Vision DSP from Cadence offers improved performance for embedded vision and AI
Built on a new, faster processor architecture than previous models, the Cadence Tensilica Vision Q6 digital signal processor (DSP) is designed for embedded vision and artificial intelligence applications.
Built on a new, faster processor architecture than previous models, the Cadence Tensilica Vision Q6 digital signal processor (DSP) is designed for embedded vision and artificial intelligence applications. The fifth-generation Q6 DSP offers 1.5X greater performance than its predecessor and features a deeper, 13-stage processor pipeline and system architecture designed for use with large local memories. This enables the Vision Q6 DSP to achieve 1.5GHz peak frequency and 1GHz typical frequency at 16nm, in the same floorplan area as the Vision P6 DSP.
Additionally, the Vision Q6 DSP supports AI applications developed in the Caffe, TensorFlow and TensorFlowLite frameworks through the Tensilica Xtensa Neural Network Compiler, which maps neural networks into executable code for the Vision Q6 DSP, leveraging a set of optimized neural network library functions. It also supports the API for on-device AI acceleration in Android-powered devices and features complete and optimized support for more than 1,500 OpenCV-based vision and OpenVX1.1 library functions.
To Learn More:
Contact: Cadence Design Systems, Inc.
Headquarters: San Jose, CA, USA
Product: Tensilica Vision Q6 DSP
Key Features: Enhanced DSP instruction set (20% fewer cycles than Vision P6 DSP), 2X system data bandwidth with separate master/slave AXI interfaces for data/instructions, backwards compatibility with the Vision P6 DSP.