The Snapdragon 888 vs The Exynos 2100: Cortex-X1 & 5nm - Who Does It Better?

GPU Performance & Power: Very, Very Hot

Moving onto the GPU side of things, I was very intrigued coming into this comparison, as both Qualcomm as well as Samsung LSI had made promises of enormous performance upgrades in the range of 35% and 40% respectively. We didn’t exactly know how Qualcomm achieved these performance gains given this year’s rather opaquer reveal of the Snapdragon 888. On the Exynos side, I was immediately dubious about Samsung’s 40% claim given that the new Mali-G78 was only meant to be a small generational performance and efficiency boost, as well as the process node having only a 20% power efficiency gain, however the Exynos 990 was in a bad position so maybe it was possible to achieve. Given a lack of large architectural as well as process node improvements, the large performance improvements must thus come from large power increases.

Starting off with Basemark GPU, we’re off to a mixed start. Both the Snapdragon 888 and Exynos 2100 notably outperform their predecessors in terms of peak performance, however their sustained performances on the Galaxy S21 Ultra isn’t too great.

The Exynos 2100 improves dramatically over the Exynos 990 in this regard, however the Snapdragon 888 S21 barely budges the needle against its predecessor, posting roughly the same sustained performance figures as any other Snapdragon 865 device such as the S20 Ultra.

In GFXBench Aztec High, we see a similar story, where peak performance of both phones is much greater than before, however it quickly throttles onto mediocre figures. Again, these are still great improvements for the Exynos, but not so great figures for the Snapdragon 888 S21 Ultra, as it’s posting worse figures than the Note20 Ultra with the Snapdragon 865+.

In terms of power and power efficiency, red alert, red alert!

Both the Exynos 2100 and Snapdragon 888 are showcasing outrageous peak power figures around 8W, which are figures that are simply impossible to sustain or dissipate in a phone.

We can see that both chips are way beyond their predecessors points in the frequency/voltages curves as the power efficiency is either outright flat, for the Exynos, or worse than their predecessors, like the Snapdragon – meaning both chips are using exponentially more power to try to drive more performance.

The phones quickly throttle down to below 4W – and fluctuate lower or higher depending on your environmental conditions. I was able to get power measurements for the Exynos around the 4W range (though it throttles down to below that), however for the Snapdragon this wasn’t possible as the phone’s thermal management had a very binomial behaviour of either settling at 3W power or ramping up to 6W, with very little inbetween.

Still, at these different power measurement points, we coincidentally ended up with similar performance – with the Snapdragon 888 here taking the lead in efficiency by 35%.

The 1080p variant of Aztec largely looks the same in terms of ranking, with the Exynos 2100 posting a good generational upgrade in sustained performance, while the Snapdragon 888 shows smaller gains.

In terms of power, here’s it’s even higher, with the Snapdragon doing one run at 8.4W of power.

Throttling down, the Snapdragon 888 takes the lead in terms of efficiency as seemingly it has a differently shaped power curve and benefits more at lower frequencies.

Same story in Manhattan – good upgrades for the Exynos 2100 – although still not very competitive, while the Snapdragon 888 is flat against most other Snapdragon 865 phones.

In terms of power and efficiency, at peak performance the Snapdragon 888 here actually seems to be fare off worse: it’s posting slightly more FPS, however It’s also higher power, reaching up to 8.34W.

Throttling down again shows that the Snapdragon has a steeper power curve and becomes more efficient at lower frequency points. The throttled states of both phones post nearly the same performance, but the Snapdragon does it at 28% lower power.

Finally, in T-Rex, the Snapdragon takes a more significant lead in peak performance at the same power, while when throttled down, the Adreno GPU showcases a +50% advantage in perf/W.

Much Too Hot to Handle

I’ll be quite frank with the results of these new SoCs: they’re terrible. Much like smartphone vendors have for years now copied the worst aspects of Apple’s devices, such a dropping headphone jacks and dropping chargers, the SoC vendors this year have now also copied the worst aspect of Apple’s SoCs: extremely high GPU peak power states.

When I tested the Kirin 9000 a few months ago in the Mate 40 Pro I thought that HiSilicon’s choice of turbocharging their massive GPU up to peak power figures of 8W was a very bad choice, but now Qualcomm and Samsung LSI followed up doing the exactly same thing, as if this was a race to the bottom as to who can create the hottest GPU in the market.

