Ambarella has been expanding its AI SoC portfolio, and the latest addition is the CV75S family of 5nm chips. The company claims this family introduces the most cost- and power-efficient SoC option for running the latest AI-based image processing like vision language models (VLMs) and vision transformer networks in security, robotics, conferencing, and sports cameras. The CV75S family is the first in Ambarella’s lineup to integrate the latest CVflow 3.0 AI engine, which results in 3 times the performance compared to the former generation. CVflow 3.0 is a chip architecture designed based on a deep understanding of the core computer vision algorithms. It features a dedicated vision-processing engine that Ambarella has programmed using a high-level algorithm description and works with Tensorflow, Caffe, and PyTorch. This engine enables the SoC to perform trillions of operations each second at a fraction of the power consumption of leading GPUs and general-purpose CPU solutions. These chips also […]
Author: Dennis Mwihia
Dennis Mwihia is a technical writer specializing in IoT, PCBs, SBCs, and single-board microcontrollers. He has worked with several companies in those areas and has over 5 years of research, writing, and software development experience.