Final Thoughts

2018 has been a very successful year for Qualcomm and the Snapdragon 845. The company had provided an extremely solid and well-rounded SoC for device vendors to build their flagship devices on- and by the looks of it the Snapdragon 855 continues this trend.

I’ve been a bit sceptical about the merits of Qualcomm’s 1+3 CPU configuration, however after seeing the preliminary performance and power efficiency figures of the new prime core on the new chipset, I’m not nearly as concerned. We reserve any final verdict for when we will have tested final commercial devices, as that’s where in the end we’ll also see the efficiency effect of the non-prime cores, and how they’ll position themselves against the competition.

Performance wise, the Snapdragon 855 is a bit odd. In steady-state workloads like SPEC the chipset is seemingly performing very well and matches or exceeds the new Kirin 980. Here Qualcomm’s changes to the CPU microarchitecture might even actually be visible in the test results, which is a nice feat. Unfortunately the memory subsystem still seems to include some of DRAM latency regressions that we also saw in the Snapdragon 845, both which are due to Qualcomm’s system level cache.

Real-world performance, while still excellent, doesn’t quite manage to reach my expectations I had for the chipset. Here for whatever reason, the chip’s improvements are not nearly as pronounced as in the more synthetic tests. Again the odd thing is that the Kirin 980 still manages to beat the Snapdragon 855 in near most of these workloads. Qualcomm had reasoned that the microarchitectural changes to the CPU were meant to help web browser performance, yet it’s here where the chip slightly lags behind the competition – I do wonder if this is a case of the CPU again being limited by either Qualcomm’s choice of more conservative caches or due to the latency penalty of the system cache.

Although the performance shown today is exemplary, it still does look maybe a little rough around the edges in some of our system performance tests – here maybe Qualcomm will be able to investigate and further improve things until we actually see commercial devices.

Whether the system performance will be improved in final devices or not, what is clear though is that power efficiency looks outstanding. Qualcomm had me worried as the PR teams had avoided talking about efficiency during the chipset’s launch, but the results today (even if they’ll need to be verified), look very promising and should result in notable battery life improvements in 2019’s devices.

On the GPU side of things, Qualcomm’s more muted performance projections of 20% were because the company has again focused a good part of the process improvements into bringing the overall power back down from the usually higher levels that we saw on the Snapdragon 845.

Overall – the Snapdragon 855 looks to be another extremely well executed SoC from Qualcomm, and I’m looking forward to validating the results and testing out the first commercial devices once they become available.

GPU Performance - Returning To Lower Power
Comments Locked

132 Comments

View All Comments

  • austonia - Tuesday, January 15, 2019 - link

    Wow that was really impressive, said no one. Apple is like 2 to 3 years ahead and QC isn't gaining any ground. 5G is a big nothingburger. If my Note4 ever burns out I'mma get a fruit-phone next time. Unrivaled performance, better security, LTS for the OS, etc. Rather have an equivalent Pixel but Google isn't even trying from the look of it.
  • eastcoast_pete - Tuesday, January 15, 2019 - link

    @Andrei: Thanks, always appreciate the level of detail in your reviews. Question: QC's concept of 1xbigFast + 3 bigNotsofast + 4 little cores might be especially suited to execute, for example, JavaScript during web browsing, as JS is single-threaded. Did you observe that to be the case?
  • eastcoast_pete - Tuesday, January 15, 2019 - link

    To be more specific: I am also a bit underwhelmed by 855's performance in the web-browsing benchmarks. How much weight does JavaScript performance have in those benchmarks. If JS performance is a significant component of the web benchmarks, the single fast Big core layout would indeed be a bit of a dud.
  • 0iron - Tuesday, January 15, 2019 - link

    Trivia: How many "here" in this article especially at the beginning of sentences? :)
  • Hung - Wednesday, January 16, 2019 - link

    What were the 845 benchmarks run with? Because the Pixel 3/XL has its A75 core clocked at 2.5GHz, while the Galaxy S9's is clocked at 2.7GHz and the LG G7's A75 runs at the stock 2.8GHz. Not a huge difference admittedly, but it definitely skews results slightly if you're comparing the maximum clock for the 855 versus the lower clocked version of the 845.
  • Andrei Frumusanu - Wednesday, January 16, 2019 - link

    Wrong, I don't know where you got the idea they're clocked differently. They're all 2.8.
  • coit - Wednesday, January 16, 2019 - link

    To me the trouble is being stuck with Google.
  • Jredubr - Wednesday, January 16, 2019 - link

    Another year that we'll see Apple's SOCs slaughtering Android's SOCs in raw performance.
    While I'm glad for the efficiency gains, that's far from enough if Qualcomm wants to remain competitive.
    Failing to meet the performance of a SOC that Apple released 1 year and a half ago and sometimes even failing meeting A10 performance just isn't enough for a 7nm SOC.
  • sean8102 - Wednesday, January 16, 2019 - link

    I'm guessing part of it is due to how much of a monopoly they are. When it comes to Android it dominates the market. A few like Samsung, Huawei etc make their own SOC's but that's about it. MediaTek is the only other I can think off but it's rare at least in the US to see them in anything but mid to low range phones and even then its still usually Qualcomn you'll get in that market range.

    From what I've read/seen one of the things that makes Apple's SOC's so fast is the large amount of cache they use. A12 having 8 MB of L3 cache, the 855 has 2 MB. Having so much cache is quite expensive and makes the die size larger which of course increases costs as well. Maybe Qualcomn just isn't getting much demand from OEM's to build such a expensive chip. If they made it and no OEM wanted to pay the price for it they would be stuck holding the bag.
  • Raqia - Wednesday, January 16, 2019 - link

    Apple doesn't have an integrated modem so it has been choosing to use that extra space for beefy, 7-wide, die space hungry CPUs and caches. Although they bench well and have world leading efficiency, those CPUs draw too much current for the small batteries that come with an iPhone and lead to the controversial and unannounced throttling they decided to enact through iOS updates to preserve battery longevity. An on die modem also saves consumers money in the end from lower packaging cost and simpler PCB layouts.

Log in

Don't have an account? Sign up now