Google Tensor Pixel 6

Robert Triggs / Android Authority

Google introduced Tensor in the Pixel 6 series late last year – a high-end semi-custom chipset with Google’s special hardware sauce on top.

Although the Pixel 6 series didn’t have best-in-class flagship performance, it still offers plenty of power and impressive machine learning capabilities. Now the mid-range Pixel 6a also uses a Tensor chipset, but would it be better for Google to create a Tensor Lite processor for the Pixel A series instead?

Argument for a mid-range Tensor SoC

The Google Pixel 5a home screen showing a close-up of the Google search bar

Jamie Westenberg / Android Authority

Now, that seems pretty counterintuitive, as a powerful high-end processor is usually a great thing for a smartphone. The Google Tensor really fits the bill and is a very capable SoC. But there are a few reasons why Google should probably tone things down a bit for the upcoming Pixel-A phones.

For one, you only have to look at the Pixel 6a to see that Google seems to have prioritized the use of the Tensor chipset over anything else. Sure, you get a high-end processor, but that comes at the cost of several other features. High refresh rate? Gone. Fast wired charging? negative response. More competitive camera hardware? forget it. A newer version of Gorilla Glass? No, you’ll have to settle for Gorilla Glass 3.

Read more: Has Google lost its way with the Pixel A series?

Flagship processors are expensive. By opting for a less capable but potentially cheaper Tensor processor, Google could potentially spend more money and resources on these aforementioned aspects of the Pixel’s mid-range design. Alternatively, Google could go the cheaper route and lower the asking price like it did with the Pixel 4a. A $399 Pixel 7a would be a sweeter deal than a $449 Pixel 6a.

A cheaper, mid-range Tensor could allow Google to spend money on other features or pass the savings on to consumers.

There’s also the small argument that the Pixel 6a doesn’t take full advantage of the Tensor chipset like the Pixel 6 series. Sure, you’ve got the Face Blur and Magic Eraser camera features, as well as offline voice typing, but you’re also saying goodbye to some camera features like Motion Mode. There’s also a lower resolution and slower refresh rate display than the Pixel 6 Pro, which requires less GPU power to drive. If the A Series isn’t going to use all the flagship features enabled by the Tensor chip, why use the full chip in the first place?

Returning to the design page of a mid-range processor also allows Google to address some of Tensor’s shortcomings faster than the annual launch cycle. For example, we previously covered the Pixel 6’s significant reception issues, which may now be plaguing the 6a as well. Our review of the Pixel 6a found the device to be hot as well. Due to their more affordable nature, mid-range chips run cooler and use less battery than flagship processors. Google could potentially offer a smaller battery with the same on-time display or longer endurance with the same battery capacity. It also opens the door for a more compact mid-range Pixel phone, in line with the pocket-sized Pixels of old.

More information about Tensor: Google Tensor vs. Qualcomm Snapdragon 8 Gen 1

In short, a Tensor Lite chipset could offer a cheaper price for the Pixel A series phones (or more features), a cooler chip, more reliable connectivity, and improved battery performance compared to the flagship Tensor SoC.

What would a mid-range Tensor look like?

Google Pixel 6a buttons

Ryan Haynes / Android Authority

The Tensor chipset actually belongs to Samsung’s Exynos family. It is designed and manufactured by Samsung and uses Arm CPU cores and an Arm GPU. It even has the same modem as the Galaxy S21 series. It makes sense that any mid-range Tensor processor has a similar foundation.

Google’s original chipset opted for a fairly versatile octa-core CPU design, featuring two Cortex-X1 cores, two older Cortex-A76 cores, and four Cortex-A55 cores. This is a high-performance setup, so Google could ditch the Cortex-X cores for a theoretical Tensor Lite processor in favor of medium and small cores (either in 4+4 or 6+2 layouts). Removing the Cortex-X cores has several advantages. They are slightly larger than medium and small cores and require a larger cache for maximum performance, so some silicon is saved and license costs can be reduced by removing them.

It makes sense that a theoretical Tensor Lite SoC would ditch those power-hungry Cortex-X cores, but the AI ​​silicon would still need to be preserved.

