Apple's M1: the fastest and bestest ever silicon = revolution? Nah, there's far more interesting stuff happening in tech that matters to everyone Apple Silicon has been the autumn’s hottest news in cool chips. Giving Intel two years’ notice, the first laptop and desktop with the new Arm-based M1 chip have shipped and the benchmarks run. If you believe some of the more febrile headlines, Apple has upended the industry, sparked a revolution and changed the face of computing …
To be clear, what Apple have done, is shipped an entry level fanless laptop that can emulate Intel code and outperform an I9, whilst offering all-day battery life.
Intel can't pivot to SoC and consumer *will* like this.
Intel still don't have their 7nm process working and is now looking at 2022 or further out and contingency plans with third party foundries.
AMD aren't constrained on the fab side so will likely take the lead in PC for the next couple of years.
nVidea buy ARM so go after the DC market, and that leaves Intel in a very bad position.
To the consumer, these are going to be very appealing...
Maybe I'm looking at this very simplistic, but I need to edit and render a video in Final Cut. The new M1 based notebook will allow me to that faster and for longer time without a power outlet for much less money than any other comparable solution. And that's just one of the real world examples for a typical Mac user.
So what is the "far more interesting stuff happening in tech that matters to everyone"? Emphasis on EVERYONE.
The power savings are the main benefit to a typical use case, I think — 20 hours on a charge for the 13" 'Pro'. But for people like me that develop native code, there's a huge reduction for build times and for video and iage editors there seems to be quite a bounce via the GPU.
So, benefits for people who just want to carry a laptop around and browse, for developers, and for media production. Isn't that essentially Apple's entire user base?
That comment is made while acknowledging the article's point, of course: many, many people do work that is entirely disjoint from Apple's user base, and this change will matter not one jot to them.
I think the article is a little harsh, but people DO tend to forget the data moving.
whether this is on a network with directors with the shiny new kit still complaining that the horoscope site their visiting is slow or, especially in the virtualised world, people buying the latest greatest server kit and then slapping a 5 year old SAN on the end of it and wondering why their databases are still a nightmare.
Apple is a consumer company, that's all they want to be. They've been dragged kicking and screaming to provide a modicum of enterprise management capability but why would they? You can see the clusterfuck that is HPE's business model, Dell isn't making a huge margin.
Why bother doing stuff outside the walled garden for Enterprise and the geek squad when you're literally able to print your own money doing shiny consumer kit.
That's where I see this going. Think about the advantages for the likes of Apple and MS. All user files will still be stored on an SSD / Hard drive, but the OS will run straight off the chip. A computer will be an instant-on device again, like home computers were back in the 80s. No more piracy / licensing / OS file corruption issues. Upgrading will require purchasing a new chip, so be even more lucrative, even though some limited flashing of fixes onto on-chip ROM might also be deemed possible. And total control by the giants. All that lovely total control and $$$$.
This will all have many many downsides, but the civilian population who just want appliances will not care a jot.
There was a meeting of Apple engineers and Steve Jobs walked in. He pressed the power button of an iPad and it was instantly ready for use. He then turned on a MacBook, and the there was a delay. "This..." pointing at MacBook "doesn't do this." pointing at iPad. "Make this.. do this!"
.... complaining about Apple being good at what they do.
Why should Apple, or anyone else, be everything for every commuting need? Attempting that sort of thing almost always produces the lowest common denominator. Should you be criticizing Microsoft for never producing their own silicon to change the world, or Intel for failing twice in a row to get smaller chip processes to work reliably?
Bit of a double standard, much?
No, it's all right, you're just permanently shirty about Apple given a lot of people what they want, rather than what _you_ want. Got it.
But they've shown what is possible, and I'll wager that Amazon and Google are going to be getting very interested in running ARM chips rather than x86. The savings in power usage will be substantial.
I wouldn't bet against Apple deciding that selling to the hyperscalers with a slightly customised chip (losing the GPU primarily, but given the power consumption - who cares) might make them an even larger pile of cash than just selling to the public, and a few corporates.
The M1 may well spawn the D1 (desktop) and the C1 (cloud) in turn. The first is more than just likely, the second is a distinct possibility.
Yes - though I don't know quite how much of it they use... this might be a significant driver - high performance cores running at substantially the same compute capability as x86 hardware for significantly less power.
I can see them pushing people to ARM even if they keep half of the power savings for themselves.
More like 16% and growing. People are sick and tired of Windows and all the issues that go with it. Dell make some nice laptops but then spoil it with Windows.
