System Performance

System performance on the QRD865 was a bit of a tricky topic, as we’ve seen that the same chipset can differ quite a lot depending on the software implementation done by the vendor. For the performance preview this year, Qualcomm again integrated a “Performance” mode on the test devices, alongside the default scheduler and DVFS behaviour of the BSP delivered to vendors.

There’s a fine line between genuine “Performance” modes as implemented on commercial devices such as from Samsung and Huawei, which make tunings to the DVFS and schedulers which increase performance while remaining reasonable in their aggressiveness, and more absurd “cheating” performance modes such as implemented by OPPO for example, which simply ramp up the minimum frequencies of the chip.

Qualcomm’s performance mode on the QRD865 is walking this fine line – it’s extremely aggressive in that it’s ramping up the chipset to maximum frequency in ~30ms. It’s also having the little cores start at a notably higher frequency than in the default mode. Nevertheless, it’s still a legitimate operation mode, although I do not expect very many devices to be configured in this way.

The default mode on the other hand is quite similar to what we’ve seen on the Snapdragon 855 QRD last year, but the issue is that this was also rather conservative and many popular devices such as the Galaxy S10 were configured to be more aggressive. Whilst the default config of the QRD865 should be representative of most devices next year, I do expect many of them to do better than the figures represented by this config.

PCMark Work 2.0 - Web Browsing 2.0

Starting off with the web browsing test, we’re seeing the big difference in performance scaling between the two chipsets. The test here is mostly sensible to the performance scaling of the A55 cores. The QRD865 in the default more is more conservative than some existing S855 devices, which is why it performs worse in those situations. On the other hand, the performance results of the QRD865 here are also extremely aggressive and receives the best results out there amongst our current device range. I expect commercial devices to fall in somewhere between the two extremes.

PCMark Work 2.0 - Video Editing

The video editing test nowadays is no longer performance sensitive and most devices fall in the same result range.

PCMark Work 2.0 - Writing 2.0

The writing test is amongst the most important and representative of daily performance of a device, and here the QRD865 does well in both configurations. The Mate 30 Pro with the Kirin 990 is the only other competitive device at this performance level.

PCMark Work 2.0 - Photo Editing 2.0

The Photo Editing test makes use of RenderScript and GPU acceleration, and here it seems the new QRD865 makes some big improvements. Performance is a step-function higher than previous generation devices.

PCMark Work 2.0 - Data Manipulation

Finally, the data manipulation test oddly enough falls in middle of the pack for both performance modes. I’m not too sure as to why this is, but we’ve seen the test being quite sensible to scheduler or even OS configurations.

PCMark Work 2.0 - Performance

Generally, the QRD865 phone landed at the top of the rankings in PCMark.

Web Benchmarks

Speedometer 2.0 - OS WebView WebXPRT 3 - OS WebView JetStream 2 - OS Webview

The web benchmarks results presented here were somewhat disappointing. The QRD865 really didn’t manage to differentiate itself from the rest of the Android pack even though it was supposed to be roughly 20-25% ahead in theory. I’m not sure what the limitation here is, but the 5-10% increases are well below what we had hoped for. For now, it seems like the performance gap to Apple’s chips remains significant.

System Performance Conclusion

Overall, we expect system performance of Snapdragon 865 devices to be excellent. Commercial devices will likely differ somewhat in terms of their scores as I do not expect them to be configured exactly the same as the QRD865. I was rather disappointed with the web benchmarks as the improvements were quite meagre – in hindsight it might be a reason as to why Arm didn’t talk about them at all during the Cortex-A77 launch.

CPU Performance & Efficiency: SPEC2006 Machine Learning Inference Performance
Comments Locked

178 Comments

View All Comments

  • gagegfg - Monday, December 16, 2019 - link

    Qualcomm works for Android, so Apple's competition doesn't generate much trouble, just embarrassment. It seems that the second does not motivate them much haha.
  • Drumsticks - Monday, December 16, 2019 - link

    This comment might be too late to be seen, but is there any chance we can see the power use for the Zen 2/SKL (ICL?) based devices on the spec charts as well? It might be off by a lot, but I'm curious how they compare to the mobile SoCs. If they're too high because they're desktop chips intended for higher TDPs where maximum efficiency isn't needed, maybe it's worth it to throw in an Icelake-U number as well as a Zen 2 mobile chip when they come in.
  • Andrei Frumusanu - Monday, December 16, 2019 - link

    We never measured it accurately, the corresponding platform power for those desktop chips is generally going to be in the 30-40W range or even higher. The laptop platforms are also going to be in the 10-15W range.
  • Drumsticks - Monday, December 16, 2019 - link

    Fair enough; thanks for the reply! There is an awful lot more platform related stuff that isn't optimized on DT, I kind of derped on that.

    Thanks for your work on the article, too. I really enjoy your writeups and sympathize with the author who stays as engaged as you do with *every* commenter.
  • TEAMSWITCHER - Monday, December 16, 2019 - link

    The ads on this site are obnoxious.
  • TheinsanegamerN - Tuesday, December 17, 2019 - link

    -Not using an adblocker in 2019....
  • GH-CC - Monday, December 16, 2019 - link

    I'm not engineer, not much knowlege but one part in this article really concerns me:

    "Generally, we’ve noted that there’s a discrepancy factor of roughly 3x. We’ve reached out to Qualcomm and they confirmed in a very quick testing that there’s a discrepancy of >2.5x. Furthermore, the QRD865 phones this year again suffered from excessive idle power figures of >1.3W."

    Does this mean compared to SD855, SD865 consume more power when idling?
    Also, was this test conducted with internet connection or not?
  • Andrei Frumusanu - Monday, December 16, 2019 - link

    The above quote is only valid for the QRD865; similar thing happened to the QRD855 test devices. It's not a concern for final commercial devices, so nothing to worry about.
  • assyn - Monday, December 16, 2019 - link

    Seems like Apple is basically untouchable.
    Evben an old A11 humiliating the top Android soc..:D
  • joms_us - Monday, December 16, 2019 - link

    Humiliating by what? Some imaginary worthless bloated benchmark scores from a primitive tool that doesn't translate to real-world? For the last 2 years Apple is the one catching up in any side-by-side comparisons out there.

Log in

Don't have an account? Sign up now