Earlier quoted context omitted.
This is the 12th generation Apple Silicon processor design. A4, A5, A6, A7, A8, A9, A10, A11, A12, A13, A14, M1
First generation of MacOS on Apple Silicon?
iOS has always used the same kernel as macOS.
2020 Mac Mini – Putting Apple Silicon M1 To The Test
331–340 of 767 posts
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#332Earlier quoted context omitted.
It's insane how bad the website's UX is for first time visitors not seeing there's more content behind the first page.
That's how websites used to fit more ads into an article before constantly-updating Javascript ads became the trend.
Yes, but with a big huge button "NEXT PAGE" or something like that. Look at the number of comments here that didn't even notice there's more content other than the 1st page.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#333Earlier quoted context omitted.
You overestimate how ALU limited Cinebench is. I managed to find an AVX vs AVX off benchmark run for Cinebench r20 [1]. Going from 128bit SSE to 256bit AVX and doubling the ALUs only results in a 10-12% increase in performance. I assume this has to do with how each SIMD lane of calculation might need to branch independently, limiting the performance speedup from just throwing wider SIMD ALUs at it. [1] https://www.te…
ELI5 please, how this change things for M1
There is more than one way to scale. Over the last decade, Intel had been pushing wider SIMD.
Instead of making your cpu able to execute more instructions per cycle, why don't you make each instruction do more work. SSE packs four floats/ints or two doubles/longs into a single 128bit register and then you can do the same ALU operation to each lane.
It works great on certain workloads.
With AVX, Intel increased the size of these registers to 256bit (eight floats) in 2011 and are currently pushing AVX512 doubles the width again (16 floats).
Apple, and ARM in general are limited to 128bit vector registers (though they are plans to increase that in the future)
Cinebench is well known as a benchmark which takes advantage of the 256bit AVX registers, and some people have speculated that Apple's M1 might be at a significant disadvantage because of this, with just half the ALU thoughput.
But these numbers show that while cinebench gets a notable boost from AVX, it's not as large as you might think (at least on this workload), allowing the M1's IPC advantage to shine though.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#334Earlier quoted context omitted.
I get why this idea of becoming iOS-like is uncomfortable for a lot of people, but will they take away the POSIX-ness of the OS? What about all the people that spend all their time in Vim, TMUX, Emacs, and/or zsh? I think these people will continue to be pretty happy on macOS if they already are. In my experience, installing alternate OS's on Mac hardware has never been frictionless or satisfying anyway.
I don't see why they would do this. If they just want to sell iPads, they could do that tomorrow. Just release XCode for Linux and Windows so that devs can create iOS apps and call it a day. Obviously they still intend for the Mac to remain a general purpose computer or they wouldn't be putting this much effort into it.
When GiorgioG speaks of a closed, iOS-style ecosystem, I don't think they mean literally running iOS on laptops.
Rather, they foresee OS X becoming a system where you can't run programs that haven't received Apple's blessing and been brought through Apple's store. Blessings that will be denied to software like youtube-dl.
As to why they would do this? A combination of the good of most users, who will enjoy protection from malware and viruses; and the irresistible temptation of a 30% cut of all sales.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#335Macbook air: $999 (2 ports, no hdmi) vs $699 mac mini (2 ports + hdmi) + ipad $329 = $1029 Thinking of upgraing, my current macbook 2013 sits in a drawer 99% of the time connected to a monitor and keyboard. That 1% of the time when I travel, the macbook is too large to use comfortably on an airplane seat. The ipad would work better for this use. macbook air also only has two ports, so one would be used for external m…
> macbook air also only has two ports, so one would be used for external monitor, the other for power. No place left to connect external drives.
You can do all this through one port. Most LG or Dell thunderbolt 3 monitors can supply 65 watts of power (some models may be higher, up to 80 or even 100w) any of which should be enough to run and charge this macbook air decently, and have 3 extra usb type A ports on the monitor.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#336It's certainly an impressive achievement and makes it pretty clear why Apple is transitioning away from Intel. I'm a bit surprised that the fact that this is on the TSMC 5nm process seems to be glossed over in the comments. Apple is benefitting from some what seem like on the surface to be significant process improvements. Will be interesting to see how other players take advantage of it as well.
