Nexus 6 Performance With Android 5.1

CPU And System Performance

Google has made a couple of changes in the 5.1 update specific to the Nexus 6 that will impact system performance. For starters, Qualcomm’s thread migration boost feature has been disabled. Prior to the update, the task scheduler would notify the Qualcomm driver whenever a thread migrated from one CPU core to another, and in an effort to increase system responsiveness, the destination core’s frequency would be boosted to the lesser of the origin core’s frequency or 1.7GHz. The boosted core would remain at the higher frequency for at least 20ms. Given the frequency with which threads migrate across cores—sometimes dozens of times per second—this feature has a nontrivial influence on performance and battery life. The similar but different feature that boosts CPU frequency briefly when a touch event is detected is still active, however.

Some of the performance loss (and battery life gain) from disabling the thread migration boost may be offset by the second big change. The Nexus 6 running Android 5.0, like all of the other devices with four or more cores we’ve tested, only kept two cores online, shutting down the other two to reduce static power drain. An updated Nexus 6 will now keep all four cores available, which eliminates the latency involved when activating cores. It should also help the OS spread system load more evenly and possibly improve responsiveness since running processes are less likely to interrupt each other.

System Performance Benchmarks

Swipe to scroll horizontally
BenchmarkNexus 6Android 5.0Nexus 6Android 5.1Difference
AndEBench ProDevice Score82878160-1.54%
CoreMark-HPC (Base)33353282-1.59%
Memory Bandwidth7843 MB/s7809 MB/s-0.44%
Memory Latency4633 KOps/s4915 KOps/s6.09%
3D28.2 fps28.7 fps1.79%
AnTuTuTotal Score5209450550-2.96%
Basemark OS II FullOverall136813951.94%
Geekbench 3 Single-CoreGeekbench Score105110570.57%
Floating Point8828880.68%
Geekbench 3 Multi-CoreGeekbench Score32503198-1.62%
Floating Point326932970.86%
PCMarkWork Performance42414234-0.17%
Web Browsing40644040-0.58%
Video Playback3566393010.19%
Photo Editing467247972.68%

Looking at the results in the table above, we see a mixture of plusses and minuses. Most of the deltas are small, less than plus or minus 3% and within the tolerance band for these tests; Since many of these synthetic tests keep all available cores fully active, they are not affected by the changes included in the 5.1 update. Where we do see a small loss in performance are less intense CPU-centric workloads such as AndEBench Platform, Basemark OS II System, and PCMark Writing. These tests do not keep all of the cores fully tasked, and subsequently are more sensitive to the thread migration boost. Also, with all four cores active in 5.1—with one or two cores focused on the foreground app and the remaining cores handling storage I/O or processing a background task for example—there’s less thermal/power envelope to set individual cores to their max frequency. This is what happens in the PCMark Writing test, where two or more cores are generally active (there’s several small, interspersed storage reads/writes) but no single core goes above 1497MHz. Running Android 5.0, the Nexus 6 holds two cores at max frequency (2649MHz) for the duration of the test.

The Basemark OS II System test provides another example of the differences in frequency scaling. Both the Math and Multi-Core tests load all available cores at 100%, so we don’t see any difference in behavior or performance between the two different OS versions. Performance in the Single-Core test varies quite a bit when running the 5.1 update, sometimes scoring a little better and other times a little worse than the initial release. It’s the XML Parsing test where we see a significant performance drop-off when running the 5.1 update. With Android 5.0, two cores run at max frequency for the duration the test. After the update, the max frequency is achieved only sporadically, with both cores at max frequency for just a couple short bursts. The end result is less average processing power available in this particular scenario due to the changes made in 5.1.

  • ZolaIII
    Just to point out how CPU clocking logic effect busses on Qualcomm SoCs. For instance if 1 core CPU frequency fell down under the minimum frequently than is tied to max bus frequency it will narrow & memory bandwidth & this will impact GPU performance badly under GPU intensive tasks. For me it looks like that on-demand scheduler is working more as it should under 5.1. Including patch sets from Linux kernel 3.12~3.21 (on demand to use more mid frequencies) should be just enough to address performance regressions still savings (even litle more) juice. They should really disable file encryption on any ARM V7 build. Switching to last stable GCC should increase user experience greatly, it's funny they still use 4.6. To address possible fluctuations & determine real impact of changes do the tests again with performance governor & disable MP decision (hot plug) for GPU tests.
  • zodiacfml
    Ouch. Glad I bought the N5 last year.
  • endeavour37a
    I have an old LG G2 and it does not even have filters :(
  • theusual
    Be sure to upgrade 'Android System WebView' through Google Play as well as for me it didn't upgrade automatically and was causing app issues.
  • Plyro109
    Sorry. Browser seems to be autofilling and submitting in every comment thread I visit.
  • Tracy Kohler
    Get that stupid bar off the top of my screen please! It takes up a whole INCH of screen space (and vertical space is LIMITED already on this wide CRAP they call monitors today).

    I guess I'll have to come up with a way to kill it and still be able to navigate, other than scrolling. Go back to pages with a bar at top or bottom for index. While your at it FIRE the guy/gal who decided an inch of real estate on a monitor is OK to block all day. He/she will only piss off users over and over (hired from win8 team?...LOL).
  • Senecaz
    TL, DR : Lollipop s*cks! next update please...
  • musical marv
    15881932 said:
    TL, DR : Lollipop s*cks! next update please...
    Why do you say Loliipop sucks?

  • musical marv
    15881932 said:
    TL, DR : Lollipop s*cks! next update please...
    Back Up what you post here and do not ignore it.

  • endeavour37a
    I thought Tom's was a place we could have opinions and points of view we could share and express freely, how does one back up what they like and don't like? I sort of like 5.0 but it's just fine if some else does not, I ignore a lot of stuff myself.