Oxmiq raises $35 million to develop chip architecture aimed at reducing AI costs BlockBeats News: On July 1st, according to Reuters, Oxmiq announced the completion of $35 million in financing for the development of a chip architecture aimed at reducing the cost of artificial intelligence. The company stated that it will use this round of funding to advance its chip design and system architecture research and development for AI computing optimization, in order to improve computing efficiency and reduce the overall cost of AI training and inference. Normally, the computation of artificial intelligence systems is divided between graphics processing units (GPUs) and central processing units (CPUs). And Oxmiq plans to integrate these two components with a third component - tensor engine - into the same chip design. The company stated that its goal is to become the 'Arm of the Next Generation Computing Ecosystem'. Co founder Raja Koduri mentioned that Arm provides chip architecture and intellectual property licensing for almost all smartphones worldwide. Oxmiq also plans to develop a "computational texture" architecture that integrates multiple chiplets (modular designs that combine multiple dedicated chips into a complete system) and memory in the same package. Click on the original link below to join the Beating · Feishu AI news channel, which continuously monitors global AI hotspots and news 24/7. [Original link]