GPU Performance

Although CPU is often the focus of any given SoC, it’s important to avoid using a weak GPU as even cases as simple as web browsing or navigating through a UI can rely on the GPU for rendering, in addition to the common use cases of gaming. It’s also possible that GPUs can be leveraged for compute, which has great use for cases like image and video processing. To this end, the Snapdragon 810 has an Adreno 430 GPU that runs at 600 MHz, similar to the Snapdragon 805’s Adreno 420. As a result, all of the improvements we’re seeing from the Adreno 420 to the Adreno 430 are solely the result of architecture and driver improvements rather than clock speed increases.

3DMark 1.2 Unlimited - Overall

3DMark 1.2 Unlimited - Graphics

3DMark 1.2 Unlimited - Physics

BaseMark X 1.1 - Overall (High Quality)

BaseMark X 1.1 - Dunes (High Quality, Offscreen)

BaseMark X 1.1 - Hangar (High Quality, Offscreen)

GFXBench 3.0 Manhattan (Onscreen)

GFXBench 3.0 Manhattan (Offscreen)

GFXBench 3.0 T-Rex HD (Onscreen)

GFXBench 3.0 T-Rex HD (Offscreen)

As one can see, the One M9 manages to deliver results that basically mirror what we saw with Qualcomm’s MDP/T, although there is some variance that can be seen. HTC did make the right call here with the 1080p display as we see a pretty massive jump in performance from the One M8 to the One M9 in GPU performance, and using a 1440p display would have eaten away most of these gains. I suspect that the hit to GPU performance with 1440p displays will be mostly compensated for by the next generation of SoCs, but for now I’m still not sure that it makes sense to push such a resolution on a phone.

NAND Performance

Storage performance is often an unnoticed aspect of any device, but it can often force itself to the foreground when it’s insufficient. Probably the most famous case of this is the Nexus 7 (2012), which was really the first device that caused people to start to look closer at NAND performance. While we’re close to a better solution for storage testing, for now we can still look at Androbench to get a decent idea of relative storage performance, although this is nowhere near as extensive as our SSD testing.

Internal NAND - Sequential Read

Internal NAND - Sequential Write

Internal NAND - Random Read

Internal NAND - Random Write

In this test, HTC does show some level of improvement over the previous generation but does regress a bit in the random read department. As far as I can tell, HTC is using Samsung’s eMMC solution here, with the model name BGND3R, as opposed to the One M8 which used a SanDisk eMMC IC. It's interesting to see how the One M9 still uses ext4 here, even though the Nexus 9 adopted F2FS. As far as I can tell, there seems to be a reason to adopting one filesystem over another but this reason is still unclear to me.

System Performance: Snapdragon 810 Software: Sense 7


View All Comments

  • PC Perv - Sunday, March 22, 2015 - link

    "Unfortunately, with the move to the Peel remote application it seems that the default application no longer supports receiving OR codes."

    What the heck doss that mean?
  • Ryan Smith - Sunday, March 22, 2015 - link

    IR codes, we meant. Reply
  • PC Perv - Sunday, March 22, 2015 - link

    Really, so can I use it as a remote or not? Reply
  • JoshHo - Sunday, March 22, 2015 - link

    The key distinction is IR receiving vs transmitting. Transmission is generally universal, receiving is generally not as universal among smartphones. Reply
  • leexgx - Friday, March 27, 2015 - link

    to bad you do not compare 2 generations back as well (in this case the M7) as most people have 2 year contracts not 1 year (as i have the M7 i had to look at the charts)
    so GPU side seems to be twice as fast CPU side seems to be 50% faster than the M7 (and that horrible cam on the M7 is now 20MB witch should of happened on the M8) battery looks like its going to be good (but need the m9 part 20) but most of that is due to Larger battery (witch in my view should be 3000-3100mAh
  • PC Perv - Sunday, March 22, 2015 - link

    "Doing some quick calculations would mean that the M9 consumed about an average of 1.22 watts throughout the test, while the M8 consumed about an average of .91 watts throughout the test."

    Average of what? Per minute? Per hour? Per run? Average throughout the test?!

    "Running this same test on HSPA+ actually increases the gap in efficiency between the M8 and M9, but the difference is around 5%."

    5% of what exactly?

    " PCMark I noticed that the M9 reached about 40C, which brings it close enough to the new update's maximum skin temperatures that all three tests must be re-done."


    In page 2, is the charge time measured with the supplied charger (1.5A) or using a 2.0A charger?

    I only finished reading the first 2 pages.
  • Ryan Smith - Sunday, March 22, 2015 - link

    "Average of what? Per minute? Per hour? Per run? Average throughout the test?!"

    An average of 1.22 watts throughout the duration of the test.
  • wiz329 - Sunday, March 22, 2015 - link

    A Watt is a unit of power, not energy, so it makes perfect sense.

    It's an average power usage throughout the entire test. It used X energy per time on average throughout the entire test.
  • garbagedisposal - Sunday, March 22, 2015 - link

    Are you genuinely retarded?
    I feel for AT's writers who have to hold back when they reply to comments by idiots like these.
  • GC2:CS - Monday, March 23, 2015 - link

    One watt = one joule per second Reply

Log in

Don't have an account? Sign up now