Alleged 'A12' benchmark for 2018 iPhone with 4GB RAM pops up

124»

Comments

  • Reply 61 of 77
    It certainly looks like they opted to create a more different design when A11 was released (to support a notebook or something comparable), but since they lack enough resources and finishing that design takes longer than one-year iPhone cycle can allow, they opted to just slightly improve the A11 making it an A12 while working on a new architecture behind the scene.
  • Reply 62 of 77
    melgrossmelgross Posts: 31,475member
    KITA said:
    tmay said:
    KITA said:
    melgross said:
    KITA said:
    melgross said:
    KITA said:
    melgross said:
    If true, not an impressive boost from last year, particularly since they say it’s got six cores. I hope this is off.
    The A11 was known to throttle considerably under sustained load.

    Geekbench 4 has pauses built in to avoid thermal throttling.

    These numbers might actually be quite impressive if they're closer to the actual sustained performance of the A12.
    No, it did not. All chips, particularly mobile chips, throttle under load, but the A11 throttles significantly less than any competing chip.
    For the iPhone X using Metal API:

    3DMark Sling Shot 3.1 Extreme Unlimited - Physics (CPU bound):

    Peak: 2523
    Sustained: 1895

    3DMark Sling Shot 3.1 Extreme Unlimited - Graphics (GPU bound):

    Peak: 4428
    Sustained: 2884

    The Snapdragon 835 throttled much less than the A11.
    You should look at the reviews of phones on aRstechnica and anandtech, instead of choosing one spec, which is the one in which Apple doesn’t seem to care much about, which is physics. You need an overal test for this.
    That is from Anandtech.

    This is also from Anandtech:

    The A11 is severely thermally constrained and is only able to achieve these scores when the devices are cold. Indeed as seen from the smaller score of the iPhone 8, the SoC isn’t able to sustain maximum performance for even one benchmark run before having to throttle.

    - Andrei F.

    You took that out of context:

    "When we’re looking at competitor devices we see only the the iPhone X able to compete with the last generation Snapdragon 835 devices – however with a catch. The A11 is severely thermally constrained and is only able to achieve these scores when the devices are cold. Indeed as seen from the smaller score of the iPhone 8, the SoC isn’t able to sustain maximum performance for even one benchmark run before having to throttle. Unfortunately this also applies to current and last generation Exynos and Kirin SoCs as both shed great amount of performance after only a few minutes. I’ve addressed this issue and made a great rant about it in our review of the Kirin 970. For this reason going forward AnandTech is going to distinguish between Peak and Sustained scores across all 3D benchmarks. This however needs to be tested on commercial devices as the QRD platform isn’t a thermally representative phone for the SoC, so until that happens, we’ll have to just estimate based on power consumption where the Snapdragon 845 ends up.

    This article was a preview on the Snapdragon 845, not a device test.

    Show me a device with a Snapdragon 845, in production, that does better than the A11 and doesn't throttle, and I'll give you a "like".

     
    I was never talking about the 845.

    The Snapdragon 835 does better and doesn't throttle nearly as much.

    For the Pixel 2 using OpenGL ES 3.1 API:

    3DMark Sling Shot 3.1 Extreme Unlimited - Physics (CPU bound):

    Peak: 2907
    Sustained: 2864

    3DMark Sling Shot 3.1 Extreme Unlimited - Graphics (GPU bound):

    Peak: 4390
    Sustained: 3591
    The phones with the 835 don’t even come close to even the years older iPhone, much less the one that’s current with it. You can pull a spec out if it suits your story, but it’s overall performance that matters. And in that, the iPhone kills the competition. You won’t find anything else in comparison testing.
    tmayericthehalfbeemacxpress
  • Reply 63 of 77
    melgrossmelgross Posts: 31,475member
    Read the ARs review and comparison. It’s the same everywhere, Apple is on top for almost everything that they measure between these phones. It’s really what matters. We do know that physics is one area that Apple doesn’t care much about, likely because of Metal, which renders these physics scores as irrelevant.


    I seem to have an iOS 12 beta bug here. All I get when I tap the cursor is select/select all, instead of the paste command. But I think it’s been working on some other sites.

    Well, go to Ars and look up the iPhone 8/8+ review. The results are the opposite of what you want them to be. If I can figure a way around this, I’ll post the direct link.
    edited July 2018 ericthehalfbee
  • Reply 64 of 77
    melgrossmelgross Posts: 31,475member
    Koll3man said:
    melgross said:
    No, it did not. All chips, particularly mobile chips, throttle under load, but the A11 throttles significantly less than any competing chip.

    You wish. Actually the A11 throttles faster and more than the Snapdragon 835 or 845.
    Anandtech made it very clear. Also the performance core on the A11 consume almost 3X more power in full load than S845's performance core.

