

Developers can already achieve remarkable performance when running state of the art convolutional neural network (CNN) algorithms on PowerVR mobile GPUs. We’re excited to enable developers to create innovative vision applications on these devices today, and we look forward to seeing the amazing things they will create on the PowerVR platforms of the future.”

Frank Brill, chairman of the Khronos OpenVX working group, says: “The momentum we are seeing with OpenVX is strong and growing, with conformant OpenVX 1.0 implementations and tools shipping from numerous vendors."

"We congratulate Imagination on being the first adopter member to achieve OpenVX 1.1 conformance, enabling developers creating applications on Imagination’s popular PowerVR GPUs to take advantage of OpenVX 1.1’s expanded range of processing functions and enhanced flexibility.”

Imagination is uniquely positioned to help its partners build innovative vision systems, with its in-depth knowledge of imaging processors, GPUs, video encoders and embedded CPUs, as well as its expertise in heterogeneous processing and compute APIs such as OpenCL and RenderScript and emerging higher level APIs for vision applications such as OpenVX.