Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
Geek bench for Mac isn’t written originally for ARM 64. It’s written for X86. Native performance of this chip can easily be seen by just looking at the iPad Pro bench mark.
Not really... The chip is the same, but the iPad system is quite different. I suppose they could have just put an iPad processing board in there, but I suspect they did something custom for the Mac form factor and peripheral set. At the very least, they hung more RAM off of it.
The down clock is odd. I wonder if that's an artifact of running under rosetta or if the chip is really under clocked. Yes, I know it isn't indicative of the performance from consumer machines, but I am looking forward to the inevitable ARM-based benchmarks. Imagine Geekbench has a vested interest in riding this publicity wave.
It‘s probably something to do with interfacing to either memory or some peripheral bus.
 
Apple's Arm-based Macs that run Apple Silicon will have new chips designed for the Mac and based on the A14 chip created for the 2020 iPhone lineup with a 5-nanometer process.
This sounds an awful lot like a guess. I don’t recall Apple saying anything about how linked the forthcoming Mac processors are to the upcoming (not yet named but presumably A14) iPhone processors. They might be based on the A14, or they might just be relatives.
 
This is why Apple will succeed because they make their product for diehard simps. Unless AMD is supplying Apple with its next RDNA2 GPU, MacBook Pro will get demolish in video production. But hey, writing a novel and browsing the web on safari will be stylish.
I guess you are just a gamer, and thats it. When the next arm 13" mbp will be crushed by the 13" Intel igpu, we will talk (so, i guess never)
And for the 16" i bet Apple will release that arm based in 2021 with a room to breath, not the hot cake that is now, when the cpu reach over 90C with less room for your dGpu to breath
So its clear you are just a gamer and dont understand video production, or video editing and so on, and thats what a mac is about. For games please check windows or console section
 
It’s not a 100% fair comparison though. the Mac mini has a cooking fan for sustained performance. The surface is a tablet primarily.

Is there a fan on these boxes? I doubt it. I have a 2012 mini i5 and I've never heard the fan turn on, even during a multi-week handbrake encode. The proc in these is even lower power than the i5. In fact, the SSD probably runs hotter than the processor.
 
To get to a level of a xeon processor it is going to take Apple about 4 years, and Intel is still going to be improving the Xeon workstation and server processors. So if you need a machine now you might as well get it and in 4 years then evaluate xeon vs Arm. I loved the PowerPC and it was a RISC processor but Apple has a long way to go to get to a workstation/server level. Get a machine get Applecare and enjoy a system for the next 4 years. Yes they should be about to match a i5 soon but then the i7 and then the i9.
Why? There are already 80 core ARM processors which are faster than a 28 core Xeon.
 
The main weakness of virtualization products like Parallels and VMware on the Mac has always been GPU performance. While CPU tasks run at near native speeds under virtualization, the same can't be said about GPU performance. Despite all the marketing from Parallels and VMware about improved graphics performance with their products, it still does not come close to native. This is why gamers use Boot Camp.

Even if Windows for ARM becomes popular and lots of Windows developers start making applications and games for ARM, virtualization on ARM Macs would still have the issue of GPU performance. Supposedly, this has been addressed on the PC side so VMs running in VMware for PC can access the full power of the GPU. VMware previously said they were unable to do the same thing on the Mac due to lack of support in MacOS. Which is also why there is no graphics acceleration for MacOS VMs in VMware Fusion. Will the updated virtualization support in Big Sur address GPU performance for VMs?
 
  • Like
Reactions: nickgovier
Qualcomm SoCs for Windows on ARM are not great though. 8cx is a disappointment. ARM have never cared about the performance sector until recently (A78/X1 are far better).

Not great? With respect to what reference? SQ1 is the fastest SoC which runs Windows with 7W TDP - e.g. which you can put into a slim passively cooled tablet.
With other words, any other SoC from Intel with 7W TDP is actually slower than the SQ1 - this is including Intels latest 7W Lakefield SoC. So from which angle SQ1 could possibly be a disappointment?
 
  • Like
Reactions: skabichevsky
There are an awful lot of people on here who posted hundreds of times that arm cannot possibly run fast, so they may be surprised. (Though those people will point out that we are comparing one arm to another...)

