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

Apple’s M1 Positioning Mocks the Entire x86 Business Model

extremetech.com

Post reply on HN
Print view View original

411–420 of 942 posts

Re: Apple’s M1 Positioning Mocks the Entire x86 Business Model

#411

Post by slver »

speedplane wrote: post #69

The M1 processor is a direct result of the death of Moore's law. It's an amazing processor, but a sad sign of things to come. The performance gains from Moore's law have typically come from shrinking die size. That has ended, you can't juice more performance from general purpose CPUs. If general purpose processors no longer advance quickly enough, the only way to get performance gains is to build custom chips for com…

> The M1 processor is a direct result of the death of Moore's law.

I know most people misunderstand Moore's law, but this is HN, so I expect better:

https://en.wikipedia.org/wiki/Moore%27s_law#/media/File:Moor...

Moore's law is quite alive and showing no signs of problems.

> The performance gains from Moore's law have typically come from shrinking die size.

Moore's Law is about number of transistors. Not about their size, and not about performance.

And it's ESPECIALLY not about linear core performance.

> That has ended, you can't juice more performance from general purpose CPUs.

You don't need to, they're fast enough. Performance is expanding in other areas like GPU and ML.

> The death of Moore's law has many consequences, the rise of ASICs and custom co-processor chips is just one of them.

No, Moore's law is the very thing supporting them... You need extra transistors for those co-processors.

Re: Apple’s M1 Positioning Mocks the Entire x86 Business Model

#412

Post by zelon88 »

Here we go again. Comparing a 10w mobile RISC CPU to a 100w x86 CPU and somehow deducing that having a mobile CPU run desktop applications is a good idea.

I wish all the Apple fanboys would just hurry up and buy one so they would realize they are comparing apples to oranges and sit back down.

Nobody is buying an M1 to replace their gaming computer. And to insinuate that such a thing is possible or practical is disingenuous to the way PC hardware works.

Additionally I think the article is of amateur quality. It takes on an Apple perspective and assumes that there will be no response from x86 vendors basically because "how could you possibly respond to something as astounding as the M1?"

Don't worry. Apple hasn't taken over the desktop market yet, and they don't have the raw horsepower to do it anyway. And they don't want to. We are comparing embedded CPU's with proprietary north bridge architecture to industry standardized and socketed CPU's with an entire industry supporting it. Nobody in the market for a desktop PC is going to get a mobile Apple device just because the M1 is more efficient. Nobody goes out to buy a pickup truck and accidentally gets talked into a Prius. Just because you conflate efficiency with performance doesn't mean the M1 is capable of replacing a Ryzen 9.

Re: Apple’s M1 Positioning Mocks the Entire x86 Business Model

#413

Post by Toutouxc »

masklinn wrote: post #271
iSnow wrote: post #217

Earlier quoted context omitted.

I know, but AFAIK those new iMacs ALL feature just 8GB of RAM? There isn't really a middle-tier, that what makes it so weird. you'd expect one machine with top SSD and 16 GB (and space grey, lol). Probably going to be the next iteration of the 27" iMac, spanning from 8GB/256GB (LOL) to 16 GB/1TB or something.

> AFAIK those new iMacs ALL feature just 8GB of RAM? No. But people are confused because the RAM is (annoyingly though not entirely nonsensically) tied to the SSD.

I don't think it is. They usually offer a couple of configurations at different prices, but you can get a BTO machine with just the upgrades you want. The SSD+RAM are tied together in the new M1 iPad.

Re: Apple’s M1 Positioning Mocks the Entire x86 Business Model

#414

Post by stepbeek »

Tehnix wrote: post #300
sto_hristo wrote: post #153

Make it as fabulous as much as you want, $1700 for an 8 core, 8 gigs of ram machine is just one plain fabulous joke. This in the time when 16 gigs ram is the baseline if you plan to do anything more than facebook and instagram.

I just went from a 32GB RAM Macbook Pro to an 8GB RAM M1 Macbook Air...the difference is insane, I don't know what the hell the MB Pro is doing with its RAM, but it just felt like RAM was never enough on Intel Macbooks. Here on the M1, I don't feel my system crawling to a halt like I did on the MB Pro, and I'm doing the same workloads.

I've just made a similar switch I went from a Pro (2018 i9 Pro with 32GiB of RAM) to an M1 Air with 16GiB of RAM and its ridiculous.

I've tried to look up what this difference might be, but all I've found is a hand-wavey answer about it being an SOC. If someone can ELI5 then I'd be super appreciative.

Re: Apple’s M1 Positioning Mocks the Entire x86 Business Model

#415

Post by jsmith45 »

oblio wrote: post #235
the_duke wrote: post #189

Earlier quoted context omitted.

