New Google Pixel 7 & 7 Pro phones released in October this year have a new Google Tensor G2 chip with upgraded TPU for AI.
Codenamed Cloudripper it features multiple ARM chips manufactured by Samsung on 4nm.
Dev board code name | Cloudripper |
---|
Model number | GS201, Tensor G2 |
---|
Cores | 2x super-big ARM Cortex-X1, 2x big A78, 4x small Cortex-A55 |
---|
GPU | Mali-G710 |
---|
Manufacturing node | 4nm Samsung PLP |
---|
Modem | Samsung Exynos 5300 5G |
---|
Google talked about the Tensor G2 and said that it would bring "even more AI-heavy breakthroughs and helpful, personalized experiences across speech, photography, video, and security." And sure enough, the company delivers. The Pixel 7 can take and process night sight images up to two times faster than the Pixel 6. There is also a new Unblur feature on board that fully fixes slightly blurred images. Further, speech recognition has been improved, with the Pixel 7 processing dictated text faster than the Pixel 6,
all without sending your audio snippets to servers.
Google is hitting the custom silicon game hard! 🔥
www.androidpolice.com
No mention of edge only TPU (Tensor Processing Unit).
Tensor Processing Unit (
TPU) is an
AI accelerator application-specific integrated circuit (ASIC) developed by
Google for
neural network machine learning, using Google's own
TensorFlow software.
[1] Google began using TPUs internally in 2015, and in 2018 made them available for third party use, both as part of its cloud infrastructure and by offering a smaller version of the chip for sale.
Wonder if there is Akida IP on one of the ARM chips?
And I think there may be something going on with Fujitsu for new AI sensors. And Apple's new VR headsets.