Live data from Hacker News

2020 Mac Mini – Putting Apple Silicon M1 To The Test

anandtech.com

451–460 of 767 posts

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

#451
post #162

This is as much a ringing endorsement of AMD Ryzen as it is of the M1. The 15W 4800U is just as impressive as the M1, and the performance per watt gap seems small enough to bridge with AMDs upcoming 5nm switch.

AMD definitely is the best of the rest, but it doesn't seem quite as close as it may be held to.

In single core tests the 4800u is running that core at 4.2Ghz. Yet it gets soundly bested by the M1 @ 3 - 3.2Ghz (running at a 50%+ advantage, 65%+ clock per clock). The M1 has an enormous IPC advantage.

In a multicore test the 4800u has 8 performance cores with HT. It only marginally beats an M1 with 4 performance cores and 4 efficiency cores (by the scaling the efficiency cores look like they're 1/4 performance or worse -- these are very lightweight cores).

Again, it's the best of the rest, but Apple clearly holds an enormous lead here. Somehow everyone is focused on 5nm, but the A13 on 7nm was still in a substantial lead. The 4800u on 5nm is only going to be marginally better.

Apple clearly sandbagged this first entrant because they're packing it into their "entry level" devices. In six months or whatever they'll unveil the 6+2 core device in the mid range, the 12+2 in the high range, etc, and we'll be back at these discussions.

(Speaking generally) - This whole discussion about Apple Silicon is fascinating because the goal posts have moved so much. Looking back to HN discussions a year ago and everyone was talking about some pathetically weak entrant that would be a joke, etc. Now people are celebrating that it doesn't beat a 24-core, 300W Threadripper. Now the narrative is that it isn't impressive because the v1 didn't overwhelming destroy everything else in the market.

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

#452

Earlier quoted context omitted.

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 control…

Are you sure you’ve replied to the right comment?

I was literally making the point that these rumours have persisted for years and nothing has ever come of it.

I couldn’t agree more with the rest of your comment!

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

#453
post #13

Dave2D 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.

Having the experience (or, love/hate relationship - so awesomely thin and quiet, so underpowered) with 12" Macbook, one surprise is that throttle time really depends on environment temperature and GPU use.

In a cool room it can last few minutes before throttling, while outside on a warm day it throttles almost instantly.

Also, a thermal budget is shared with GPU, so once you plug-in the external display, or start Sidecar, you run out of thermal headspace pretty much instantly.

I'd love to see these two factors tested.

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

#454
post #201

Earlier quoted context omitted.

Couldn't the Pro just turn on its fans after 8-9 minutes (to avoid throttling), thus giving the best of both worlds?

Best of both of worlds is: - active cooling - lack of a touchbar

That would be the Mac Mini.

But seriously, I share your opinion on laptop keyboards: regular function keys please.

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

#455

Earlier quoted context omitted.

For most everyday work - Raspberry Pi is fast enough, so it's not even an argument. Raspberry Pi 8GB is 10x cheaper? There are mini desktops starting at $250 that will do everyday work. If you throw in "everyday work" - then we have passed the need for new chips altogether.

> For most everyday work - Raspberry Pi is fast enough That really stretches the meaning of 'everyday work' quite a lot. The pi is dog slow, even compared to an Intel i9 ;)

That's a bit of an overstatement. Booting from SSD instead of SD card has an enormous uptake in performance. I have yet to hear of a Pi 4 that couldn't overclock to 2GHz which is a pure uplift of 25%. Moving to 64-bit PiOS gives another double-digit jump in performance too. Not record-breaking, but not unusable either.

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

#456

Earlier quoted context omitted.

The iMac will be replaced with a custom-built PC. The MacBook Pros are another story. I don't know. I can't see me buying any new Intel Macs since they'll be phased out at some point. I've never had much luck with the Dell XPSes. I may give ThinkPads a look (I have a P50 at my current job which has been fine (if not for all the corporate antimalware slowing it to a crawl.))

Thanks for the response. I'm hesitant to move my family away from Macs because they have been relatively easy to support.

I'm hesitant as well, for the same reason. Having said that my personal PC (desktop) is still running well 3+ years after initially installing Windows on it. My inlaws' very old laptop is still running fine (it's at least 8 years old and was upgraded (on accident!) from whatever version of Windows it was running prior to 10.) Aside from user errors (accidentally installing adware toolbars in Chrome, etc) there really hasn't been any real issues as it pertains to Windows itself.

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

#457
post #248
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.

Honest question. Does the ISA, as a language, really matter? Or is it more a by product of who owns the ISA, eg intel sucks, arm is more liberally licensed.

I used to work at intel, and no one I knew there thought ISA mattered at all. That’s just a few people though, so I’m curious if people think there’s something better or worse about the different ISAs as a technology in their own right, or if it’s more about the business interests behind them that matters.

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

#458
post #212

Earlier quoted context omitted.

> 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 20w. It would seem that the switching of AMD chips in the various graphs have caused some confusion. I was referring to the "Geekbench 5 Multi-Thread" graph on page 2. This…

If you're referring to the single time the 5950X's multi-threaded performance was compared then sure, the 105W TDP is fair. But you should also be calling that out, or you're being misleading, as the majority of the 5950X numbers in the article were single-threaded results, and it did not appear in most of the multi-threaded comparisons at all. But in multi-threaded workloads it also absolutely obliterates the M1. Ma…

It's really not clear what you are trying to argue here. The number of single-threaded benchmarks are irrelevant to this point: when the M1 was compared to the 5950X in a multithreaded comparison:

* The 5950X was 2x faster * The 5950X was using 4x the power (28W system vs 105W+ for the processor). * The M1 only has 4 performance cores, the 5950X has 16.

Even counting the high-efficiency cores as full cores in the comparison has the M1 with 8-cores providing 1/2 the performance of the 5950X with 16-cores, i.e. it implies that the lower performance cores are providing as much as the 5950X cores.

That is certainly not the 5950X obliterating the M1, as the article stated (and was the quote that started this thread) the M1 is giving the 5950X a good run for its money. If you think otherwise could you provide some kind of argument for why you think so?

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

#459

Earlier quoted context omitted.

It's really kind of tragic that so much incredible research and engineering work goes into creating new hardware like this only for it to be locked into one particular company with very tight constraints on target audience, income bracket, and technical limitations. Think how incredible it would be if everyone could use this new silicon.

It is, in fact, already used by everyone, because it's an evolution of the chipset in basically every smartphone in the world with widely divergent target audiences, income brackets, and technical limitations.

I don't know that that's a fair comparison. Just because it's an ARMv8 chip doesn't mean it's directly comparable to what's in smartphones. (I assume you aren't comparing it to Apple made chips for iPhone specifically, since then it wouldn't be true that it's in "basically every smartphone in the world".)

In particular, this is the first 5nm chip to be widely available, and by most accounts on performance it competes with top of the line hardware at a small fraction of the power use. Most existing ARM chips are designed for the very-low-power market, e.g. in phones, not to be used in a high performance laptop.

If there's a Dell or Thinkpad laptop with an ARM chip that's comparable, by all means, let me know.

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

#460

Wow 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…

That's the consequence of resting on your laurels and getting complacent. They relied too much on being the large incumbent, and they reap what they sow.

They reaped billions in profits. The issue is that organizations can't turn it on and off based on competition, once you are rich and lazy, the organization fills up with coasters and before they know it they no longer have a higher gear. Remains to be seen if Intel can come back, but I doubt it under their current leadership.
Post reply on HN