    That nonsense. I’ve read all the reviews, and that not true.
    ericthehalfbee
  • Reply 65 of 77
    ericthehalfbeeericthehalfbee Posts: 4,024member
    Koll3man said:
    melgross said:
    No, it did not. All chips, particularly mobile chips, throttle under load, but the A11 throttles significantly less than any competing chip.

    You wish. Actually the A11 throttles faster and more than the Snapdragon 835 or 845.
    Anandtech made it very clear. Also the performance core on the A11 consume almost 3X more power in full load than S845's performance core.


    Always funny when a new troll comes to the aid of an existing troll.
    tmay
  • Reply 66 of 77
    KITAKITA Posts: 163member
    melgross said:
    KITA said:
    tmay said:
    KITA said:
    melgross said:
    KITA said:
    melgross said:
    KITA said:
    melgross said:
    If true, not an impressive boost from last year, particularly since they say it’s got six cores. I hope this is off.
    The A11 was known to throttle considerably under sustained load.

    Geekbench 4 has pauses built in to avoid thermal throttling.

    These numbers might actually be quite impressive if they're closer to the actual sustained performance of the A12.
    No, it did not. All chips, particularly mobile chips, throttle under load, but the A11 throttles significantly less than any competing chip.
    For the iPhone X using Metal API:

    3DMark Sling Shot 3.1 Extreme Unlimited - Physics (CPU bound):

    Peak: 2523
    Sustained: 1895

    3DMark Sling Shot 3.1 Extreme Unlimited - Graphics (GPU bound):

    Peak: 4428
    Sustained: 2884

    The Snapdragon 835 throttled much less than the A11.
    You should look at the reviews of phones on aRstechnica and anandtech, instead of choosing one spec, which is the one in which Apple doesn’t seem to care much about, which is physics. You need an overal test for this.
    That is from Anandtech.

    This is also from Anandtech:

    The A11 is severely thermally constrained and is only able to achieve these scores when the devices are cold. Indeed as seen from the smaller score of the iPhone 8, the SoC isn’t able to sustain maximum performance for even one benchmark run before having to throttle.

    - Andrei F.

    You took that out of context:

    "When we’re looking at competitor devices we see only the the iPhone X able to compete with the last generation Snapdragon 835 devices – however with a catch. The A11 is severely thermally constrained and is only able to achieve these scores when the devices are cold. Indeed as seen from the smaller score of the iPhone 8, the SoC isn’t able to sustain maximum performance for even one benchmark run before having to throttle. Unfortunately this also applies to current and last generation Exynos and Kirin SoCs as both shed great amount of performance after only a few minutes. I’ve addressed this issue and made a great rant about it in our review of the Kirin 970. For this reason going forward AnandTech is going to distinguish between Peak and Sustained scores across all 3D benchmarks. This however needs to be tested on commercial devices as the QRD platform isn’t a thermally representative phone for the SoC, so until that happens, we’ll have to just estimate based on power consumption where the Snapdragon 845 ends up.

    This article was a preview on the Snapdragon 845, not a device test.

    Show me a device with a Snapdragon 845, in production, that does better than the A11 and doesn't throttle, and I'll give you a "like".

     
    I was never talking about the 845.

    The Snapdragon 835 does better and doesn't throttle nearly as much.

    For the Pixel 2 using OpenGL ES 3.1 API:

    3DMark Sling Shot 3.1 Extreme Unlimited - Physics (CPU bound):

    Peak: 2907
    Sustained: 2864

    3DMark Sling Shot 3.1 Extreme Unlimited - Graphics (GPU bound):

    Peak: 4390
    Sustained: 3591
    The phones with the 835 don’t even come close to even the years older iPhone, much less the one that’s current with it. You can pull a spec out if it suits your story, but it’s overall performance that matters. And in that, the iPhone kills the competition. You won’t find anything else in comparison testing.
    The 835 matched or beat the A11 in every sustained performance that Anandtech tested. The 835 is from H1 2017, the A11 is from H2 2017.

    melgross said:
    Read the ARs review and comparison. It’s the same everywhere, Apple is on top for almost everything that they measure between these phones. It’s really what matters. We do know that physics is one area that Apple doesn’t care much about, likely because of Metal, which renders these physics scores as irrelevant.


    I seem to have an iOS 12 beta bug here. All I get when I tap the cursor is select/select all, instead of the paste command. But I think it’s been working on some other sites.

    Well, go to Ars and look up the iPhone 8/8+ review. The results are the opposite of what you want them to be. If I can figure a way around this, I’ll post the direct link.
    Ars isn't using sustained performance testing, which is what we've been talking about from the start.

    The 3DMark test is broken down into a physics and a graphics test, both use Metal on iOS. I don't know why you would think physics doesn't matter because "Metal".

    melgross said:
    Koll3man said:
    melgross said:
    No, it did not. All chips, particularly mobile chips, throttle under load, but the A11 throttles significantly less than any competing chip.

