Google in house white chip for smartphones
The Smartphone industry is massive. Each and every year, the revenue from smartphone sales is about 400 billion US dollars and over a billion units are sold each year.
Google, who owns the android ecosystem, is taking a page out of apple’s handbook. They are going to be designing their in-house smartphone chip, which will be debuted in Google’s upcoming Pixel 6 smartphones later this year.
We’ll take a look at how new Google research is using AI design computer chips in just a few hours whereas a human expert would have taken months.
It’s pretty interesting.
Most android phones including Google’s pixel line have relied on the chips designer Qualcomm.
For clarity’s sake, Qualcomm is American company designs the chips but the chips themselves are built by Samsung and TSMC.
The latest move from Google looks to remove itself from Qualcomm completely.
The new in-house process codenamed Google silicon 101 or otherwise known as Whitechapel will power Google's upcoming phones but is also expected to feature in future Chrome books.
Samsung has teamed up with Google to build their custom chip and this makes sense as they already build chips for Qualcomm but also use their own custom chips in their smartphones sold outside the US. These Samsung chips are known as the Exynos series.
Google CEO Sundar Pichai stated that Google planned to seed more investment into hardware but as it stands Google hasn’t invested enough in their semiconductor business to be competitive just yet.
Although they are choosing to hone their focus in an area where they can obtain a competitive advantage against the major player, and this area is AI.
Google is already good at using AI to enhance image quality, the camera hardware on their phones hasn’t been updated in years but manages to keep up with the competition solely, thanks to the AI within their software, a chip with a focus on AI hardware acceleration could lead to even better photos.
Using machine learning improved color science, image stabilization, and even audio processing is possible.
A report from Axios the white chapel chips will have a dedicated area for Google assistant processing this is to improve performance and always-on capabilities. with Google’s lambda coming on the software this side could be interesting. For those of you who don’t know Google Lambda is going to incorporate the latest in AI language processing so the Google Assistant can understand the context and have a conservation with its user.
Lambda plus customs hardware could make for a next-level AI assistant potentially even offline.
Why do this?
In the first place, one of the biggest advantages of building an in-house chip over buying an external one off the shelf is the tight integration between software and hardware. The software knows exactly what it’s going to be working with so it can be more efficient this should improve the end user’s experience.
In the earlier day of smartphones, heavy optimization from apple controlling both the software-hardware allowed the iPhone to operate smoothly and provide an arguably better user experience, despite being woefully underpowered and limited in feature compared to the competition of the time
Another benefit of Google building their chips is a reduction in production costs.
Now instead of acquiring processors, from external providers like Qualcomm who themselves need to make a profit Google can design the chips themselves, and if they choose they can use the money saved to either cut down costs or use the money to improve other areas of the phone.
So what can we expect from Google’s upcoming white chapel chip?
Google's decision to separate from Qualcomm is an interesting one because it's going to look like there’s going to be a performance drop when compared to the best that Qualcomm has to offer.
The new white chapel chip is going to be behind Apple’s A14 bionic the snapdragon 8 and not to mention the M1
According to WCCF Tech, we know from the internal documents and leaks that the white chapel chip will have an 8 core arm design with 3 clusters much like the Samsung Exynos 2100 and while efficient compared to the company’s previous manufacturing techniques. The Google chip will cost certainly be a step behind the competition.
Nine to five google states predicted performance will be similar to the Qualcomm snapdragon 765 already used in pixel 5, to the layman this just means that the Google chip will have middle-of-the-road performance.
Using AI To Design Chips
Interestingly according to the economic times, a team of Google researchers is working on an ai model that allows chip design to be performed by artificial intelligence
The new AI method utilizes past experience to become better and faster at solving a new instance of the problem. The Google team writes in the paper for the scientific journal nature quote “our method was used to design the next generation of Google’s artificial intelligence acceleration and has the potential to save thousands of hours of human effort for each new generation.
According to the team in about six hours the model could generate a design that optimizes the placement of the different components on the chips.
In under six hours, our method automatically generates chip floor plans that are superior or comparable to those produced by humans in all key metrics, includes power consumption, performance, and chip area”
To archive, this Google team used a data set of 1ooo chips layout for a machine learning model which was then trained with reinforcement learning.
Anna Goldie research scientist at Google brain explains quotes “our reinforcement learning agent generates chip layout in just a few hours, whereas human experts can take months”
Despite many decades and mature industry, chip design has resisted automation requiring months of intense effort by physical design engineers to produce manufacturable layouts
So this latest development only published last month is extremely interesting so we are going to wait and see if Google will make up for the first time by using AI in their upcoming chip design. It’s also important to note that with the global semiconductor chip shortage Google might have a tough time actually getting these chips built.
Join GraspHack Family!
We will never spam you.
Be a part of our ever growing community.