CEVA Launches SensPro2
CEVA, a provider of wireless connectivity and smart sensing technologies, today introduced its 2nd generation SensPro DSP family, a hub for artificial intelligence and digital signal processing workloads associated with a wide range of sensors, including camera, audio, radar, and more. SensPro2 offers improved processing, performance, and speed at lower power.
The 2nd generation SensPro DSP family includes the SP100 and SP50 DSPs, with a tenfold performance improvement for DeepSpeech2 speech recognition neural network, compared to the CEVA-BX2 scalar DSP. They are ideal for audio AI workloads, such as conversational assistants, sound analytics, and natural language processing (NLP.
SensPro2 is supported by a broad portfolio of software infrastructure to expedite system designs including an LLVM C/C++ compiler, Eclipse-based integrated development environment (IDE), OpenVX API, software libraries for OpenCL, CEVA deep neural network (CDNN) graph compiler including the CDNN-Invite API for inclusion of custom AI engines, CEVA-CV imaging functions, CEVA-SLAM software development kit and vision libraries, Radar SDK, ClearVox noise reduction, WhisPro speech recognition, MotionEngine sensor fusion, Tensor Flow Lite Micro support, and the SenslinQ software framework.
"Our new SensPro2 family of power-efficient sensor hub DSPs offers scalable performance, multiple precisions and high utilization for the increasingly complex and diverse AI/sensor workloads of contextually-aware devices," said Ran Snir, vice president of research and development at CEVA, in a statement. "The SensPro2 architecture is unique and innovative and uses a common ISA enabling seamless software reusability across all the SensPro2 DSPs. Our customers highly value this, along with the application-specific ISAs, as they increasingly utilize SensPro2 cores in their product designs."