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

M1 Macs: Truth and Truthiness

daringfireball.net

Post reply on HN
Print view View original

801–810 of 882 posts

Re: M1 Macs: Truth and Truthiness

#801

Post by ianhowson »

alwillis wrote: post #721
ianhowson wrote: post #540

Earlier quoted context omitted.

Anandtech is comparing M1 vs A14. It's high performance for a cellphone part. Dual channel DDR3L or DDR4L also has a 128 bit bus. 4200MHz DDR4 is clocked on the high side for most laptops, sure, but it's hardly unusual. Run the numbers and you get the exact same throughput figure as for M1, which isn't surprising, because we're just taking width * rate = throughput. So I'll repeat my assertion, downvotes be damned: t…

Anandtech is comparing M1 vs A14. It's high performance for a cellphone part. That’s where they started, but their conclusion was beyond that. Did you miss the part where they said the fact that a single Firestorm core can almost saturate the memory controllers is astounding and something we’ve never seen in a design before ? This isn’t only about A14 vs M1. It’s not that LPDDR4X-4266-class memory is special; it’s be…

> Did you miss the part where they

I don't think that's notable, sorry. I would expect that of any modern CPU.

> it’s not common for general purpose laptops and desktops

Well, yeah, because "memory on package" has major disadvantages. You (laptop/desktop manufacturer) are making minor gains in performance and power and need to buy a CPU which doesn't exist. Apple can do it, but they were already doing it for iPhone, and they must do it for iPhone to meet space constraints.

I think unified memory is the right way to go, long term, and that's a meaningful improvement. But as you point out, there is plenty of prior work there.

> they don’t have everything that’s part of the M1 system on a chip

They actually do! The 'CPU' part of an Intel CPU is vanishingly small these days. Most area is taken up with cache, GPU and hardware accelerators, such as... hardware video encode and decode, image processing, security and NN acceleration.

Most high-end Android cellphone SoCs have the same blocks. NVIDIA's SoCs have been shipping the same hardware blocks, with the same unified memory architecture, for at least four years. They all boot Ubuntu and give a desktop-like experience on a modern ARM ISA.

> There’s no other desktop ... at the price point of $699

Literally every modern Intel desktop does this.

Re: M1 Macs: Truth and Truthiness

#802

Post by x0x0 »

wpietri wrote: post #785
x0x0 wrote: post #675

Earlier quoted context omitted.

all day on-battery real-world heavy usage without significant compromises. In fact, not just without significant compromises, but about as fast as a laptop can go.

That's a nice feature, sure. But I don't see it as revolutionary. Are there a lot of people suddenly able to live or work differently because of this?

For me, a lack of constantly thinking about the battery is a big deal. I had the same thing happen w/ my phone: mine got large enough a couple years ago that it was a full 2 day battery life. So I could assume it would work all day.

Same deal here. I can go (in a !2020 world) to a customer, go from meeting to meeting, etc and it will just work.

edit: Also, it feels like we're transitioning from a world in which laptops are mostly / often used while being plugged in, to a world more like a phone. The default mode of operation is disconnected from a power source.

Re: M1 Macs: Truth and Truthiness

#803

Post by trevor-e »

Oreb wrote: post #784
internet2000 wrote: post #655

Earlier quoted context omitted.

It wasn't a surprise they were doing it. It absolute was a surprise for Intel that it ended up being this good.

But how can that be a surprise to anyone who has been following the development of the iPhone/iPad CPUs? The M1 is exactly what you would expect it to be by extrapolating from the performance of recent iOS chips.

I certainly wasn't expecting an M1 mac mini to compile our iOS app codebase in half the time compared to a 2018 super beefy MacbookPro.

Re: M1 Macs: Truth and Truthiness

#804

Post by wffurr »

andrewprock wrote: post #548
coldtea wrote: post #532

Earlier quoted context omitted.

> The author is bashing another author for not doing measurements, yet himself declares that m1 beats all the other CPUs, without providing any measurements. That's because there are plenty of measurements published, which agree with the author, and disagree with the "another author".

The published benchmarks are mostly "meh" when it comes to anything at the prosumer level and above. The insanely good thermals and 5mm process make M1 a great laptop, but middling performance and a lack of expansion only makes it decent mini-desktop for family use. If the rumors of the M1x prove true, that might be the first real pro-level ARM CPU. For pro-level performance, it's roughly matching AMD's three-year-ol…

A 10W SoC roughly matching a 65W CPU... That's bonkers.

