Overview

SensPro™ is the industry’s first high performance sensor hub DSP for processing and fusing data from multiple sensors including camera, Radar, LiDar, Time-of-Flight, microphones and inertial measurement units.
SensPro is designed to handle multiple sensor processing workload for contextually aware devices and can be utilized in modern intelligent systems in automotive, robotics, AR/VR, voice assistance, mobile and smart home devices.

sensor hub dsp
SensPro is a highly-configurable and self-contained architecture that brings together scalar and parallel processing for floating point and integer data types, as well as deep learning training and inferencing.

SensPro maximizes performance-per-watt for multi-sensor processing use cases by utilizing a combination of high performance single and half precision floating point math, point cloud creation and Deep Neural Network processing, along with parallel processing capacity for voice, imaging, and Simultaneous Localization and Mapping (SLAM).
SensPro platform approach is paired with advanced software and development tools that include LLVM C/C++ compiler, Eclipse based integrated development environment, CEVA Deep Neural Network (CDNN) graph compiler for neural networks including the CDNN-Invite API for inclusion of custom AI engines, OpenVX API, and a multitude of software libraries for OpenCL, CEVA-CV imaging functions, CEVA-SLAM SDK, DSP functions, ClearVox noise reduction, WhisPro speech recognition, MotionEngine for Sensor Fusion, and the SenslinQ software framework. These broad set of software and development tools help to minimize cost and improve time to market.
SensPro sensor hub architecture provides a platform to improve the processing of more precise modeling of the environment for contextually aware devices.

 

 

Benefits

SensPro is high performance sensor hub architecture, allowing it to address the processing and fusing of data from multiple sensors for contextually-aware devices. It is a highly configurable architecture that support the data-processing of various sensors in devices that need high performance and ultra-low power consumption.

Self-contained, specialized sensor hub on-device processor that unifies multi-sensor processing with AI and sensor fusion in a unified solution
Highly configurable for different computation needs of various sensor types
Multi-Tasking support to switch between AI and sensor processing tasks

Main Features

  • Self contained, specialized sensor hub on-device processor
  • Unifies multi-sensor processing with AI and sensor fusion
  • Highy-configurable 8-way VLIW architecture
  • State-of-the-art micro architecture that combines Scalar and Vector Processing Units
  • Paralles Processing capability for imaging, Radar, DNN inference and Simultaneous Localization and Mapping
  • Advanced set of software and development tools
  • CEVA-BX2 scalar processor for control code execution
  • Up to 1024 integer (8x8) MACs
  • Up to 64 Single Precision and 128 Half Precision floating-point MACs
  • Support for Binary Neural Networks

Block Diagram

Applications Include Smart IoT Devices, Drones, and Small Robots

By Mike Demler (April 20, 2020)

Ceva’s new SensPro gives designers a versatile and highly configurable set of licensable intellectual-property (IP) cores for scalar and vector signal processing as well as neural-network acceleration. The company designed SensPro, which it introduced at the recent Linley Spring Processor Conference, as a powerful sensor hub that combines technology from its BX2 DSP, XM6 computer-vision engine, and NeuPro deep-learning accelerators (DLAs). Although the new offering’s neural-network capacity is less than NeuPro’s, its AI/sensor-fusion capabilities are a good fit for a wide range of products, from IoT devices and smartphones to ADASs, augmented/virtual-reality (AR/VR) headsets, drones, and robots.