System Performance Cont'd

Now that we've gone over the more general purpose system benchmarks we can focus on new benchmarks that emphasize GPU performance much more strongly. For the most part we haven't had huge issues here like we've had with good CPU and general performance benchmarks, but it's important for us to keep our benchmarks up to date in terms of workload balance and overall performance.

3DMark Sling Shot 3.1 Extreme Unlimited - Overall

3DMark Sling Shot 3.1 Extreme Unlimited - Graphics

3DMark Sling Shot 3.1 Extreme Unlimited - Physics

One of our first new benchmarks designed to better test the GPU is 3DMark's Sling Shot ES 3.1 test, which is designed to test a GPU's performance when the application is either using OpenGL ES 3.1 or Metal. As one can see, the Snapdragon 820 and Exynos 8890 have basically comparable GPU performance in this test and in the physics test as well. Once again we're seeing how core count and clock speed are basically the primary determinants of performance in the physics test when the device isn't strongly limited by thermals. I wouldn't draw any real conclusions from this as generally game CPU code can extract ILP unlike what we're seeing in this test.

Basemark ES 3.1 / Metal

Basemark ES 3.1 / Metal Offscreen Test

Basemark ES 3.1 / Metal Onscreen Test

In this test we start to see that the Mali GPU in the Exynos 8890 and the PowerVR GPU in the A9 are providing a noticeable advantage over the Snapdragon 820's Adreno 530 to a noticeable extent.

GFXBench 4.0 Car Chase (On screen)

GFXBench 4.0 Car Chase (Off screen 1080p)

GFXBench 3.1 Manhattan ES 3.1 (Onscreen)

GFXBench 3.1 Manhattan ES 3.1 (Offscreen)

GFXBench 3.0 Manhattan (Onscreen)

GFXBench 3.0 Manhattan (Offscreen)

With GFXBench we can see that in Car Chase and Manhattan the Adreno 530 actually manages to pull away. However, because we have basically zero architecture disclosure on the Adreno 530 there's really no way for us to explain what's going on here and why. The reasons for the difference in performance could be related to drivers or architecture or architecture implementation and in the absence of information it's probably best to avoid making blind guesses. Regardless of these details, the Snapdragon 820's GPU should be more than enough for playing the latest games, but unless you use Samsung's automatic game optimizer system to set render resolution to 1080p it won't do as well as the iPhone 6s but given that most Android games target a much lower spec level it's likely that you won't have any problems given that the Adreno 530 is on the bleeding edge for Android SoCs.

System Performance Revisited Camera Architecture and UX
Comments Locked

266 Comments

View All Comments

  • realbabilu - Thursday, July 7, 2016 - link

    If we bought for performance. The lags or the speed of apps is quite small than last one or two years ago oneplus one s801, you can't fell it big difference unless on benchmarking apps.
    The photos can tell different story, you can know it good or bad than last year mobile or other features like ois
  • ntp - Thursday, July 7, 2016 - link

    That's a very thoughtful reply, Impulses, thanks. But with the small sensors of smartphones I think 3/4ths of a stop is a significant advantage, more so than in the case of large sensor cameras, since we'd care about the F number in low light scenarios, where the ISO will be high. I'm just saying it should be better emphasized so people understand the real world advantages it gives.
  • Impulses - Thursday, July 7, 2016 - link

    It's a valid point, I'm just saying you can't look at that in a vacuum, specially since you're not looking at an ILC anyway... If you can't swap any parts, then the end result is all that really matters and that includes sensor efficiency, post processing (unless you're shooting RAW, a rarity on phone users), the presence of OIS, effectiveness of the latter, and even things like how smart the auto mode is...

    That last bit is probably beyond AT's more data driven evaluation, but a phone that relies to heavily on OIS for instance (or HDR) might take more blurry shots under real life conditions... That actually does favor a faster aperture but the point is emphasising specs in a vacuum is pointless.
  • mavsaurabh - Tuesday, July 12, 2016 - link

    I just wish to reply regarding aperture , you rightly said that f no causes cost to skyrocket in case of lslr ens all else being equal, the catchphrase is all being equal ! In case of constraints of mobile photography, lens stack size & weight limitations, heat produced etc leads to various compromises like plastic lens which coupled with bigger apertures leads to higher corner aberration, diffraction etc etc. in end as Impulses wrote what matters is the end result which is fine tuned balance of various compromises made !
    I am a pixel peeper and street, landscape photgrapher by hobby with 25 years of film and digital shooting through Slr's , mobiles , compacts, Fuji X100.
    My observation is that samsung uses hard sharpening and over saturated colors which "creates" pleasing photos on phone screen but if you display it on decent monitor and zoom to even 50% you will see various artefacts and no latitude for post processing. Now most of casual photographers will like larger than life portrayal or smearing of face pimples etc by clever use of face detection but hey any one who loves photography will differ!
    I completely agree about fast focussing advantages but honestly i am yet to use a mobile camera with lens fast enough to freeze pet/ child movement in indoor light to take advantags of fast focussing.
    Only phone which was able to do that with use of proper flash though is Nokia 808 Pureview and kudos to its mazing manual controls plus superb post processing which bettered apple even in natural post processing !
  • beggerking@yahoo.com - Wednesday, July 6, 2016 - link

    please just stop those BS apple biased benchmarks at 10x lower resolution... just take them off the chart! its not even a good comparision and serves no uses.
  • realbabilu - Thursday, July 7, 2016 - link

    What you see on your screen mobile is what you get. Offscreen just measuring the gpu can do,basically it useless for user because you can't see it.
  • lilmoe - Wednesday, July 6, 2016 - link

    "The one notable shortfall here is that Samsung only allows 800 ISO max in manual ISO mode when the true maximum is 1250"

    I had that number in mind when I read it last night, and was too lazy to test. I've tested it now and my unit can go up to 1600 ISO. Is that also a variable difference in Samsung's sensor (mine is Samsung made), or is the extra third stop on mine extended?
  • Chris_m1296 - Wednesday, July 6, 2016 - link

    Joshua ho, how did the exynos 8890 manage this score on slingshot es 3.1 unlimited? mine only got 2223 and even 3dmark themselves list the exynos version at 2223.
  • UtilityMax - Wednesday, July 6, 2016 - link

    Some people complain that the review is too harsh. But my personal view is that if this is a +650USD smartphone that _also_ happens to be carrier locked, it'd better be not just good, but _excellent_ in every respect. Otherwise, it's not clear what exactly justifies the price premium over a phone like Oneplus 3 or why a typical shopper should choose this over an apple product.
  • Impulses - Thursday, July 7, 2016 - link

    I kinda agree... I still feel some areas could've been better tested given how long the review date got dragged out, but there was still content here that's pretty unique to AT. I think the market, overall, is definitely giving the high end OEM too much of a pass given the prices phones are now commanding.

    A $1,000+ laptop with performance sapping bloat that the user can't remove (that aren't part of the core OS) would get ripped to shreds. It's time $700+ phones were held to the same standards.

Log in

Don't have an account? Sign up now