Those benchmarks also aren't differentiating between the fanless MacBook Air, the actively cooled MacBook Pro, or the wall-powered Mac Mini, all of which have different performance characteristics with the same chip.

Re: M1 Macs: Truth and Truthiness

#805

Post by wayneftw »

ascagnel_ wrote: post #798
arminiusreturns wrote: post #226

Earlier quoted context omitted.

I am willing to bet if mods did some data munging they would find sockpuppetry of a hail corporate type at work, because if hn is really this brainwashed about macs it makes me sad.

Apple has always operated with a more closed-off ecosystem that sacrifices openness for tighter control on the user experience, and that's always been at odds with the "I want access to everything so I can tinker" mindset on HN. I expect any HN discussion about Apple to be a mess, because the average HN commenter/reader wants something very different than what Apple sells.

I think something like 80% of Silicon Valley tech workers are using Macs and tons of them hang out on HN. I have always seen the HN crowd as being mostly pro-Apple.

Maybe I'm wrong though - it might depend on the thread. Whenever I put out an anti-Apple sentiment on a pro-Apple article thread I usually get massive amounts of disagreement.

My own dislike for Apple goes way beyond their protectionist policies. Maybe if I didn't hate the Mac UI with that hideous global menu bar and horrid window management, I could be more forgiving towards their politics. Heck, I used Windows as my main OS for decades until I finally switched to Manjaro and XFCE for the sheer convenience of running Docker and npm/yarn smoothly without all the Windows cruft slowing me down all the time.

It's funny though - I do less tinkering on my Linux desktop than I ever did on Windows (or my Mac), since everything just works the way I want it to in Manjaro. I think my first week using it, I had to figure out how to write an xdotools script to get window snapping in XFCE. Never had to touch it since. My Mac has broken things like Karabiner, Better Touch Tool, Little Snitch and so forth after many updates - so much so that I just stopped reinstall them. Luckily, I only have to use it once in a while for doing the occasional Mac/iOS thing.

Re: M1 Macs: Truth and Truthiness

#806

Post by buzzerbetrayed »

nvarsj wrote: post #779
buzzerbetrayed wrote: post #530

Earlier quoted context omitted.

How are 2 laptops running different operating systems not comparable? The similarities of a Windows laptop and a Macbook far outweigh the differences.

Because the software I use that works on Linux or Windows doesn't exist or cannot be run on OS X. CUDA doesn't even support OS X anymore. If I can't run my OS/software of choice, it doesn't matter how great M1 is.

Oh so because this laptop doesn't work for YOU, anyone who compares it to Windows or Linux is making a "silly argument". Gotcha.

Re: M1 Macs: Truth and Truthiness

#807

Post by pjmlp »

mikepurvis wrote: post #797
pjmlp wrote: post #753

Earlier quoted context omitted.

ARM started on the desktop.

But for the last twenty years, surely pretty much every linux-capable ARM part produced in excess of Q>1M has fallen into one of two buckets— either a) a device that runs on batteries, or b) an embedded, specialized processor such as for a router, vehicle infotainment, or home appliance.

That sums pretty much the actual usefulness of Linux itself.

Re: M1 Macs: Truth and Truthiness

#808

Post by dangus »

p1necone wrote: post #563
nwienert wrote: post #538

Earlier quoted context omitted.

Using an M1 Air, coming from a 16" Pro, here's the diff: - Cost: $1400 vs $4000 (nearly 1/3) - Speed: Air feels significantly faster, and more apps move to native, will be even moreso - Battery: At least double, if not 3x - Size: Less than 1/2 the weight The revolutionary thing is doing all of those at once . Nearly tripling battery life while making a huge leap in performance, at 1/3 the cost and half the weight is…

Comparing it to previous gen Apple devices doesn't really tell the whole story. You can get a machine from a different manufacturer with similar hardware for much much less than $4000, and it wont have totally broken cooling[0]. [0] https://www.notebookcheck.net/Apple-MacBook-Pro-15-Core-i9-s... Bear in mind that I'm not arguing that the m1 macbooks aren't a really compelling option. I'm just saying this is evolution…

Why are you using Apple’s discontinued 15” model as a benchmark here?

