On this week's Made by Google podcast, Tensor G2 is the topic of discussion, and the latest episode provides us with an overall insight into Google's approach to these chips, along with the benchmarks.
Google Openly Admits That AI-Powered Functionality is More Important Than Hardware Prowess for Pixel Phones, and the Company is Happy With the Results
Monika Gupta works as a senior director of product management for Google Silicon Teams and gets "to focus on what [Google] need[s] five years from now" for its chips. The interview mainly revolved around how the in-house approach helps the silicon team working closely with Google's AI researchers to "know exactly where machine learning models are trending in five years."
I’m not making decisions based on where machine learning is today, and I can say that because I work at Google. Same with the software that our software team is doing. I know where the software team wants to take the user experiences five years from now. That’s the benefit of not being a merchant silicon supplier, but an in-house silicon supplier. So those trade-off decisions are very tough, but I think they get a little easier when you’re vertically integrated.
In addition to that, the podcast also had a section on the Tensor team's opinion on benchmarks and what Pixel phones are focusing on instead.
I think classical benchmarks served a purpose at some moment in time, but I think the industry has evolved since then. And if you look at what Google is trying to do by pushing AI innovations into a smartphone, because we feel like this is the approach that will deliver helpful experiences like some of the ones i just mentioned, classical benchmarks were authored in a time where AI and phones didn’t even exist.
They may tell some story, but we don’t feel like they tell the complete story. And so for us what we benchmark are the actual software workloads that we are running on our chip and then we strive with every generation of tensor chip to make them better, whether it’s better quality, better performance, lower power.
Google has said that it is "perfectly comfortable" with not winning or leading the benchmarks as it is focusing on prioritizing end-user experience that originates from the chip decisions that the company has made.
Like on Pixel 6 and Pixel 7, you can see all the amazing innovations that we have landed, and a lot of them were like the first on Pixel. So we’re very comfortable with that approach.
Needless to say, this approach clearly showcases that Google is valuing artificial intelligence more than raw hardware prowess, and it would be interesting to see how this philosophy goes forward. Will we see a day when Tensor chipsets can finally rival the likes of Apple and Samsung?
Gupta was asked about the silicon roadmap as well, and she talked about how the goal is to ensure that Tensor supports ambient computing.
…overall vision for us and for Tensor family is really all about ambient computing. Ambient computing means that the technology is making your life easier. I think we have a lot of evidence of this that we talked about today, whether it’s making photography easier, whether it’s making phone calls and how you use your phone, like your day-to-day tasks, easier.
I would say we build upon that vision of ambient computing and figure out how to do super complex, nuanced things in the chip in a power-efficient way that are going to unlock some of those ambient computing experiences.
There is no denying that Google is showing promising ambitions, but at the end of the day, they are just ambitions, and we are not sure how long it is going to take AI to catch up to actual hardware prowess that is found in the likes of Qualcomm, Samsung, and Apple chips.