    You wish. Actually the A11 throttles faster and more than the Snapdragon 835 or 845.
    Anandtech made it very clear. Also the performance core on the A11 consume almost 3X more power in full load than S845's performance core.

    That nonsense. I’ve read all the reviews, and that not true.
    Which part?

    Re Anandtech; the A11 does throttle more from its peak in the sustained performance testing than the 835 or 845. 

    The A11's big core uses 3 to 3.5 W, while the Snapdragon's big cores use 1 to 1.1 W.
    Koll3man
  • Reply 67 of 77
    frantisekfrantisek Posts: 401member
    wizard69 said:
    melgross said:
    Rayz2016 said:
    bsimpsen said:
    At 8-11% faster for the CPU, I think this would be the smallest generational improvement in the A-family since its introduction. Eventually Apple will run up against the wall or simply not need much additional horsepower, but I was expecting bigger gains, particularly in light of the rumored ditching of x86 in the next couple years.
    You’re assuming that Apple will put the fastest chip they can make in the phone? If it has more memory and a bigger screen then they might step it down to preserve battery life. The same wouldn’t apply to a processor fitted inside an iPad or a laptop since they have much larger batteries. 
    Yes, we do. Unless Apple has totally changed what they’re doing, we should be expecting at least a 25% boost for the individual core, and at least a 40% boost for the GPU cores. Of course, we don’t know what else Apple may have done for specialized purposes, but this would be disappointing.
    I would t call these numbers disappointing until we know more, even then these are bigger gains than Intel is seeing from year to year.  

    Things to consider:  


    1.  The cores could very well be 3 + 3 that is geekbench may be confused as to the number of high performance cores. 

    2.   The GPU resilts are fairly impressive and are supportted with sound growth in compute.   This is a very good thing in my mind because GPU performance is critical for midern apps.  

    3.   In all likelyhood a prototype would be running heavily instrumented code slowing the benchmarks down.  

    4.   There is good reason for Apple to spend engineering time on other sections of the SoC.   They could have easily place priority on the GPU, AI/ML hardware, and other sections that have or are starting to see increased importance.   Im as guilty as the next guy when it comes to looking at CPU performance first but the reality is that the CPU is only part of the game in modern hardware.   Iphone couldnt even exist without the capabilities of the GPU and that applies to many apps.  

    5.   As others have suggested Apple may have heard from the sheep and decided that battery life is important.    This could be a huge win for some users as the process shrink is rumored to do very well when it comes to power.  

    Seriously im going to wait for real figures.  Sadly if Apple doesnt lower proces significantky i wont be seeing an iPhone in my future.  
    That all can be true.
    And what about new 6.1" LCD rumored model? Supposed to be cheap so even performance can be "lower".
    Or 7 nm build A11?
    Just few my guesses.
  • Reply 68 of 77
    wizard69wizard69 Posts: 12,720member
    tipoo said:

    The GPU is still improved by 40% though, I could almost hear them saying something like "And this year, it's all about the GPU for AR" on the inevitable A12 slide. 

    They (Apple) have been effectively saying this for the last couple of years at WWDC.  They have heavily stressed the use of Metal and related technologies that leverage the GPU.  They have also spoken about the further relance upon the GPU by Apple software.  Basically anything that can be accelerated on the GPU is being accelerated.  

    If these numbers are honest it is an indication that Apple has focused engineering on the areas that will do iOS and modern apps the most goood and that is the GPU.   Just consider the APIs and software kits Apple has been focused on recently.  These technologies benefit from either enhanced GPUs or special function processors.    The CPU in many cases spends time directing these resources.  

    I just dont see a reason to get all worked up over these numbers.  If anything they highlight a processor designed to perform excellentky in the new workd of iOS software.  

  • Reply 69 of 77
    Alex1NAlex1N Posts: 37member
    Until we have the actually phones in hand, I would take these figures with a sack o' salt. 'Analysts' and others have been known to get things wrong before now. In fact, I personally would ignore this.
    edited July 2018
  • Reply 70 of 77
    palegolaspalegolas Posts: 1,274member
    Interesting with 4GB! The new A12 generation is supposedly 7nm too, which is interesting too. I hope It'll have a great impact on battery life.

