Mobile News

Google Pixel 7, Pixel 7 Pro Tensor G2 SoC built on 5nm process, not 4nm claim report

The Google Pixel 7 and Pixel 7 Pro were launched in India earlier this month. The company’s latest Pixel-branded smartphones debuted the next-generation Tensor G2 SoC, which was previously reported to be built using Samsung’s 4nm manufacturing process. However, according to a new report, the Tensor G2 SoC uses a 5nm process instead of 4nm. Google, in its keynote announcing the Pixel 7 series with Tensor G2 SoC, said that the Pixel 7 and Pixel 7 Pro processor will offer a 60 percent speed boost and a 20 percent battery efficiency boost over its predecessor, the Tensor G1 SoC, which was seen on the Pixel 6 series. Google hasn’t actually confirmed if this improvement is due to an improved manufacturing process or other optimizations and tweaks.

Google in cooperation with Android control confirmed that the Tensor G2 SoC used in the Pixel 7 and Pixel 7 Pro is built on a 5nm process instead of the previously predicted 4nm process.

A nanometer measurement on a chipset is half the gate pitch, or half the distance between the “edges” of a transistor’s gate. Given that there are billions of transistor gates on a single SoC, a nanometer size difference can greatly improve power consumption, space usage, and performance. The reduced size of an individual transistor means that more of them can fit on a chip of the same size, making the chip more powerful.

Google, however, claims to have focused on the machine learning capabilities of the Tensor G2 SoC implemented with next-generation TPUs rather than puzzling over the fabrication process.

“We specifically built Google Tensor G2 for real-world use cases. Our final architecture, incorporating the 5nm process, helped us achieve this goal by improving performance and power efficiency. This approach also allowed us to add new features, taking it a step further. on machine learning with our next generation TPU with the G2,” a Google spokesperson said in an interaction with the Android Authority.

Google, however, has not confirmed who built the chip, while it is widely known that Samsung is the company’s main partner. Samsung has two 5nm nodes in its strategy which include the 5LPE process used for the original Tensor G1 SoC and the newer 5LPP process. However, the process used for the SoC Tensor G2 has not been confirmed by the company.

It was previously reported that the Tensor G2 SoC has reference clock speeds that did not show a significant enough improvement to improve the manufacturing process. The numbers have been interpreted by Android developer Cuba Wojciechowski based on Geekbench list these are two ARM Cortex-X1 cores clocked at 2.85 GHz, as well as two ARM Cortex-A78 cores clocked at 2.35 GHz and four ARM Cortex-A55 cores clocked at 1.8 GHz.

The upcoming Google Tensor G2 will use the same CPU cores as the first generation Tensor, Mali-G710 GPU – details below 👇 🧵 pic.twitter.com/xbZVFhMc1l

— Cuba Wojciechowski⚡ (@Za_Raczke) September 16, 2022

Additionally, the Tensor G2 SoC is said to be paired with a Mali-G710 GPU for enhanced gaming and HDR performance. The Google Tensor G2 SoC can also be integrated with the second generation EdgeTPU AI processor. It is reported to be compatible with LPDDR5 RAM. It has 4MB shared L3 cache and 8MB shared system cache.

The next generation Tensor G2 SoC is said to feature an improved Image Signal Processor (ISP) that allows 4K video recording at 60fps on all cameras. The chipset can also reportedly handle a 108-megapixel camera without stuttering or lag.

Will the revelation that the Tensor G2 SoC is built as a 5nm chip instead of the more advanced 4nm make a significant difference to the competitive position and actual performance that will grace the Pixel 7 and Pixel 7 Pro, or will it remain an afterthought on paper details, yet to be seen.


Affiliate links may be generated automatically – see our ethics statement for details.




Source link

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button