Tag Archives | GPU Compute

Embedded Vision Summit - PowerVR GPUs running CNN demo

Deep learning on mobile devices at the Embedded Vision Summit 2016

     

It was clear last week at the annual Embedded Vision Summit in Santa Clara that the time of computer vision and deep learning on mobile had finally arrived. Interest in the area is growing noticeably – the Summit program expanded from one to two days this year, there were an impressive number of attendees, and […]

Continue Reading 3
ELVEES_groups2

ELVEES goes full purple: MIPS, PowerVR and Ensigma united in one vision chip

       

UPDATE: ELVEES’ new ELISE SoC targeting ADAS, smart devices, IoT, augmented reality and other computer vision applications has been announced in a press release earlier this week. You can read more about the partnership between Imagination and ELVEES on our website. If you follow this blog closely (and I hope you do), you may have […]

Continue Reading 5
Vulkan demo screenshot

Experience Vulkan graphics and compute at launch on PowerVR GPUs

    

Vulkan™ started more than a year ago as a cross-industry effort to develop an explicit API designed to work optimally on today’s leading-edge hardware. The activity has been managed by the Khronos™ Group, the same non-profit organization that develops popular APIs such as OpenGL ES, OpenCL, WebGL, or OpenVX as well as the universal file […]

Continue Reading 5
PowerVR Series7 - Series7XT_USC

Imagination’s smart, efficient approach to mobile compute

             

Imagination designed its PowerVR Tile-Based Deferred Rendering (TBDR) graphics architecture more than 20 years ago with a focus on efficiency across performance, power consumption and system level integration. This approach has equally been applied to our integration of compute functionality in our GPU architecture; PowerVR Rogue is the most recent version of our GPU architecture […]

Continue Reading 1
20-Parallel versus serial execution of a statement in a warp

Measuring GPU compute performance

    

After exploring a quick guide to writing OpenCL kernels for PowerVR Rogue GPUs and analyzing a heterogeneous compute case study focused on image convolution filtering, I am going to spend some time looking at how developers can measure the performance of their OpenCL kernels on PowerVR Rogue GPUs. The performance of scalar code running on […]

Continue Reading 1
05-Zero-copy transfer between a camera and display

Supported zero-copy flows inside the PowerVR Imaging Framework

     

In a previous article we described our PowerVR Imaging Framework, a set of extensions to the OpenCL and EGL APIs that enable efficient zero-copy sharing of memory between a PowerVR GPU and other system components such as a CPU, ISP and VDE. Most flows use EGL to facilitate the sharing of objects between multiple client […]

Continue Reading 2

Debugging OpenCL programs with Oclgrind

   

James Price is currently completing a PhD degree at the Department of Computer Science, University of Bristol. When developing programs that utilise GPU compute via OpenCL, we can’t use our traditional CPU development tools. This can make debugging complex OpenCL kernels challenging. As part of my PhD, funded by Imagination Technologies, I’ve developed an OpenCL […]

Continue Reading 0
PowerVR framework offers easy imaging integration 2

The PowerVR Imaging Framework camera demo

     

Writing and optimizing code for heterogeneous computing can be difficult, especially if you are starting from scratch. Imagination has set up a new page where developers can access the source code for an example camera and video post-processing application that leverages the PowerVR Imaging Framework to implement efficient zero-copy flows for a range of image […]

Continue Reading 0
12-Block-level implementation of face detection on CPU and GPU

Deep dive: OpenCL face detection on PowerVR [part 3]

       

Imagination’s R&D group has developed a face detection algorithm, which is based on a classifier cascade and is optimized to run on mobile devices comprising a CPU and PowerVR GPU. The algorithm employs several optimizations to improve performance and accuracy. In particular, instead of searching each entire frame for faces, the detector limits its search […]

Continue Reading 0
1-Baidu offline mobile DNN app

Deep dive: Implementing computer vision with PowerVR [part 1]

     

Computer vision is the use of computers to extract useful meaning from images, such as those that arise from photographs, video and real-time camera feeds. Thanks to the proliferation of low-power parallel processors, the increasing availability of 3D sensors and an active ecosystem of algorithm developers, it is now possible for many embedded devices to […]

Continue Reading 0