Enabling Deep Learning and Artificial Intelligence in Low Power Embedded Devices
CEVA-XM6 is the 5th generation imaging and computer vision processor IP from CEVA, designed to bring deep learning and artificial intelligence capabilities to low-power embedded systems, targeting mass market intelligent vision applications.
- Superior performance for optimal real time execution in time-critical use cases, such as autonomous driving, sense and avoid drones, virtual and augmented reality, smart surveillance, smartphones, robotics and more.
- Low power consumption to meet the demand of battery-powered devices of all sizes, including use cases with multiple vision engines.
- Flexible and scalable to efficiently address the many use cases and the constantly evolving domain of intelligent vision.
- Small die size for a cost-effective solution required to address mass market applications.
- Augmented by the CDNN toolkit, a collection of hardware and software IPs that streamline the implementation of deep learning in embedded systems
- Addressing every aspect of creating a superior vision system with minimal effort, allowing our customers to focus their development on product differentiation.
CEVA Deep Neural Network (CDNN) Toolkit
CDNN is a comprehensive toolkit that simplifies the development and deployment of deep learning systems for mass-market embedded devices. Tailored and optimized for the CEVA-XM family of imaging and vision DSPs, the CDNN toolkit includes the CEVA network generator, the CDNN software framework and a CDNN hardware accelerator that work in tandem to deliver superior performance while ensuring flexibility to stay up to date with the constantly evolving domain of machine learning.
Learn more about the CDNN toolkit
CEVA-XM6 Based Vision Platform
Designing an intelligent embedded vision application has never been faster, easier or lower-risk, thanks to the comprehensive vision solution built around the CEVA-XM6 DSP. The solution includes hardware accelerators, neural network software framework, software libraries, and a broad set of algorithms, all aimed at assisting the development process of our customers, minimizing cost, risk, and time-to-market.
For more information download CEVA-XM6 product note
The CEVA-XM6 introduces a range of architectural innovations and enhancements that deliver breakthrough performance for neural networks and advanced computer vision processing
- Innovative vector processor unit (VPU) architecture – ensuring above 95% MAC utilization.
- Enhanced Parallel Scatter-Gather Memory Load Mechanism – further improving the performance of vision algorithms, including SLAM and depth mapping
- Sliding Window 2.0™ – This patented mechanism takes advantage of pixel overlap in image processing and helps to achieve higher utilization for a wider variety of neural networks and cope with the increasing complexity of these networks
- Optional 32-way SIMD vector floating-point unit that includes the IEEE half precision standard (FP16) and major non-linear operations enhancements
- Other improvements include an enhanced 3D data processing scheme for accelerated CNN performance, a 50% improvement in control code performance versus the CEVA-XM4, a new scalar unit which further reduces code size, multi-core and system integration support
CEVA-XM Announcements5 Jan 2017 Altek License CEVA Imaging and Vision DSP for Deep Learning in Mobile Devices
5 Jan 2017 DeepGlint Harness the Power of CEVA-XM4 Imaging and Vision Platform for Intelligent Video Analytic and ADAS Solutions
4 Jan 2017 ON Semiconductor License CEVA Imaging and Vision Platform for Automotive ADAS
- Products Overview
- DSP Cores
- Connectivity Platforms
- Development Environment