Alphabet's Google is currently negotiating with Marvell Technology to develop two new chips designed to run artificial intelligence models more efficiently.
One chip is an in-memory processing unit intended to work alongside Google's Tensor Processing Units (TPUs), while the other is a new type of TPU specifically engineered for operating AI models.
Google has been actively promoting its TPUs as viable alternatives to NVIDIA's dominant GPUs. Sales of TPUs have become a major driver of growth in Google's cloud computing revenue, as the company seeks to demonstrate to investors that its AI investments are yielding returns.
The two companies aim to finalize the design of the in-memory processing unit as early as next year, followed by the delivery of trial production samples.
Comments