Overview: GPUs provide the flexibility and computing power needed to train large AI models, while TPUs optimize tensor-heavy ...

There are central processing units (CPUs), graphics processing units (GPUs) and even data processing units (DPUs) – all of which are well-known and commonplace now. GPUs in particular have seen a ...

KBRA releases research examining the credit considerations associated with artificial intelligence (AI) compute infrastructure, including graphic processing units (GPU), tensor processing units (TPU), ...

Alphabet is moving to commercialize its custom AI chips, known as Tensor Processing Units, by selling TPU capacity to external cloud providers. The company is also preparing a neocloud offering that ...

Google’s in-house Tensor chips from the beginning have faced criticism for not offering solid performance. While they are excellent for everyday tasks, the performance gap is pretty significant when ...

Nvidia has asserted that its graphics processing unit (GPU) platform remains a full generation ahead of its competitors, responding to increased attention on Google's ...

Google's expanding Tensor Processing Unit (TPU) strategy is emerging as a serious challenge to Nvidia's long-running dominance in AI accelerators, particularly after a report from The Information ...

Zhonghao Xinying was founded in 2018 by Yanggong Yifan, a Stanford and University of Michigan-trained electrical engineer Chinese AI chip start-up Zhonghao Xinying has emerged as a home-grown ...