Intrigued by the single-thread main memory bandwidth being a multiple of what you get from a single SKX. We also see this with Graviton 2. The latency is not terrible, either. How would this much available bandwidth change your choices when optimizing your algorithms?
2020 Mac Mini – Putting Apple Silicon M1 To The Test
221–230 of 767 posts
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#222Macbook 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…
I switched from a MBP to a Mac Mini and iPad Pro last winter for my personal setup. I absolutely love it. I spend roughly equal time on both, but I’m not doing a ton of programming these days outside of work. Taking the iPad traveling is way easier than taking a laptop.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#2231) Can I run VirtualBox on M1 (yet)? 2) What is the overhead of doing so with Rosetta2 vs native on Intel? 3) What is the situation with VT-X?
You may be interested in this thread:
https://forums.virtualbox.org/viewtopic.php?f=8&t=98742
tl;dr: VirtualBox is an x86/x86 hypervisor, there's no porting to do. It would be a re-write.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#224Performance per watt of this thing is INSANE, take a look at the battery left after compiling WebKit, compared to older Mac: https://techcrunch.com/wp-content/uploads/2020/11/WebKit-Com... https://techcrunch.com/2020/11/17/yeah-apples-m1-macbook-pro... IMO the all day battery will be THE killer feature of the new laptops.
These gains are just through improvements in processors. Now, combine that with parallel leaps for battery tech... It's also good that battery tech hasn't jumped too far ahead already - the constraint has helped in the development in these mobile chips. The display panel is still the biggest energy draw on my laptop. There's a lot of chance for improvement there too. A 2 day battery in 5 years isn't that crazy.
Apple is the kind of company that will choose to slim down the laptop instead of making it 2 day battery life.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#225Performance per watt of this thing is INSANE, take a look at the battery left after compiling WebKit, compared to older Mac: https://techcrunch.com/wp-content/uploads/2020/11/WebKit-Com... https://techcrunch.com/2020/11/17/yeah-apples-m1-macbook-pro... IMO the all day battery will be THE killer feature of the new laptops.
This metric is hilarious and perfect.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#226Wow it must suck to be Intel right now. It wasn't so long ago that the trope was while others had better multi-core performance "...Intel still holds the lead for single core performance" Now not only do AMD have a better product, but also Apple now offer equal or better performance than the best that Intel can offer. I wonder what is next for Intel now their £1000+ CPUs are firmly in third place. Looking forward to…
Market share x86 overall (mobile + desktop + server), AMD vs Intel:
Q3/2020 20,2% vs. 79,8%
Q2/2020 19,7% vs. 80,3%
Q1/2020 17,5% vs. 82,5%
I don't know why the OEM business works that way, but it is very slow to shift, so Intel still has time. Self-built consumer PCs for gaming are already overwhelmingly AMD though.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#227This might get me back into the Apple ecosystem. I'll still wait for the kinks to be ironed out in the first generation though.
I feel the same way. Very interested, but not going to go in for first gen.
This is the 12th generation Apple Silicon processor design.
A4, A5, A6, A7, A8, A9, A10, A11, A12, A13, A14, M1
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#228Dave2D found the air to be on par with the Pro, at least for tasks that took under ~8.5 minutes. It only really throttled after that point, according to him.
Here's one data point: a WebKit compile took 25min on the Air vs 20min on the Mini/Pro. That 25min is still a bit faster than the Intel 16-inch Pro, which took 27min and waaay faster than Intel 13-inch Pro at 46min.
The crazy thing is that both M1 MacBooks still had 91% battery left after the compile, vs 61% on the 16-inch Pro and 24% on the 13-inch Intel Pro.
[1] https://techcrunch.com/2020/11/17/yeah-apples-m1-macbook-pro... -> "Compiling WebKit"
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#229Earlier quoted context omitted.
Eminent Internet speculation about Apple is correct surprisingly often. EDIT: I'm getting downvoted, maybe because I was too cryptic. To clarify, it seems like the rumors that gain traction with mainstream sites and Apple-focused YouTube channels and forums tend to have strong correlation with something that will happen later.
This speculation has been going on for years. They're not going to remove the ability to run arbitrary code or the unix core. There would literally be no reason to buy a mac over another product of theirs.
I suspect there is an element of truth to it. I agree they will keep the Unix core and allow you to use clang and ld however you want. I suspect, however, they're not interested in supporting alternate OS's nor are they interested in allowing typical users to download normie GUI apps from anywhere.
Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test
#230Earlier quoted context omitted.
Only in single threaded performance, which nobody actually uses for rendering. In multi-threaded, the Ryzen 5950X is at 28,641 while M1 is at 7,833. So no, the Mac Mini is maxing out at 27% of the Ryzen 5950X if you use it properly. And I was already friendly and used the M1 number for a native port, while in reality you'll likely need Rosetta and take a 33% performance hit.
I think the overall point is that for the average user, who doesn't need all those cores or could make good use of them, the M1 may in fact feel / be faster. For users like you or I, of course we'd see a huge difference, but not everyone is running workloads that need more than 2 or 4 cores.
An average user is going to buy a 5600X or whatever not the 5950X, and the 5600X's single-threaded performance is barely behind the 5950X. You only get a 5950X if you want multi-threaded performance.