Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

2020 Mac Mini – Putting Apple Silicon M1 To The Test

anandtech.com

Post reply on HN
Print view View original

281–290 of 767 posts

Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test

#281

Post by konart »

GiorgioG wrote: post #38

I'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.

>they can effectively lock users out of alternate OS choices on their hardware

People buy mac to use macOS. Some will also use bootcamp for windows if VM is not enough for their tasks. And installing linux instead of macOS on a mac even sounds strange.

So - nothing to be aware of. Macs always were build to run Apple OS

Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test

#283

Post by JAlexoid »

formerly_proven wrote: post #203

The Cinebench R23 results seem kinda weird to me. The 5950X would have almost a 40 % clock speed advantage over the M1 (~5 GHz 1C vs 3.2 GHz 1C), yet the M1 is only about 8 % slower in an entirely ALU-limited SIMD benchmark? This suggests the M1 core has like 50 % more EUs and achieves much higher throughput than Zen 3. The SPEC results are... decisive to say the least. Without Zen 3, x86 CPUs would look, well... lik…

Intel's CPUs have been getting remarkably worse for a long time now.

They trail the software improvements. To give you an anecdote - I got a ThinkPad T430s and it made my work feel 10x faster(Java EE development in 2012). I got my next ThinPad P51s in 2017 - an it was just one huge disappointment. It felt like Intel was stepping back. I now have ThinkPad P1 and computing power is still just OK, though still better than the U class i7 in P51s.

I'll be happy to knock Apple for marketing BS("3 times faster", etc). But Intel has shown that they just need to crumble. I hope that my next laptop is not using Intel's ISA or cores.

Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test

#284

Post by ogre_codes »

rowanG077 wrote: post #200
foldr wrote: post #194

Earlier quoted context omitted.

"Only". It would probably be easier for them to maintain the Linux drivers themselves than to thoroughly document every feature of the SoC. It's not just about individual drivers though, it's about the surrounding kernel infrastructure and the whole desktop experience. For example, getting instant suspend/resume working on Linux is not (I'm fairly sure) just a matter of writing a driver for a particular bit of hardwa…

They don't need to anything new. What they already have is enough. Their own software engineers could handle it fine. It's good enough for people who want this. There are people who have clean room implemented entire nvidia drivers. Without doc. We can manage fine with whatever incomplete doc Apple allready has.

It's been a few years since I used Linux so forgive me if I'm off base here. But last time I used Linux with Nvidia, you had the choice of using FOSS drivers with mediocre performance, or having closed source drivers that performed on-par with Windows.

Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test

#285

Post by vdfs »

diimdeep wrote: post #255
phire wrote: post #233

Earlier 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

ELI5: Some things that ARM can do in one instruction, can be done with multiple instructions on x86

Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test

#286

Post by alwillis »

geerlingguy wrote: post #55
fxtentacle wrote: post #39

Earlier 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.

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.

It’s hard to imagine a regular person playing games or editing the family photos or editing the kid's birthday party videos aren't using multiple cores for almost everything they do.

Even browsing the web these days uses multiple cores.

Apple wouldn't have made the investment if people couldn't see and feel real world results.

Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test

#287

Post by andy_ppp »

offtop5 wrote: post #256
bstar77 wrote: post #215

Earlier quoted context omitted.

AnandTech isn't the only one providing benchmarks, they are rolling in from all over the place now. People are running 15 minute finale cut pro jobs and the fan isn't kick in on the macbook pro.

Any word on if Final Cut and Logic X are recompiled for Arm ?

If they are Apple they are Universal apps I believe?

Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test

#288

Post by xuki »

Brendinooo wrote: post #272
xuki wrote: post #224

Earlier quoted context omitted.

Apple is the kind of company that will choose to slim down the laptop instead of making it 2 day battery life.

Do you think that's still true in 2020? Seems like thinness hasn't been a major consideration for a couple of years now.

They're doing it again with the new iPhone. All of this year iPhone have a smaller battery.

Re: 2020 Mac Mini – Putting Apple Silicon M1 To The Test

#289

Post by JAlexoid »

tonyhb wrote: post #248
em500 wrote: post #228

Earlier quoted context omitted.

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-macb…

This is insane perf/watt. x86 backwards compatibility may have gotten us to where we are, but it's certainly holding it back. Arm is looking great, and maybe it's time for x86 to die.

It's time for Intel and x86 to die.

But I would also be a little wary, because ARM systems are way more locked down than x86 systems today.

Post reply on HN