As for software on Mac, even Microsoft have had MacOS versions for years and are building M1 versions of Office 365, as are Adobe et al . . . it's popular and getting more popular or Apple wouldn't have bothered investing in the M1.
Then there's iOS . . . again increasing in use given the stats from my sites.
I wasn't sure who to believe on this, so I checked StatCounter, which attempts to monitor trends through web traffic analysis. Make of that methodology what you will.
Worldwide it does indeed look like a ~16% share for macOS, on a gradual upswing, with Windows very slightly fading. In Europe macOS is nipping at 20%, and in North America it's more like 27.5%, but apparently the continent that likes Macs the most proportionally is Oceania where Apple gets almost to a third. I did not see that one coming.
But it's easy to oversell: in the worldwide all-OS that chart both Android and Windows are basically as important as each other, both hanging around just below the 40% total share mark; from Appleworld iOS appears to be about twice as used as macOS.
I wonder how they are measuring that...
While I don't doubt that the macOS share has been growing, 17% WORLDWIDE seems pretty unlikely to me simply given the entry price of a Mac vs the entry price of a Windows PC, and how many people in the world for whom even an entry level Windows PC is more than they can afford.
I personally don't see the lack of expandability on the current M1 based Apple kit an issue for most end users. People have sort of got used to many electronic gadgets not being upgradable, I mean there is no way to add more RAM to your phone or iPad. And even my current laptop which can have the RAM upgraded, the manufacturer wasn't expecting many to bother going down this route when designing the laptop, as you have to pull the whole laptop apart to get to the DIMM sockets. Unless you are tech savvy not many end users would probably be comfortable to do it.
Yeah, this is just an argument people can use to hate on what it has done without recognizing that they replaced the low end option on several low end products. That the performance is competitive (in single thread/low multithread) with Intel and AMD's fastest shouldn't distract people into thinking Apple is trying to push these at high end customers who need upgradeable RAM etc.
I'll bet if it were possible to measure the percentage of new Windows PCs sold to consumers (the whole market, across all price points) the percentage that EVER get an upgrade of RAM or storage is probably low single digits. The lack of upgradeability the tech writers and the kind of people who read The Reg think is terrible is something the average person would simply not care about.
Funny, I didn't see a Mac Pro - the MBP has been rather less than Pro for a while (I have a 2019 one my laptop stand at the moment).
These are firmly consumer oriented.
The markup on the increased memory isn't even that much, it's substantially less than MS charge for memory on their Surface line up... so if you need 16GB, just buy it. If you need more, then this isn't the machine you are waiting for - give it a couple of years (or buy one of these for your desk and a proper server).
Apple only replaced the low end version of the Mini, Air, and MBP13" this time around. The "high end" version is still x86 (slower, but with more memory/storage options)
When the faster / more core CPU/GPU comes out in H1 2021 they'll fill the remainder of those product lines (plus maybe the low end of the MBP16" and iMac) and offer larger memory configurations. Maybe using DIMMs in some cases, we'll see. If they weren't going to support DIMMs or m.2 storage the Mini could be a lot more "mini" so I have to assume they have something in mind for it in higher end configs that allows for some expandability.
I am slightly surprised they didn't do the mac-micro.
An appleTV sized M1 powered box with hdmi, power, ethernet, dual USB-c, and probably a single/dual USB-A port as well. Make it limited, 8GB RAM only, the 7 gpu core version... but that'd would suit alot of people, and the amount of space in the current mini suggests it's easily possible.
It's not as if the M1 needs huge amounts of cooling, just stick it to the aluminium shell of a TV sized box and be done with it.
Hell even my desktops never receive a RAM upgrade.
I buy enough to start with and in 5 years time I'm probably being held back by something else, in which case it's a new mobo and new cpu anyway and what's the chances the new mobos even using the same type of ddr anymore let alone that I can match it exactly to increase capacity without ditching my old modules.
Real people upgrade storage and that's about it.
This is just another strand to the RISC versus CISC tradeoff. One thing I learned very early on in my career was that in terms of instruction flow RISC will always run rings around CISC provided there was effectively infinite memory bandwidth because the vast majority of instructions were straightforward RISC type orders rather than the multifunction complex instructions that a CISC processor might issue (instructions which are likely to be implemented in microcode anyway). There have been more or less successful attempts to match CISC orders to the needs of programming languages -- the PowerPC seems to be the best example -- but you start trading flexibility for performance.
