CEVA will offer its expertise in DSP integration and programming for the benefit of heterogeneous architectures composed of CPUs, GPUs and special purpose processors, and collaborate with other HSA members to push forward innovations in mobile and embedded computing.
By improving the hardware interfaces, high-level computing language and software application programming interfaces (APIs) between the many components in modern heterogeneous SoCs, the workload can be distributed across the various processors more efficiently, resulting in significant improvements in performance, power efficiency and lower overheads for memory transfer and data bandwidth. The common specification will allow system engineers take full advantage of CEVA's imaging and vision technologies, including the CEVA-MM3101 platform, in heterogeneous architectures for a broad range of applications, including image enhancements, object tracking, augmented reality and natural user interface.
The CEVA-MM3101 a fully programmable platform that is dedicated to addressing the extreme computational needs of the most sophisticated image enhancement and computer vision applications. By off-loading the device's main CPU and replacing multiple hardwired accelerators for performance-intensive imaging and vision processing tasks, the highly-efficient CEVA-MM3101 dramatically reduces the power consumption of the overall system, while providing complete flexibility.