hattig

About

Username
hattig
Joined
Visits
24
Last Active
Roles
member
Points
374
Badges
1
Posts
860
  • Apple posts ARM-compatible source code for XNU kernels in iOS & macOS

    I agree that the Mini could be a great test bed for the concept and for encouraging future migration of applications.

    An A11X in Spring, >3GHz, 4+4 cores, 12 GPU cores, 8GB LPDDR4X... could be a nice little machine for casual Mac users. And the same chip at a lower speed could be used in the iPad Pro 2018.

    Don't tell me that the A10X in the AppleTV 4K isn't being used en-masse within Apple to repeatedly test MacOS X and certain applications for issues. Well, okay, you can suggest it's not, that's a possibility.

    This is a clue. Maybe it's just a clue for Intel to give better pricing, but maybe it's not.
    schlackwatto_cobra
  • With iPhone 8, Apple's Silicon Gap widens as the new A11 Bionic obliterates top chips from...

    TBH the main thing remaining is for Apple to integrate the modem into the SoC. Samsung only use Snapdragon in the US because of the modem differences there. Exynos is everywhere else. Exynos really is the closest chip in spirit to Apple's (because only Samsung use them these days), but Samsung don't appear to care too much about leading the market, instead being content to roughly match the equivalent Snapdragon in performance. The M1, M2 cores that Samsung uses appear to be lightly modified basic ARM core designs. Even Qualcomm have gone this direction with their latest Kryo cores. Apple have taken control of their chip design future, and have the money and the sales to drive this forward for the foreseeable future. It's unlikely that ARM is going to launch a mobile core that will compete on single-threaded performance anytime soon, and now that Apple have fixed their multi-core processing to use all cores, even the traditional "octo-core" method for other SoCs to get great scores has been surpassed. I can't see any other SoC outperforming the A series SoCs in CPU/GPU for many years (Kirin 970 on-paper has a more powerful AI core, we should find out more within a month or so, I note an AI core is only as good as the learning applied to it which Apple surely has not skimped on). Still, performance is not everything in a phone, but it's not like A11 appears to have compromises in other places like battery life. Like many, I would really like to see an A11 or later SoC (likely a different enhanced design that is optimised for this usage) running OS X on a laptop. Let's see what the additional TDP headroom can do in these form factors.
    Muntzpatchythepiratewatto_cobra
  • Apple's A11 Bionic matches single-core 13" MacBook Pro performance in alleged benchmark

    Remember that a phone has a very low power usage, the SoC might be allowed 2 or 3W, maybe 5W turbo for small periods of time. In a laptop, even a thin one, Apple could allocate 15W to the SoC. That would mean that instead of 2.5GHz Apple can push the clocks (if the design allows it). If Apple are planning to use their cores in laptops, then their design should cater for higher speeds. Additionally, the chip would be able to maintain those speeds without throttling down. A11 also has a revamped uncore that should be able to keep the cores fed with data better. That was likely a reason the A9X benches mentioned previously were good at micro-benchmarks, but not so good when compared in real world use. The A11 core is powerful for its clock. Assuming that the A11 Geekbench results are correct, and are at 2.5GHz (i.e., the A11 doesn't have higher turbos for short periods), at 3GHz it could be getting over 5000 points in single-threaded Geekbench. At 3.5GHz nearly 6000. A quad-core (4+4) laptop variant (A11X I guess) could get multithreaded scores at 3GHz of 16000, at 3.5GHz 20000. Obviously real-world performance probably would not reflect this due to the nature of the benchmark, and scaling to new peaks is a massive difficulty compared to catching-up most of the way, but Intel should not be sitting comfortably. Because if Apple can beat Intel's performance, and for a lower price, it doesn't seem hard to realise that this would be a major advantage over PC OEMs stuck with Intel/AMD. Switching to their own SoCs is the sensible business decision, once software issues are dealt with. Ice Lake is probably Intel's last chance (I don't think Apple would be in a position to switch until 2019/2020 with an A12X or A13X (A14X?).
    watto_cobra
  • Leaked part could show Apple's 'iPhone 8' wireless charging coil assembly

    Haha, that's about 2mm thick, no way that's going into a phone. The phone will have a much thinner, neater printed coil. No, if that's a real part, then it's for the charging pad.
    cornchipwatto_cobra
  • Apple Park consumed more by parking space than actual offices - report

    So 14000 people, and the local government wants 34% of them to not use cars. Therefore, the local government makes Apple install 11,000 parking spots, when 9240 would be enough to meet the other rule. But, that auditorium holds 1000 people, and I can bet they'll all drive in. So they're catered for. And then some more for rainy days where more people come by car rather than bike. And I'm sure there will be hundreds of people coming for meetings every day needing spaces. So it seems reasonable.
    Soli