Geekbench results for the Apple-silicon-Developer Transition Kit surface online
At the WWDC20, Apple has announced its next big change for the Mac—way of Intel processors Apple-designed silicone. It is a great thing, and the first products will be available to consumers later this year.
In the meantime, Apple’s Developer Transition Kits makes some developers so that you can begin to re-compile and optimize your Mac-apps. The DTK is a Mac mini case with a A12Z system-on-chip inside (the same as in the current iPad Pro). It has 16 GB of RAM and a 512 GB SSD, and a special version of macOS Big Sur, and Xcode development tools.
For Mac apps to be updated, compatible with Apple silicon, the new Macs will translate to an automatic emulation tool called Rosetta apps on Intel processors. And now that the DTKs to are-to-ship-developers, we have an early look, what kind of performance could give us.
Early Rosetta Geekbench results
The Geekbench results database currently shows eight benchmark results of the DTK. Since Geekbench is not yet available, a new universal set-Apple/Intel Mac app to show these results, what the DTK is capable of, when you have an app with the Rosetta translation.
The scores typically fall in the low-800s for a single core power and around 2,800 or so for multi-core performance.
How does that stack up to other products? The same A12Z-processor, running native code on an iPad Pro, scores over 1,100 for single-core and 4,700 for multi-core. The iPad Pro is about 25 percent higher on single-core performance and 40 percent more multi-core performance.
The latest MacBook Air, with its entry-level processor that achieves around 1,100 for single-core and 2200 for multi-core. And an entry-level Mac mini (which was not updated, since from 2018) scores in the high 800s for single-core performance, and around 2,500 for multi-core.
So the Mac Developer Transition Kit, a Computer with an Intel-based benchmark under the Rosetta emulation/translation, adopts big – hit compared to native performance. But Apple chips are so fast that it still runs roughly in the same ballpark as an entry-level Mac mini, 2018, or an entry-level MacBook Air from this year.
This is very good news indeed! Unless Geekbench is a very positive outlier is, how it looks, and Mac apps for the Intel chips and runs under emulation can be expected to run almost as good as the modern low-power Intel processors. You will probably not be thrown back to the stone age, if you need to run an app that was not updated, the natively on Apple silicon.
Good news, but not the preview of the final results
This is rather interesting, in an academic sense, but one should not read too much into it. It could be a preview of what kind of performance hit some applications under emulation, and it may not, but it is nearly sure, that’s what you can expect from the new Apple-silicon-Macs, which will go on sale this year.
to start with, macOS, Big Sur is still in beta, and the Rosetta optimization technology, a further optimization.
What’s more, didn’t Apple just throw in the plan to an iPad-Per-chip in its next Macs. Apple has said it is working on a “family” of Mac-specific SoCs, so that we can’t expect that something tailored to the Mac performance. That probably means that changes in the architecture that are suitable to the higher power, boundaries, and relaxed thermal environments of a Mac, and not to forget the window-multitasking environment and high-end professional apps.
Finally, the Rosetta-emulation-can be tuned in software to run better on this upcoming Mac processors than on the A12Z. The current emulator can be tuned to the new chips in such a way that it runs in some hard bottlenecks on the DTK, which will not be available on the new Macs (say, in the expectation of a much larger L2 cache).
In other words, Rosetta on the new Macs can’t cover with a fee of 25 to 40 percent of the hits to performance on this DTKs, and even if it does, it is probably from a higher power.
Released on Mon, 29 Jun 2020 18:30:00 +0000