I've been discussing for a long with this kind of people about the, back then, "rumoured" ARM macs. I learned 2 things all this time: 1. they never do any decent research, they just parrot what other people said somewhere 2. they are just denial

When geekbench scores appeared, Geekbench wasn't making a fair comparision between OSses/platforms. When an iPad Pro was shown rendering the same video and same quality faster than a MBP 15", it was due to the app being more efficient than FCP or just different quality settings. When this benchmarks came, oh well it's underwhelming and Intel and AMD beats it (while comparing 28W laptop to 7W tablet chips). And when the ARM Macs are released in this fall, it will be some other excuse like no software compatibility/it's a toy laptop. But they won't ever recognize ARM can be designed for high performance and even beat x86 on the same tasks.
 
If you watched the keynote, they mentioned that they will be making a specific line of processors for the Macintosh. It will share the same architecture, hence the DTK, but it may not even be called an A14. Could be called B14 or perhaps a A14M.. They aren’t just taking the chips from the iPad and slapping them into a computer going forward. That’s only for the DTK.

I'm really hoping they go with a "M*" naming scheme for the Mac chips? This year M14, then M15, then M16 ...
 
I've been discussing for a long with this kind of people about the, back then, "rumoured" ARM macs. I learned 2 things all this time: 1. they never do any decent research, they just parrot what other people said somewhere 2. they are just denial

When geekbench scores appeared, Geekbench wasn't making a fair comparision between OSses/platforms. When an iPad Pro was shown rendering the same video and same quality faster than a MBP 15", it was due to the app being more efficient than FCP or just different quality settings. When this benchmarks came, oh well it's underwhelming and Intel and AMD beats it (while comparing 28W laptop to 7W tablet chips). And when the ARM Macs are released in this fall, it will be some other excuse like no software compatibility/it's a toy laptop. But they won't ever recognize ARM can be designed for high performance and even beat x86 on the same tasks.


Yep. That's why it's always fun to *try* and get them on the record: if you think Arm isn't good enough, specify exactly what software you need to see on these new Macs, and exactly what quantitative performance level you need to see (benchmark, the time to perform some specific operation, whatever), in order to admit that Arm is good enough.
 
Not great? With respect to what reference? SQ1 is the fastest SoC which runs Windows with 7W TDP - e.g. which you can put into a slim passively cooled tablet.
With other words, any other SoC from Intel with 7W TDP is actually slower than the SQ1 - this is including Intels latest 7W Lakefield SoC. So from which angle SQ1 could possibly be a disappointment?
From the angle of this entire thread: the SQ1 vs the A12Z.
 
  • Like
Reactions: rbgaynor
But they won't ever recognize ARM can be designed for high performance and even beat x86 on the same tasks.

Just let me make one thing clear, ARM chips outperforming X86 chips (everything else being equal) is the expectation and not surprising at all. The ARM architecture is just so much better than the aging x86, that you can design much higher performant SoCs using the same resources (e.g. area and power).
x86 actually beeing as performant as ARM would actually be the big surprise!
 
I guess you are just a gamer, and thats it. When the next arm 13" mbp will be crushed by the 13" Intel igpu, we will talk (so, i guess never)
And for the 16" i bet Apple will release that arm based in 2021 with a room to breath, not the hot cake that is now, when the cpu reach over 90C with less room for your dGpu to breath
So its clear you are just a gamer and dont understand video production, or video editing and so on, and thats what a mac is about. For games please check windows or console section

I'm a gamer.

Earlier this year I finally just invested in a dedicated Windows machine for gaming.

It's a MASSIVE relief to not have to worry about what changes Apple is making that may affect gaming. To not have to maintain a separate Boot Camp install. To just sit down and play my games while having MacOS running just to the right so I can do other things while I play. It's also nice to have a Windows machine around to run the occasional Windows-only software, like Hackchi to add games to my SNES Mini.

If you can do this, I highly recommend it. Then you can use each computer for everything it's best at.
 
From the angle of this entire thread: the SQ1 vs the A12Z.

But how can it be a disappointment if it is still the fastest 7W SoC, which runs Windows. Something else being faster but currently only runs iOS does not make the SQ1 a disappointment.
This might change next year, when you can run Windows also on Apple silicon - but as of today SQ is still the fastest (for such devices). And even then, this depends on Apple releasing Windows drivers for its SoC.
 
Does anyone have speculation as to why they didn't use their fastest A-series chip, the A13, for this developer Mac?

Because A12z has more cores and a larger GPU - it is a higher TDP SoC after all - closer to what you can expect in a Mac.
 
  • Like
Reactions: CarlJ
Does anyone have speculation as to why they didn't use their fastest A-series chip, the A13, for this developer Mac?
They don't want to show what they got also the GPU on the A12Z is faster (more cores) then the A13 one, they haven't made a A13X probably skipping for a A14X and that not is not available yet. Making a A13X just for this would be waste of cash.
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.