The 16” MacBook Pro most certainly does not have those same cooling issues.

But that’s the thing: Apple had to make their flagship performance laptop bigger including a larger battery than its original design in 2016 because Intel was never able to hit their roadmap goals.

That doesn’t sound like progress to me, it kind of sounds backwards.

In other words, Apple couldn’t give you a reason to buy their performance laptop four years later without making it physically larger. Because if they didn’t do that their customers would only have minimal incremental improvement to compel them to consider a newer system after four years.

In contrast, a four year old iPhone is over twice as slow from a raw performance perspective than the current model.

So yeah, I could buy a much cheaper PC laptop with proper thermals and cooling for much cheaper than a 16” MacBook Pro to get that fantastic performance. Maybe it’d even be a lot better than the M1 Macs.

But I can’t buy a Windows laptop, for any price, that has no fans at all and manages performance and battery life of the MacBook Air.

Apple’s throwing a CPU into their *cheapest laptop that is marketed for basic usage (students, home users) that benches faster than basically all but AMD’s most performant chip, a chip that would probably get you pretty terrible thermals and battery life in a 16” MacBook Pro.

A lot of evolutionary products were, in retrospect, revolutionary. Was the guts of an iPod or Walkman or iPhone or IBM PC or Honda Civic all that different from conventionally available parts? No, consumer electronics almost never have anything particularly exotic going on.

But it’s the whole package that can be revolutionary. The Civic was a dirt cheap car with excellent fuel economy and reliability. Is it all that different from other cars? No, not really, but the entire Japanese auto industry was a disruptive product in the 1980s.

The rumor mill is already telling us that the 16” MacBook Pro may ship with a 12 core (8 big, 4 little) “M1X” or “M2” chip. If the tech media landscape is head over heels for the M1, this new chip is going to make serious waves, because if you double the performance cores in the M1 it’s basically going to be untouchable by anything that can remotely be considered a laptop.

If Apple doesn’t touch the form factor of the 16” MacBook Pro it’s going to have similar results: it’s going to run quieter, cooler, and longer.

In short, it’s just my own opinion that calling this bit of incremental improvement evolutionary rather than revolutionary is something of an understatement.

Re: M1 Macs: Truth and Truthiness

#809

Post by Zancarius »

bayindirh wrote: post #750
Zancarius wrote: post #447

Earlier quoted context omitted.

> when a flawlessly running driver degrades after an update (cough, intel e1000e, cough), it leaves a bad taste in the mouth. Hah! I see I'm not alone. For me it was the iwlwifi drivers. In one kernel revision, they worked fine; in another, they'd randomly panic and bring down the interface. Downgrading the firmware packages didn't do anything. Kernel upgrades have worked as of late. Though, it may be hardware-relate…

Intel went through a phase where they managed to break their graphics and network drivers at the same time . I thought whether my hardware was failing but, when they broke three different NICs with the same update, I understood what happened. Hope they don't do it again. I'm not going to use their processors in my next build but, I tend to like their NICs.

> I thought whether my hardware was failing but

You're now making me question whether this is a problem with the wifi card or the driver. I admit I'm still convinced it's probably the card (I have an earlier revision in a ThinkPad that works fine), but now I'm not so sure!

Curious: Are you talking about that "little" issue where the i915 module was randomly causing a panic? I ran into someone who had some really perplexing issues that a kernel update later resolved, and their dmesg was strongly hinting (to me) that it was linked to the i915 drivers. That, and a bug report I managed to dig up.

And I also agree. I'm looking at a Ryzen build, too. I have a couple of Intel NICs in my file server though and they're better quality IMO than the Realtek cards.

Re: M1 Macs: Truth and Truthiness

#810

Post by 5ersi »

throwaway894345 wrote: post #744
stouset wrote: post #715

Earlier quoted context omitted.

I think there’s a qualitative difference here between viable (which is where we’re currently at) and utterly dominant (which is where I suspect we’ll be in five or so years).

I agree, but even still how does that affect Intel’s business model? Are they incapable of building ARM chips and selling them the same way as their x86 chips? Seems like the business model is fine but the product will need to change, no?

Sure they can, but at vastly lower profit margins.
Post reply on HN