![\"\"](\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/04\/a7a749de522c74cdca69383f760caf7c.jpeg\")
<\/p>\n <\/p>\n
Alphabet Inc.’s Google is reportedly advancing its AI hardware push by working with Marvell Technology on two new chips designed to improve efficiency and challenge Nvidia Corp’s lead.<\/p>\n
Google is in discussions with Marvell to develop a memory processing unit designed to work alongside its\u00a0Tensor Processing Unit\u00a0and a new TPU specifically optimized for running AI models, Reuters reported on Sunday (via The Information).<\/p>\n
The chip is aimed at improving how data moves during AI workloads, a key bottleneck in large-scale model performance.<\/p>\n
Don’t Miss:<\/p>\n
The companies are also exploring a next-generation TPU tailored specifically for running AI models more efficiently.<\/p>\n
The report said the memory chip design could be finalized as early as next year before moving into test production<\/p>\n
Google and Marvell did not immediately respond to Benzinga’s request for comments.<\/p>\n
Google has been investing heavily in its in-house chips to reduce reliance on Nvidia’s GPUs, which dominate the AI computing market. Sales of TPUs have emerged as a major contributor to Google’s cloud revenue growth.<\/p>\n