Qualcomm revealed more info on its upcoming Snapdragon 835 mobile processor last week during CES 2017. However, its not done yet with reveals about its latest high-end chip. This week, it revealed that it will support Google’s TensorFlow machine learning framework for better app performance.
Google already uses TensorFlow in some of its own Android apps, such as Google Photos and Google Cloud Speech. Qualcomm says it was designed to run on processing units inside of processors and of course the Snapdragon 835 has that kind of design, with its Kyro 280 CPU, the Adreno 540 GPU, and the Hexagon 682 DSP.
In the case of apps that use TensorFlow, the Snapdragon 835 will use the Hexagon 682 DSP, so that the apps don’t have to task the CPU. Google created two example apps, both of which can recognized real-world objects when placed in front of a smartphone camera. In this case, the app that used the TensorFlow framework and ran on the Hexagon DSP was able to recognize more objects at a faster rate than the same app that used the CPU to do the same tasks.
TensorFlow is also open source software and is available to use by any Android app creator. The Qualcomm Snapdragon 835 processor is scheduled to make its first appearance inside a smartphone sometime in early 2017.