Preferred Networks is increasing its investment in customized AI chips to secure critical hardware in the face of a global AI investment surge. It had completed the design of its second-generation AI chip, manufactured by TSMC, which will power its upcoming supercomputer.
Preferred Networks' new AI chips are specifically optimized for AI tasks, emphasizing lower power consumption and enhanced computing power. This is achieved by transferring functions typically handled by hardware to software.
The Japan-based startup, backed by investors like Toyota and Fanuc, initiated the development of its first-generation AI chip in 2016 for its supercomputers. The company plans to make this latest technology available for specific applications in 2023 and offer pure computing power to customers by 2027.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.