The past year you might not have heard much from OpenCL-on-ARM, besides the Arndale developer-board. You have heard just a small portion of what has been going on.
Yesterday the (Linux) OpenCL-drivers for the Chromebook (which contains an ARM MALI T604) the have been released and several companies will launch products using OpenCL.
Below are a few interviews with companies who have built such products. This will give an idea of what is possible on those low-power devices. To first get an idea of what this MALI T604 GPU can do if it comes to OpenCL, here a video from the 2013-edition of the LEAP-conference we co-organised.
Understand that the whole board takes less than ~11.6 Watts – that is including the CPU, GPU, memory , interconnects, networking, SD-card, power-adapter, etc. Only a small portion of that is the GPU. I don’t know the exact specs as this developer-board was not targeted towards energy-optimisation goals. I do know this is less than the 225 Watts of a discrete GPU alone.
Interviews with ARM partners
Michael Tusch, Founder and CEO of Apical Ltd, describes how GPU Compute has emerged as the best candidate for hardware-based graphics acceleration. Apical is a member of the ARM ecosystem and specializes in advanced imaging and video technology. Their Assertive Display demonstration in this video shows how a smart device can adapt to viewing conditions such as high sunlight levels in order to improve the user experience and improve battery life.
Gideon Shmuel, CEO of eyeSight, describes how GPU Compute is enabling new opportunities in the machine vision market by enhancing a system’s processing capabilities and reducing time to market. EyeSight is a member of the ARM ecosystem whose gesture recognition technology brings next-generation user interface to mass-market devices.
See also this PR text.
Mikael Bourges-Sevenier, Director of High Performance Imaging at Aptina Imaging, describes how GPU Compute is reducing time to market by enabling software-based image processing solutions on the GPU. A member of the ARM ecosystem, Aptina is one of the world’s leading imaging-solutions company which provides image sensors and image processors to customers across the globe.
Marc Guillamet, VP Marketing & Managing Director for Europe at Ittiam Systems®, describes how GPU Compute can accelerate video compression and decompression whilst consuming far less energy than CPU-only solutions. Ittiam Systems is a member of the ARM ecosystem and specializes in Digital Signal Processing (DSP) based applications in Multimedia and Communications domains.
See also this PR text.
Not all partners are ready to present their new product, so expect more in the coming half year. ATM identifies these use-cases, as discussed in this “don’t be left behind” Webinar, discussing why you cannot ignore GPGPU anymore:
Do you also want your ARM-software to run faster? We help you port your software and algorithms to OpenCL-on-ARM.
Does you or your company also have a product using OpenCL on ARM MALI? Put it in the comments for the world to see.