No, the gains from Apple's A13 (TSMC 7nm) to Apple's A14 (TSMC 5nm and same cores as the M1) really aren't that large. About average for a node jump.
This is mostly about architecture, not silicon process.
From A13 to A14, Apple managed to increase the clockspeed by about 15% and increase IPC by 5% all while keeping power consumption the same.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#337Earlier quoted context omitted.
> The Zen3 processor that they are comparing it to is the 5950x - the fastest desktop processor with a TDP of 105W. The entire system power of the M1 mini under load was 28W. This is a very misleading statement. They primarily only used the 5950X in single-core tests, and in those tests it doesn't come remotely close to 105W. In fact per Anandtech's own results[1] the 5950X CPU core in a single-core load draws around…
> This is a very misleading statement. They primarily only used the 5950X in single-core tests, and in those tests it doesn't come remotely close to 105W. That’s true but keep in mind this is the power going into the AMD CPU only. The power number measured for the mini was the entire system power pulled from the wall, so that 28W included memory, conversion inefficiencies and everything. That’s crazy.
When we get to the detailed comparisons - it's almost impossible to compare without deconstructing the chips.
In the end it'll be a question of - can Apple scale it without incurring massive costs?
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#338I'm not buying into Apple's eventually-closed desktop computer systems - I don't care what the performance is. They've been slowly marching towards iOS's closed ecosystem model on the Mac and with an in-house CPU, they can effectively lock users out of alternate OS choices on their hardware. Buyer beware.
Going on internet comments they've been marching towards this for years. I've yet to see anything actually happen.
> Going on internet comments
So instead of going on evidence and public statements by Apple executives - statements that have repeatedly said the Mac is the Mac - you choose to believe random internet comments?
There is a delicate balance between protecting average users who have no clue what is safe software and what isn't vs allowing power users and developers to do what they want. Since the days of ActiveX controls we've know if you give users a "Please pwn me" dialog they'll just click "OK". They've been trained that computers put up lots of pointless dialogs they can't understand even if they take the time to read them so just click until it gets out of the way. Even with default security settings if opening an app from an "unidentified developer" fails you can go into System Preferences > Security and click "Allow".
macOS is trying to protect people by default while still allowing the HN crowd to turn these protections off if they so wish.
Apple Silicon Macs still allow you to disable SIP which turns off a lot of modern protections. You can still downgrade boot security. It is a deliberate decision to continue allowing ad-hoc code signing. Software can still be distributed outside the Mac App Store either with a Developer ID or without. The vast majority of Mac users don't know or care what any of these things are but the Mac has always allowed them and as Craig has said several times over: the Mac is still the Mac. It is still the system that supports hobbyists and developers - people who sometimes want to poke at the system, install their own kernel extensions, etc.
If your complaint is that things are not wide-open by default anymore then I don't know what to tell you. We don't live in the same software landscape we once did and there are far more malicious actors out there. Protecting users by default is the right thing to do IMHO.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#339I hope Apple allows us to install the OS of our choice. The battery life is impressive but I refuse to not use Linux.
They have already stated they won’t: “We’re not direct booting an alternate operating system,” says Craig Federighi, Apple’s senior vice president of software engineering. “Purely virtualization is the route. [...]” https://www.theverge.com/2020/6/24/21302213/apple-silicon-ma...
I realize Federighi's reply seems to rule out Linux, but the context of the question seemed to be with respect to Boot Camp and Windows. My take is that Apple doesn't want to continue to invest in Boot Camp, especially since Microsoft apparently isn't willing to license ARM Windows for this use case.
It's not clear to me that the new Macs won't allow booting Linux if the Linux community can figure out how to do it. The number of folks booting Linux on Mac via Boot Camp has to be really tiny.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#340Earlier quoted context omitted.
Not to mention 5950X alone without cooling ($799) costs almost as much as an entry level MacBook Air The M1-based Mac mini starts at $699.
Yeah, forgot about that. Everything else being equal (ostensibly), the M1 Mac Mini is $200 cheaper than the crappy Intel i5 Mac Mini, more if you upgrade the Intel CPU. As an owner of a decked out 2019 Mac Mini, in hindsight I made a shitty purchase decision.
Why?
Today's purchase of Mac Mini will be a crappy decision in hindsight in about a year... and that is true every year.
It would have been a crappy decision - if you got a worse product at the time of purchase. So don't get FOMO.