Google Tensor vs Snapdragon 888

Google Tensor vs. Snapdragon 888

Want to know who wins when we pit Google Tensor against Snapdragon 888 in a one-on-one processor showdown?

Google Tensor vs Snapdragon 888: how the Pixel 6

Qualcomm Snapdragon could get GPU boost in 2022 - 9to5Google

The Chip Works The phone hasn’t even hit the market yet, but the prospect of a Pixel 6 series with a custom Google Tensor SoC already raises big questions. Catch the apple? Are you going to use the latest and greatest technology?

Google could have bought chipsets from its partner Qualcomm or even bought an Exynos model from its new friends at Samsung, but that wouldn’t have been so fun. Instead, the company worked with Samsung to develop its own chipset that uses a combination of standard components and some of its internal machine learning (ML) silicon.

According to a solid report, the Pixel 6’s Google Tensor SoC will be a little different from other flagship chipsets on the market. Of course, we save the benchmarking and all the performance and battery ratings when we pick up the device, but we already have a lot of information to do a paper comparison between the latest Qualcomm chipsets (and Samsung even during let’s take a look at the outcome of the Google Tensor chipset vs. Snapdragon 888 showdown.

Google Tensor vs. Snapdragon 888 vs. Exynos 2100
While Qualcomm and Samsung’s next-gen SoCs aren’t far behind, Google is the only Tensor chip designed to compete with the current generation of flagship Qualcomm Snapdragon 888 and Samsung Exynos 2100 chipsets. Use it as a basis for our comparison of its latest Exynos Processor. According to the report, the modem and GPU settings were taken directly from the Exynos 2100, and the similarities extend to support for similar AV1 media decoding hardware.

If the GPU setup matches Samsung’s Exynos 2100, the Pixel 6 will be a decent gaming phone as well, albeit within a few frames of the Snapdragon 888’s graphics capabilities. Chip’s Tensor processing unit) will offer even more competitive capabilities for artificial intelligence and machine learning.

Google’s 2 + 2 + 4 processor setup is an odd design choice. It’s worth exploring a bit more, which we’ll get to later, but the highlight is that two powerful CortexX1 processors are supposed to give the Google Tensor SoC more grunt. Single threaded but older CortexA76 cores can make the chip less multitasking. It’s an interesting combination that dates back to the unfortunate setups of Samsung’s Mongoose processor. However, there are still important questions to answer about the energy and thermal efficiency of this construction.

On paper, the Google Tensor processor and Pixel 6 series look very competitive with the Exynos 2100 and Snapdragon 888, which can be found in some of the best smartphones of 2021.

Understanding the layout of Google’s Tensor processor

Let’s come to the big question on the lips of all enthusiasts: why should Google choose the Arm CortexA76 2018 processor for a state-of-the-art SoC? The answer lies in a compromise of surface, performance and warmth.

I dug up a slide (shown below) from a previous view by Arm that helps visualize the key arguments. The graphics scale is certainly not particularly precise, but the main thing is that the CortexA76 is smaller and less powerful than the new CortexA77 and A78 with the same clock frequency and the same manufacturing process (ISO comparison). has been working with Arm on a 5nm CortexA76 for quite some time. If you want numbers, the CortexA77 is 17% larger than the A76. while the A78 is only 5% smaller than the A77. Likewise, Arm managed to reduce power consumption by just 4 between the A77 and A78, so the A76 remained the smallest and least efficient option.

The trade-off is that the CortexA76 offers much lower peak performance. Comparing Arm’s numbers, the company saw a 20% increase in microarchitecture between the A77 and A76 and a further 7% in a similar process with the move to the A78. As a result, multithreaded tasks can be slower on the Pixel 6 than its Snapdragon 888 rivals, although that depends a lot on the exact workload, of course. With two CortexX1 cores for heavy lifting, Google can be sure your chip has the right chip. Combination of maximum performance and efficiency.

Leave a Reply

Your email address will not be published.