A few weeks ago, I sold an old MacBook Pro 2016 that was not using much. I replaced it with a MacBook Air equipped with Apple’s M1 processor, which I bought for $ 899 with a student discount. Although I mainly use a Chromebook, I use a variety of devices and operating systems to maintain a general market perspective. And after using the M1 MacBook Air, I’m more convinced than ever that Google should design a custom ARM processor for Chromebooks.
Let me elaborate on two key points why I think so.
The M1 drops devices with Intel technology in browser benchmarks
First, it is the general responsiveness that M1 provides. While I can’t compare apples to apples between devices running Chrome OS and macOS, I can share some important performance measures.
Take a look at this Octane benchmark, for example, using the ARM version of the Chrome browser on the MacBook Air:
I’ve run this benchmark on dozens of Chromebooks over the years and the highest score I’ve seen is around 45,000 points. And that was on an Intel Core i5 processor at the time. Granted, a Core i7 Chromebook would probably offer an even greater number, but probably around a few thousand more points. In other words, it would not be a jump of 20,000 points.
By the way, I should note that Google quickly did a good job of optimizing Chrome for macOS to run natively on Apple M1 laptops. The company quickly offered a version that boosted performance over the existing x86 version for Macs with Intel technology. And for the morbidly curious, Apple’s Safari browser on the MacBook Air scored almost as high as Chrome:
Why is Octane (or any other browser benchmark) important?
Obviously, there is more than just navigation features to any modern computing device. And the M1 handles everyone I need just as quickly.
For Chromebook users, however, browser performance is a key factor. Because? Because the entire user experience is built around the browser. Of course, there are other use cases, like Android apps and the Linux experience. But for everyone except a few extreme users, a Chromebook is typically used for browsing and web apps.
I can’t comment on how well a chip similar to the Apple M1 would handle Android or Linux. I can say that it works extremely well with iOS and iPadOS applications, but although it is similar to Android applications, it is a totally different structure and coding approach. I would assume that a custom ARM processor built like the M1 would perform well, however.
What’s different about the M1 and the current ARM options for Chromebooks
This is the second part of my reasoning, which will require a little deeper dive into the M1 chip itself. That’s because it is unlike any ARM chip designed by MediaTek, Qualcomm, Samsung and others that can (or put) their silicon on a Chromebook.
Simply put, Apple found a way to increase the performance of the M1 processor cores far beyond that of any competitor.
There are four “big” cores and four “small” cores, which are similar to how other chip designers today design their products. But none of these designers is reaching the M1’s clock speed in an energy-efficient manner. Note that I am making this observation based on the clock speeds and power requirements of the chips currently available. But even if you look at a sample of the ARM chips recently announced or to be released, you can see how Apple outperforms the market when it comes to raw performance potential.
Here is an overview to illustrate:
| Apple M1 | MediaTek Helio G95 | Snapdragon 888 | Exynos 990 | |
| Large cores | 4 x 3.2 GHz | 2 x 2.05 GHz | 1 x 2.84 GHz, 3 x 2.42 GHz | 2 x 2.7 GHz, 2 x 2.5 GHz |
| Small cores | 4 x 2 GHz | 6 x 2 GHz | 4 x 1.8 GHz | 4 x 2 GHz |
| Big core TDP | 13.8 W | TBD | TBD | Reported 9W |
| Small TDP core | 1.3 W | TBD | TBD | TBD |
Also remember that a 10th generation Intel Core i5, like the one found on the Acer Chromebook Spin 713, has only four cores. They can increase from 1.6 GHz to a boost level of 4.2 GHz, but not for long. At that point, the TDP is up to 15W and the chipset starts to accelerate. I have yet to see the M1 accelerator at lower speeds due to the heat during testing in the past few weeks.
There is another factor at play here as well: system memory.
Today, whether you have a Chromebook with an ARM or x86 (Intel / AMD) processor, you have system memory somewhere away from the chip itself. This means that the use of memory for readings and writes goes through some system bus. The M1 has 8 or 16 GB of memory directly on the chipset. This is much more efficient, which means more memory throughput.
Continuing with the Intel Core i5 example, Intel claims that the maximum memory bandwidth is 45.8 GB / s. Is fast! But when compared to the M1 chipset? It’s not that impressive: the closer the RAM, the M1 can read the memory at 68.25 GB / s.
Essentially, a chipset designed similar to the M1 on a Chromebook can offer better performance than one with a current Core i5, if not a Core i7.
Wait, I don’t need a faster Chromebook
When I raised the question and the benefits of a custom Chromebook chip similar to Apple’s M1, I saw a common response. “For most users, today’s Chromebooks are fast enough” is the general vibe. And I understand that feeling.
But it’s not all about speed, although a faster browser will certainly lead to a better Chromebook experience. By increasing speeds more efficiently in terms of energy, a solution like this can also increase battery life. And that without increasing the size of the battery.
The MacBook Air I bought has a 49.9 WHr battery, for example. The Acer Chromebook Spin 713 has slightly less capacity of 48 WHrs. The screen sizes are almost the same in both. I can get about 8 hours of battery life with a Chromebook with around 50% brightness. The same scenario for the MacBook Air with M1? Sixteen hours of use on one charge is the lower I have seen. I usually stay for almost 18 hours before I need to connect.
There’s also the cost factor, although we don’t know how much a similar custom ARM chip would cost for Chromebooks. However, as you move the Intel Core line up to the i5 and i7 range, you begin to see the chipset increase the cost of the device by $ 200 to $ 400 minimum. And you’re still not getting the battery life or performance of a chipset like the M1 if you could design a Chromebook around it.
So I understood the mantra “we don’t need more speed”. This does not mean that we must discount the other benefits.
In short, anything that can improve the Chromebook’s experience – be it its performance, battery life or even lower-priced, next-generation devices – is a victory for me.