Imagination had two really interesting goodies at MWC, the previously mentioned VP9 codec and 3DMark Next with full shaders on an iPad. Of the two, the 3DMark demo impressed SemiAccurate the most, but the VP9 codec will probably have a bigger impact on the average user.
As Thomas Ryan wrote up last week, Imagination is porting the full VP9 codec to their GPUs. Not much to add to what Thomas said other than a two cluster Rogue/Series6 GPU can decode 1080p video in hardware at 400MHz or less. If you were doubting the viability of OpenCL, this should change your mind, or it will when you see the power numbers. It also looks pretty, see?
VP9 looks good on an iPad
The other new showing was quite unexpected, the full version of 3DMark Next running on an iPad. Other than showing how much Imagination likes iPads, this demo shows the power of the Series6 GPUs. They were running the full weight PC 3DMark shaders, ported to OpenGL ES3 of course, at decent speeds. For a mobile device it looked pretty amazing, the lighting and shading was completely correct, or at least completely correct to the accuracy available to an observer’s eye.
3DMark Next full on an iPad with Series6 GPUs
What more is there to say? How about that these Imagination Series6 GPUs which should be all over the place in this year’s crop of mobile devices do GPU Compute right. While the 3DMark demo was still early, it only came to MW C on the last day of the show, it showed none of the usual lack of polish early showings of graphical prowess normally do. This is a really good sign, I can’t wait to see what happens when the game devs really pound on this core.S|A
Have you signed up for our newsletter yet?
Did you know that you can access all our past subscription-only articles with a simple Student Membership for 100 USD per year? If you want in-depth analysis and exclusive exclusives, we don’t make the news, we just report it so there is no guarantee when exclusives are added to the Professional level but that’s where you’ll find the deep dive analysis.
Latest posts by Charlie Demerjian (see all)
- HyperX ships it’s 60 millionth enthusiast memory module - Oct 15, 2018
- Bittware/Nallatech water cools 300W of Xilinx FPGA - Oct 12, 2018
- More on Intel’s 10nm process problems - Sep 17, 2018
- Intel puts out another 14nm 2020 server platform - Sep 11, 2018
- Why Can’t Intel Supply Enough 14nm Xeons? - Sep 10, 2018