    Benchmarks give no insight in the camera hardware, or do they? Is it hidden in there somewhere?
    What I'm mostly looking forward to at some point is a next generation camera sensor. Perhaps the QuantumFilm sensor?
  • Reply 71 of 77
    smalmsmalm Posts: 655member
    melgross said:
    We do know that physics is one area that Apple doesn’t care much about, likely because of Metal, which renders these physics scores as irrelevant.
    No. We do know that Futuremark did a miserable job with the physics tests.
    They even confirmed that: we know our implementation is bad but that's the way we do it and we won't change that...
    So yes, these physics scores are irrelevant.
  • Reply 72 of 77
    melgrossmelgross Posts: 31,475member
    smalm said:
    melgross said:
    We do know that physics is one area that Apple doesn’t care much about, likely because of Metal, which renders these physics scores as irrelevant.
    No. We do know that Futuremark did a miserable job with the physics tests.
    They even confirmed that: we know our implementation is bad but that's the way we do it and we won't change that...
    So yes, these physics scores are irrelevant.
    Physics tests show one basic thing. That is, the number of cores, even if they don’t perform that well, determines how well the physics score will turn out. When Apple went to more cores, their physics score jumped. It’s pretty simple.
    Alex1N
  • Reply 73 of 77
    Koll3manKoll3man Posts: 29member
    melgross said:
    Koll3man said:
    melgross said:
    No, it did not. All chips, particularly mobile chips, throttle under load, but the A11 throttles significantly less than any competing chip.

    You wish. Actually the A11 throttles faster and more than the Snapdragon 835 or 845.
    Anandtech made it very clear. Also the performance core on the A11 consume almost 3X more power in full load than S845's performance core.

    That nonsense. I’ve read all the reviews, and that not true.
    The thing you wrote is nonsense. Show me a link that proves that the A11 throttles significantly less than any competing chip.
    I bet you can't.
  • Reply 74 of 77
    Koll3manKoll3man Posts: 29member
    Koll3man said:
    melgross said:
    No, it did not. All chips, particularly mobile chips, throttle under load, but the A11 throttles significantly less than any competing chip.

    You wish. Actually the A11 throttles faster and more than the Snapdragon 835 or 845.
    Anandtech made it very clear. Also the performance core on the A11 consume almost 3X more power in full load than S845's performance core.


    Always funny when a new troll comes to the aid of an existing troll.
    Why are you such a desperate apple fanboy?
  • Reply 75 of 77
    tmaytmay Posts: 3,567member
    Koll3man said:
    melgross said:
    Koll3man said:
    melgross said:
    No, it did not. All chips, particularly mobile chips, throttle under load, but the A11 throttles significantly less than any competing chip.

    You wish. Actually the A11 throttles faster and more than the Snapdragon 835 or 845.
    Anandtech made it very clear. Also the performance core on the A11 consume almost 3X more power in full load than S845's performance core.

    That nonsense. I’ve read all the reviews, and that not true.
    The thing you wrote is nonsense. Show me a link that proves that the A11 throttles significantly less than any competing chip.
    I bet you can't.
    Show me a link that demonstrates an actual application affected by thermal throttling.

    I'll wait.
  • Reply 76 of 77
    Koll3manKoll3man Posts: 29member
    tmay said:

    I bet you can't.
    Show me a link that demonstrates an actual application affected by thermal throttling.

    I'll wait.
    LoL any application that keep the A11 close to it's limit for more than a few minutes will cause a thermal throttle. That includes video rendering apps, AR games or graphics intensive games.
    I don;t understand why is this up for discussion anyway, Anandtech compared A11's thermal performance against Android SOC's through test, it's not a product of their imagination. Melgross's statement is wrong so why are you defending it?

  • Reply 77 of 77
    tmaytmay Posts: 3,567member
    Koll3man said:
    tmay said:

    I bet you can't.
    Show me a link that demonstrates an actual application affected by thermal throttling.

    I'll wait.
    LoL any application that keep the A11 close to it's limit for more than a few minutes will cause a thermal throttle. That includes video rendering apps, AR games or graphics intensive games.
    I don;t understand why is this up for discussion anyway, Anandtech compared A11's thermal performance against Android SOC's through test, it's not a product of their imagination. Melgross's statement is wrong so why are you defending it?

    So, no links?

    I'm quite aware of mobile games that throttle, not just on iOS, reducing frame rate, or even worse, so I would assume that other applications that utilize the GPU do as well. Surprisingly few people are complaining about specifics on the internet, so it would appear that Apple has designed a well balanced device in the iPhone, based simply on a broad range of application usability. As I have stated elsewhere on AI, the iPhone X has an extremely high satisfaction rate, something not seen in any competitor device.

    I still don't consider the synthetic benchmarks for sustained GPU performance a relevant test, and you haven't changed my mind on that. More to the point, one could gather from the tests, that competitive devices, with a very few exceptions, throttle at about the same rate as the A11, the difference is that these devices tend to have much more powerful GPU"s, and, uniformly poor single thread performance compared to the A11; just tradeoffs.

    I'm quite satisfied with the direction Apple is going with the A series. It appears likely that you'll see a larger GPU on the A12, merely as it is Apple's second generation of in house GPU design, but that still might throttle under sustained, but much higher load than today.
    Alex1N
Sign In or Register to comment.