Tensor G2 confirmed as 5nm processor, not 4nm as expected

As per the new information, the Tensor G2 is actually built on a 5nm manufacturing process and not a 4nm one as was expected before the launch.

This means that the Pixel 7 series processor is not using the 4nm processor. Some of the confusion seems to have stemmed from pre-release benchmarks and the fact that Google didn’t initially confirm the process it used for the Tensor G2. As of the Pixel 7 series keynote, claims were made of 60% speed and 20% efficiency gains over the previous generation.

A deep dive has been taken of a leaked Geekbench listing ahead of launch, with some legitimate elements such as clock speed and core layout incorrectly predicting die size. There appears to be no evidence within the Pixel 7 build, which lends more credence to the theory that a 5nm process is being used. Since then, a Google spokesperson has confirmed android authorization In fact, the Tensor G2 is made using a 5nm process:

We purpose-built Google Tensor G2 for real-world use cases. Our final architecture, which includes 5nm, helped us reach that goal while increasing both performance and power efficiency. This approach allowed us to add new capabilities while taking a step forward on machine learning with the G2 with our next generation TPU.

as Come Notes, this is still not a completely comprehensive answer to the question, although Google hasn’t used the specific build process. This means that on paper the 5nm Tensor G2 isn’t as efficient as last year’s 4nm-based Qualcomm Snapdragon 8 Gen 1 or Samsung’s own Exynos 2200. This may come as a disappointment, but the Tensor G2 boasts a very modest clock speed boost over its predecessor. Google is banking on better machine-learning power with next-generation TPUs.

Also read: Google Tensor G2 Chip: Everything you need to know

Whether the Tensor G2 in Pixel 7 uses a 5nm manufacturing process instead of 4nm is a big question for you. How do you expect if the Pixel 7 series carries on with skills in areas that other devices don’t, such as image and language processing, does or won’t make it a go? Tell us in the comment section below.