Yeah the marketing effort is immense, and it's really surprising to me how many eagerly lap up the angle Apple is pushing without much reflection, even on HN. Like the good old Apple hype days. Now to be fair, the M1 is an impressive iteration on the A* chip line. But the Ryzen 5000 mobile chips really don't look bad at all in comparison, and a 5nm version of those would level the field.

I don't know why you're being downvoted. A 5nm version of the AMD stuff should be reasonably close to the M1. The main bottleneck is the production capacity, we badly need more manufacturers of high end chipsets.

But let's say that a 5nm Ryzen comes out ahead for mobile usage. (But not necessarily by very much.)

Chips like the M1 (or ideally, something similar made available to other device manufacturers) is still really interesting. The ARM architecture can scale down better than x86/x64 can, allowing a device maker to hit low end performance targets with less cost than x86 chips can manage. For the low end, it also tends to provide better power consumption for a fixed performance target than the x86 offerings.

This makes M1 type chips really interesting for any manufacturer who want to make devices that span a huge scale of performance requirements, from slow kiosks performance range to the decent laptop range. All being the same ISA makes sharing firmware and applications across the lineup easier than having to switch to x86/x64 above some threshold.

It also does not hurt that M1 means that the really popular for development Apple devices are now running on ARM, which helps ensure that more software has been ported to (and/or tested on) ARM devices. ARM's weak memory model for example is something that can trip up a lot of software that tries to implement low lock algorithms, but whose designers were only familiar with the x86/x64 memory model.

Re: Apple’s M1 Positioning Mocks the Entire x86 Business Model

#416

Post by protomyth »

alberth wrote: post #369

ARM is not more efficient / faster because it’s “newer”. People imply ARM is relatively new and thus could correct for the misdirection x86 has gone. 1978 is when x86 was introduced. 1985 is when ARM was introduced. ARM isn’t that much newer than x86. https://en.m.wikipedia.org/wiki/X86 https://en.m.wikipedia.org/wiki/ARM_architecture

ARM 64-bit is cleaned up from the 32-bit ISA and showed up in 2011.

Re: Apple’s M1 Positioning Mocks the Entire x86 Business Model

#417

Post by bstar77 »

zelon88 wrote: post #412

Here we go again. Comparing a 10w mobile RISC CPU to a 100w x86 CPU and somehow deducing that having a mobile CPU run desktop applications is a good idea. I wish all the Apple fanboys would just hurry up and buy one so they would realize they are comparing apples to oranges and sit back down. Nobody is buying an M1 to replace their gaming computer. And to insinuate that such a thing is possible or practical is dising…

I don't think this comment is going to age well.

Re: Apple’s M1 Positioning Mocks the Entire x86 Business Model

#418

Post by zelon88 »

bstar77 wrote: post #417
zelon88 wrote: post #412

Here we go again. Comparing a 10w mobile RISC CPU to a 100w x86 CPU and somehow deducing that having a mobile CPU run desktop applications is a good idea. I wish all the Apple fanboys would just hurry up and buy one so they would realize they are comparing apples to oranges and sit back down. Nobody is buying an M1 to replace their gaming computer. And to insinuate that such a thing is possible or practical is dising…

I don't think this comment is going to age well.

I'm sure there are comments from the 64 bit PowerPC days that aged just fine.

Re: Apple’s M1 Positioning Mocks the Entire x86 Business Model

#419

Post by glhaynes »

alberth wrote: post #369

ARM is not more efficient / faster because it’s “newer”. People imply ARM is relatively new and thus could correct for the misdirection x86 has gone. 1978 is when x86 was introduced. 1985 is when ARM was introduced. ARM isn’t that much newer than x86. https://en.m.wikipedia.org/wiki/X86 https://en.m.wikipedia.org/wiki/ARM_architecture

People tend to lump them all together and just call them "ARM" but the 64-bit instruction set ("AArch64") first came out in 2011 and is hugely different than classical 32-bit ARM. And the chips Apple makes these days don't even implement the 32-bit instruction set anymore.

Re: Apple’s M1 Positioning Mocks the Entire x86 Business Model

#420

Post by leetcrew »

mysterydip wrote: post #211
emteycz wrote: post #190

Earlier quoted context omitted.

There's a value in that too - people know immediately that i7 is powerful, and everyone [that cares] already knows that processors are renewed frequently. Though yeah, perhaps something like 7i1, 7i2 would've been better. Apple solved this nicely (given the naming is confirmed) with M1X.

That's fine if you're buying new. Is there an i5 that beats an older i7 in performance? When buying a used laptop or desktop, how much extra research do I need to do to figure out which processor I'm actually getting? There's been 13 years of i7's.

I don't think this is a solveable problem. with a wide range of skus, inevitably there will be an nth gen part that outperforms an n+1th gen part.
Post reply on HN