As to why the SoC vendors are doing this, it’s very easy to look at the benchmark charts and see the marketing pressure that Apple applies on the rest of the industry, being far ahead of the pack in terms of performance and efficiency. I wouldn’t be surprised if this generation of SoCs have had design decisions impacted by the marketing departments.

Inside devices such as the Galaxy S21 Ultra today – these peak performance states are utterly pointless as they are just impossible to maintain for any reasonable amount of time, as the thermal envelope of the phones really aren’t any different to that of any other device of this form-factor, including the predecessor S20 Ultra.

The Snapdragon 888’s peak performance state is pretty absurd, as at its 840MHz GPU frequency I’ve measured average power of around 11W. This state can’t be maintained for longer than a few seconds before it throttles down to 778 and 738MHz at 9-8W for the rest of the duration of a test on a cold device, before further limiting down due to thermals during prolonged periods. In terms of sustained performance, the S21U’s advantages over the S20U is in the 5-20% range, depending on workload, well below Qualcomm’s proclaimed 35% performance boost. That margin here actually is even smaller against the Snapdragon 865+ Galaxy Note20 Ultra.

I asked Qualcomm to rationalise these high-wattage peak performance points, and the official response was that these were enabled in order to give a higher level of flexibility in terms of higher power gaming phones and higher thermal envelope devices which are able to sustain greater power levels. I know that at least Xiaomi’s Mi 11 will be more aggressive than the S21 Ultra in terms of sustained power levels, at a cost of higher device temperatures. As for gaming phones – the last few generation of those devices have shown little actual physical design differentiation to actually enable higher thermal envelopes, with most of their advantages simply being that they are allowed to get hotter, showing no advantage over “regular” phones which do the same (OnePlus devices, ZenFone 7 Pro for example). The S21 Ultra here has peak skin temperatures of around 46°C with long-term throttling at around 42°C.

For the Exynos 2100 – Samsung LSI’s claim of a 40% performance boost is more credible as this not only refers to the peak performance figures, but can actually also be applied to the sustained performance figures of the phone. It’s actually a tangible and very large upgrade to the Exynos 990 last year, however it needs to be put into context. The peak power figures here have the same negative connotations as on the Snapdragon unit so I won’t repeat myself in that aspect.

In terms of sustained performance, although the Exynos 2100 is a large generational upgrade, it still falls below that of last-generation Snapdragon 865 devices, and naturally also the newer Snapdragon 888. The benchmark figures here also pretty much correspond to the real-world gaming performance of the phones – the Exynos S21 Ultra fared not only worse than the Snapdragon S21 Ultra, but also worse than a Snapdragon S20 Ultra or Note20 Ultra.

The interesting data here is the comparison to Huawei’s Mate 40 Pro with the Kirin 9000 and its gargantuan Mali-G78MP24 GPU – 10 more cores than the Exynos 2100’s configuration. Putting the Mate 40 Pro into power-saving mode will actually cap the maximum GPU frequency and give you reasonable power consumption figures around 4W, which are comparable to what the Exynos 2100 in the S21 Ultra throttles at. We can see that the Kirin’s performance is either superior, lower power, or both, signifying the chip is being notably more efficient than the Exynos 2100. The larger GPU as well as the superior TSMC 5nm node come at play here.

Samsung LSI’s confirmation that they’ll be deploying AMD’s RDNA-based GPU for next-generation flagship SoCs will hopefully mean that the Exynos’ competitive positioning will be quite different next year; however, we shouldn’t expect miracles as the process node differences to Apple’s GPUs will likely still linger on.

Unfortunately, Samsung’s (the mobile division) battery saving mode on the Galaxy S21 doesn’t affect the GPU frequencies at all, unlike Huawei’s PSM, so it doesn’t help at all for the power envelopes or efficiency. I would highly recommend them to introduce such a mechanism here as having burning hot phones really isn’t a great experience while gaming, and the performance will regress to those sustained levels anyhow.

Generally, I see this generation as quite the disappointment when it comes to GPU advancements. Qualcomm likely suffered an efficiency set-back and minor improvements due to the process node shift, and while Samsung LSI has achieved good generational advancements, the Exynos still clearly falls behind due to architectural GPU disadvantages.