The DSPs carry out the image processing needed in computational photography and computer vision applications such as video analytics, augmented reality and advanced driver assistance systems (ADAS).
The dedicated DSPs take off-loaded tasks from the CPUs and GPUs, which can make mobile applications more power efficient.
The IP includes a vector processor developed specifically to deal with the complexities of such applications and an extensive Application Development Kit (ADK) to enable easy development environment.
Gideon Wertheizer, CEO of Ceva, writes: “Their market leadership and stellar reputation for leading edge innovation in mobile enables them to fully leverage the capabilities of our DSP to add feature-rich, differentiated vision-based technologies to their mobile devices.”
The Ceva ADK includes an Android Multimedia Framework (AMF) for software development, development tools and libraries optimised for the DSP.
For embedded systems targeting deep learning, the Ceva Deep Neural Network (CDNN) real-time neural network software framework streamlines machine learning deployment at a fraction of the power consumption of the leading GPU-based systems.