First Apple Silicon Developer Transition Kit benchmarks show Rosetta performance impact

13»

Comments

  • Reply 41 of 48
    tipootipoo Posts: 1,158member

    So, not even trying to make a shipping ARM mac chip, a two year old tablet SoC translating a more complicated x86 ISA to ARM still performs better than the Qualcomm SQ1 in the Surface Pro X running native, or just above a 2012 iMac, which while old is still a 91W TDP and running its own native ISA benchmark, again.

    Man, the silicon when they’re actually trying is going to be bonkers insane.

    right_said_fredchiawatto_cobra
  • Reply 42 of 48
    rob53rob53 Posts: 3,309member
    Everyone is talking about it using Rosetta 2. Has anyone simply tried running the iOS version of Geekbench 5? Keynote shows this is possible but not sure how you'd get the iOS app onto the DTK. If it can be done, then it wouldn't be using Rosetta at all, just the iOS version, which runs on the A12 chip.
    watto_cobra
  • Reply 43 of 48
    thttht Posts: 5,685member
    rob53 said:
    Everyone is talking about it using Rosetta 2. Has anyone simply tried running the iOS version of Geekbench 5? Keynote shows this is possible but not sure how you'd get the iOS app onto the DTK. If it can be done, then it wouldn't be using Rosetta at all, just the iOS version, which runs on the A12 chip.
    AFAICT, Apple has turned on this feature yet. Maybe someone can hack it on, but the wait will be longer regardless. Eventually, more apps will be transitioned and the best kind of benchmarking can be done: ones that use applications that people may use.
    watto_cobra
  • Reply 44 of 48
    MplsPMplsP Posts: 4,038member
    jdb8167 said:
    hattig said:
    jdb8167 said:
    I’m pretty sure Rosetta only uses the “big” cores which is why these results show up as a 4 core CPU and not 8. You also can’t rely on the reported clock speed. These results are from a kit that isn’t supposed to be benchmarked running an x86-64 translation to Aarch64. They shouldn’t be used to infer anything about native ARM performance. 

    It’s also interesting that the date of the tests were from before WWDC which likely means they came from a developer with very early access. 
    Rosetta is a translator, rather than a runtime emulation. Even the JIT feature will be implemented by translating finalised Intel Code into ARM (when you mark a memory page as executable post-JIT, Rosetta kicks in and does its work - I guess). **HOWEVER** there will be some things that need to be trapped as they are not emulateable, and therefore I suspect Rosetta provides a very thin VM/system layer around the executable. Also binary translators really cannot infer intent, so there is only so much they can do - they will generate code that is less optimal, especially when coming from x86 with all its quirks.

    Yes, these are likely in-Apple or in-close-third-party leaks.
    It looks like Apple Insider got the dates on the Geekbench entries wrong. They are from June 29th not June 20th. So it does look like they from a released DTK. (And someone might be getting a note from Apple very soon since this is expressly prohibited by the NDA.)
    Apple Insider had a ‘hands on with the new ADK’ a few days ago that has mysteriously disappeared. Hmm...
    watto_cobra
  • Reply 45 of 48
    BeatsBeats Posts: 3,073member
    People who think the A12Z Mac will be the final product are not thinking are they?

    These kits are EXACTLY what they say on the box: "Developer Transition Kit". It only exists to give developers a jump start and to have a variety of programs available day one.


    Craig Federighi:
    "But it can give you a sense of what our silicon team can do without even trying"


    3:29 he explains the obvious. The chip is NOT intended to ship in the final Mac.



    Just for fun:

    edited June 2020 watto_cobra
  • Reply 46 of 48
    SpamSandwichSpamSandwich Posts: 33,407member
    DAalseth said:
    hattig said:
    Aside: The bottom-of-article comment form is so horribly broken I'd rather that there was just a link to the forum only.
    that is so true. I don't even bother trying to post there. I just go the the forum and go from there. Like the update to the AI site. Hate how kludged the comments are now.
    Honestly, I haven’t gone to the “front page” of the site in many, many years. My bookmark directly to the forums saves me time.
    watto_cobra
  • Reply 47 of 48
    XedXed Posts: 2,881member
    chaicka said:
    Wondering what if the production A-based Macs coming end of the year actually ship with an A14Z chip instead (since A14 is going to be in this year's iPhone 12s), and that chip includes plentiful of specific-advancements meant for Rosetta 2 and Big Sur as compared to the A12Z in DTK?

     :D 
    I’m expecting an entirely different designation for their ARM-based Macs. 
    eriamjhwatto_cobra
  • Reply 48 of 48
    gregalexandergregalexander Posts: 1,401member
    Is it odd that no further articles on performance have surfaced?

    It must be atleast possible for developers to load their own software and compare speed on the transition kit to other Macs... so I assume that means Apple has cracked down on the leaks?
Sign In or Register to comment.