So Apple has made a RISC that's closely coupled with its memory. Great for them, especially as they're always been in the "computing appliance" business (just like a phone you buy it and use it as a complete unit). For the rest of us that need high performance computing that's relatively low power there's the MIPS architecture. MIPS has never registered much in desktop computing but its the go-to processor for heavy lifting, especially moving a lot of network data. This type of architecture turns up in soft processors and is also similar to the open RISC-V standard so I'd expect to see it around for some time.
Apple have produced a highly optimised processor design that works extremely well in their vertical integration business model.
There are two devices, that are probably the best selling PC devices, the Playstation and the Xbox, that have a similar hardware model, these are currently using AMD designs. AMD has a licence for ARM but has yet to produce any hardware. I can see the sense in aSoC in these devices as they are effectively sealed boxes and integrationg AMD graphics and ARM cores and other specialist processors that support specific gaming related processes in to an SoC woudl save costs and improve performance. 4-5 years time is long enough for them to actually spin something up in this field and with MS moving Xbox over then Windows would go to, though it could be the other way round though x86 emulation is a bit of a sore point between Intel and MS if I recall correctly. Oh and Nvidia are buying ARM so that could be interesting too.
The ARM architecture is very different to x86/amd64 in terms of memory coherence.
A lot of places are going to believe Apple's "Just recompile!" hype and produce software that randomly fails in ways that a naiive examination of the source code (and even machine code) would say is totally impossible, because of the way ARM re-orders memory access.
Apple know this, because their amd64 translation layer puts the M1 into a special memory coherence mode that papers over the cracks. The "native" apps don't get that special treatment because it slows it down.
So the next few years is going to have a slow, quiet wave of utterly impossible bugs on "native" Apple Silicon, that are unrepeatable but persistent.
Memory access ordering is not cache coherence.
You are one of the developers who will - likely already has - made these mistakes, because x86 simply has a different memory model to ARM.
Codebases that have had decades of real-world usage on x86 fail on ARM because of the different memory model. No software house is going to find all of those cases.
Early Intel processors had external memory, interrupt, dma, npu, i/o, etc units.
The cpu wasn't much, registers, alu, branch/next instruction fetch & decode, etc.
M1 has shown the efficiency of bringing the main ram onboard, big deal, no, progression, yes.
First to do it, hell no.
Rupert is correct in that Apple has tailored the M1 to a specific task
and this is where the ARM ecosystem has been headed for a long time.
A designer has a need, finds an MCU to fit the requirements,
or if you're big enough, roll your own MCU.
This post has been deleted by its author
Kudos to Apple to shrinking the PCB down to a System-on-a-chip. Welcome to the world where physical chips are becoming obsolete and where companies can now stick whatever bits and pieces they need into a single device and then get TMSC or whomever to churn out countless copies. Seymore Cray recognized memory bandwidth as an issue during the Jurasic era of computing - his machines were a marvel at the time. Shedding an external memory bus allows a lot of innovation in the memory system,. As for bemoaning the ability to plug in other stuff onto a bus, you need new stuff to plug into the new Universal Serial Bus.
...it can make the whole thing work extremely well.
As you say, nothing at this price point comes close in performance and low power use.
You didn't mention access to millions of new apps from the iPhone and iPad.
Because you choose to eschew all things Apple, the M1 will not make a difference to your world...
Wait. What? Apple wants to continue to make oodles of money by selling computers and phones?
<GASP> HOW! DARE! THEY!?
I use Apple products because I like them. They're well made and they last a long time (although Windows is better at this now) so they tend to be a good use of my limited money. I'm not an apologist for them and they sometimes do silly things. But expecting a well established, phenomenally profitable company to change its business model is also incredibly silly. In 1997, no one expected Apple to survive, let alone become the largest corporation in history. They're apparently doing something right.
Indeed they are. Perhaps to the chagrin of some.
I used Macs through the 1990's, 2000's, etc., because I was working in the ad agency world, so postscript was standard. Today, I still use Macs, and I my MacBook Air is smooth. But every now and again, I will fire up my . . . PowerBook 3400c and it runs wonderfully as well (800 x 600). With 16mbs of RAM. Yes, they CAN last a long time.
I've been trying to move to Apple since about 2005. Every time I or someone in my family takes a tentative step they get clobbered by unreliability. Usually absurdly short hardware lives. Current but not first problem is trying to get a 400Gb iTunes library to play on a phone. The Apple Music people are very sweet but as ignorant as I am. I doubt whether Apple is really any less reliable than anyone else, but their reputation and pricing says they're really good.
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2024
