Tensilica Vision P6 DSP improves performance for AI and vision applications

Intelligent edge devices and smartphones today demand a wide array of image-processing and AI-based functionality. Advanced vision and AI techniques allow the use of a single camera for bokeh, which translates into lower power and cost.

The lower power consumption on the Vision P6 DSP enables the bokeh effect to run in real time during live preview and capture. Facial unlock requires faster response time at lower power, and ArcSoft’s facial recognition algorithms are built for high efficiency, low power consumption and high accuracy.

ArcSoft HDR technology works in a variety of lighting conditions and adjusts and boosts brightness in underexposed areas while restoring details in overexposed areas. These applications lend themselves well to processing on the low-power, high-performance and highly programmable Vision P6 DSP.

“We needed a very high-performance vision and AI DSP to accelerate our beauty shot, HDR, bokeh and facial unlock applications. Cadence DSPs come with excellent software tools and a comprehensive vision and AI library which allowed us to increase the performance of our HDR algorithm by 6X compared to CPUs,” said Frison Xu, marketing VP at ArcSoft.

“Cadence’s low-power, high-performance Vision P6 DSP is an ideal DSP for porting our vision and AI applications.”

“The combination of Cadence’s vision and AI DSP and ArcSoft’s software technology make on-device vision and AI experiences possible on today’s mobile platforms. Cadence is pleased to collaborate with ArcSoft to enable our joint customers to deploy compelling on-device AI experiences,” said Pulin Desai, product marketing director, Tensilica Vision DSP product line at Cadence.

The Vision P6 DSP has been designed into application processors from two of the top five mobile application processor vendors. Based on the Cadence Tensilica Xtensa architecture, the Vision P6 DSP combines flexible hardware options with an extensive library of vision/imaging DSP functions and numerous vision/imaging applications from established ecosystem partners.

The Vision P6 DSP supports AI applications developed in the Caffe, TensorFlow and TensorFlowLite frameworks through the Tensilica Xtensa Neural Network Compiler. The Vision P6 DSP also supports the Android Neural Network API for on-device AI acceleration in Android-powered devices.

The software environment also includes complete, optimised support for more than 1,500 OpenCV-based vision and OpenVX 1.1 library functions.

Rounding out the Tensilica Vision DSP family are the Vision Q6 DSP for vision and AI, which is well suited for high-performance systems and applications with its 384GMAC/sec peak performance; the Vision C5 DSP, a complete, standalone DSP for neural networks that has 1TMAC/sec computational capacity; and the vision-optimised Vision P5 DSP.