Google has opened a 2nd war path with NVIDIA, while still in a war with Microsoft on Chat-Search.
Google’s parent company, Alphabet, has claimed that its custom tensor processing units (TPUs) can outperform Nvidia’s A100 chip, which is currently used to power many AI systems. In a scientific paper, Google researchers revealed that their supercomputer, which uses more than 4,000 of the latest generation of TPUs, is up to 1.7 times faster and 1.9 times more power-efficient than a system based on Nvidia’s A100 chip. This data is significant, as Alphabet is competing in both hardware and services to benefit from the growth of artificial intelligence. Nvidia has yet to respond to Alphabet’s claim.