Additionally, Arm’s Cortex-X cores are built with performance in mind, not battery life, and generate a lot of heat. Non-Cortex-X processors, such as the Dimensity 8100-Max and Snapdragon 870, show lower strain than recent flagships and seem to have better battery life. Arm’s latest mid-range core – the Cortex-A715 – would be a good replacement. Arm claims that the A715 can achieve the same performance as the Cortex-X1 and is suitable for supporting existing Pixel flagship features. However, Google has shown that it is not against using older CPU technologies. A Cortex-A77, or rather a Cortex-A78, combined with the small Cortex-A55 cores still offers a lot of performance at an affordable price.

More silicone coating: What you need to know about Arm’s 2023 CPUs and GPUs

Google will almost certainly use an Arm GPU in a theoretical mid-range processor, while the current Tensor SoC uses an Arm Mali-G78 MP20 GPU. There are good reasons to reduce the number of shader cores. Mid-range gaming is not a top priority, and GPU cores take up a lot of silicon space and are therefore expensive. On the other hand, Arm’s newer mid-range graphics cores, such as the Mali-G610 or Mali-G615, are more performance and energy efficient. Arm’s recent mid-range GPUs are the same basic designs as its flagship GPUs, differing mainly in the number of shader cores. So while switching to mid-range graphics and reducing the number of shader cores results in better performance compared to the flagship silicon, it should still deliver decent performance for high-end gaming.

We’d like Google to keep its proprietary machine learning (TPU) silicon for the proposed Tensor Lite processor, as it’s also heavily integrated into the phone’s image processing pipeline – it’s what gives the Pixel 6 AI and intelligent imaging. . In contrast, Qualcomm and MediaTek’s mid-range processors typically use less machine learning hardware than their flagship silicon. But the TPU is a key part of Tensor’s identity, enabling current Pixel features and tangible benefits like offline voice typing, sophisticated camera features, and live voice translation on the cheaper Pixel.

Mid-level silicon isn’t just about performance and cost, it could free up Google to make a more compact phone.

However, the modem is an area for improvement. The original Tensor uses an external 5G modem to support some of the best features, but external modems typically consume more power and have a larger footprint than an integrated modem. Moving to a less capable but integrated modem can save on power and parts costs, but with a few trade-offs for peak speeds and future-proofing for 5G. However, do you really want 10Gbps speeds and other fringe features instead of better battery life and lower cost in a mid-range phone?

Read more: The best cheap phones of 2022

Either way, a mid-range Tensor SoC with a less impressive CPU, scaled-down GPU, and integrated modem could result in a lower-end design than the original Tensor. But these reductions free up silicon area on the Tensor Lite chip, resulting in a smaller design with better battery life and fewer concerns about overheating. Aside from the obvious benefits of a longer-lasting and cooler phone, it could also allow Google to try new things in terms of phone design, and the limitations of battery and cooling can be somewhat overcome. This could mean a thinner design, a more compact phone, or something like a flip. It can also reduce manufacturing costs, as more chipsets can be produced from the same silicon wafer.

The positives outweigh the negatives

Google IO 2022 Tensor on Pixel 6a

That’s not to say that a mid-range Tensor processor for the Pixel A series is without its drawbacks, as there are advantages to using a high-end SoC instead.

Continuing to use last year’s flagship Tensor processor gives the Pixel A phones enough power and better performance than their competitors. And that ensures smooth performance overall and a smooth experience when playing high-end games, securing Google’s bragging rights along the lines of Apple’s iPhone SE. The flagship Tensor chip in the Pixel A phone also makes it easier for Google when it comes to porting features from the flagship Pixel to the Pixel A series, as well as streamlining the development process to keep its phones up to date.

As we found out with the iPhone SE, flagship silicon can be overkill in a mid-range smartphone.

There’s also the question of whether Google will save money by switching to a mid-range Tensor chip. It is possible that the company will use the flagship Tensor chipset as it already has a lot of stock. In addition, a new chip requires additional costs in terms of research, development and production start-up.

Nevertheless, there are clearly significant advantages to using a mid-range Tensor processor. Between a potentially cheaper price, a more optimized mid-range feature set, a cooler chip and a more battery-powered phone, the positives are clear. Plus, mid-range doesn’t necessarily mean power-efficient, as today’s best mid-range processors can struggle with older flagship SoCs.

Should Google build a mid-range Tensor chipset for the Pixel A?

11 votes