SiMa.ai, an edge computing chip and software startup based in SAN Jose, California, recently announced the launch of a new product -MLSoCModalix chip, the industry's first multimodal edge AI product family, further consolidating SiMa.ai's position in the edge AI market.
According to the understanding, MLSoC Modalix chip adopts a 6-nanometer process, which has a significant increase in volume and power consumption. The chip is based on SiMa.ai's ONE platform developed for edge AI, designed to handle advanced AI models, including large models of cutting-edge AI such as convolutional neural networks (CNN), Transformers, and generative AI, while ensuring industry-leading performance and energy efficiency.
With performance configurations ranging from 25 to 200TOPS, the Modalix series of chips are designed to handle high-load AI work and excel at reducing power consumption, enabling easy generative AI deployments for the embedded edge ML market. It is reported that the chip is suitable for industrial automation, healthcare, intelligent vision systems, aerospace and defense and many other fields.
Founded in 2018, SiMa.ai has been developing embedded edge machine learning system-on-chip (MLSoC) to provide edge AI SoCs to organizations in industrial manufacturing, retail, aerospace, defense, agriculture, and healthcare.
In April, SiMa.ai announced it had raised $70 million in a new round of funding to breathe new life into its edge computing and robotics research and development. The company plans to use the funds to meet current market demand for MLSoC products and to advance the development of its next-generation processors. It is reported that the new generation of processors is expected to launch in the first quarter of 2025.
This paper is from Ulink Media, Shenzhen, China, the organizer of IOTE EXPO (IoT Expo in China)
