That's an incredible improvement in just a few years. I wonder how much of that is Apple engineering and how much is TSMC improving their 3nm process.
So I've become really suspicious about any claims about performance done by Apple.
Also what games are you trying to play on it? All my M-series Macbooks have run games more than well enough with reasonable settings (and that has a lot more to do with OS bugs and the constraints of the form factor than with just the chipset).
The problem is two-fold, first the marketing bullshit does not match the reality and second the Apple converted will lie without even thinking about it to justify the outrageous price.
There are a lot of things I like about Apple hardware but the reality is that they can charge so much because there is a lot of mythology around their products and it just doesn't add up.
Now if only they be bothered to actually make software great (and not simpleton copies of what already exists), there would be an actual valid reason to unequivocally recommend their stuff but they can't be bothered since they already make too much money as it is.
Single Core: iPad Pro (M2): 2539 Macbook Air (M2): 2596 Macbook Pro (M2): 2645
Multi Core: iPad Pro (M2 8-core): 9631 Macbook Air (M2 8-core): 9654 Macbook Pro (M2 8-core): 9642
So, it appears to be almost the same performance (until it throttles due to heat, of course).
1. https://browser.geekbench.com/ios-benchmarks 2. https://browser.geekbench.com/mac-benchmarks
Gave me quite a laugh when Apple users started to claim they'd be able to play Cyberpunk 2077 maxed out with maxed out raytracing.
https://www.theverge.com/2022/3/17/22982915/apple-m1-ultra-r...
Apple was comparing the power envelope (already a complicated concept) of their GPU against a 3090. Apple wanted to show that the peak of their GPU's performance was reached with a fraction of the power of a 3090. What was terrible was that Apple was cropping their chart at the point where the 3090 was pulling ahead in pure compute by throwing more watts at the problem. So their GPU was not as powerful as a 3090, but a quick glance at the chart would completely tell you otherwise.
Ultimately we didn't see one of those charts today, just a mention about the GPU being 50% more efficient than the competition. I think those charts are beloved by Johny Srouji and no one else. They're not getting the message across.
They really love those kind of comparisons - e.g. they also compared M1s against really old Intel CPUs to make the numbers look better, knowing that news headlines won't care for details.
It's not some virtue that causes them to do this.
Apple compared against Intel to encourage their previous customers to upgrade.
There is nothing insidious about this and is in fact standard business practice.
The intensity of the reality distortion field and hubris is mind boggling.
Turns out, you fell for it.
You're explanation is a really baffling case of corporate white knighting.
that's honestly kind of stupid when discussing things like 'new CPU!' like this thread.
I'm not saying the M4 isn't a great platform, but holy cow the corporate tripe people gobble up.
I eventually made a visual showing it was the same as claiming your iPhone was 3x the speed of a Core i9: Sure, if you limit the power draw of your PC to a battery the size of a post it pad.
Similar issues when on-device LLMs happened, thankfully, quieted since then (last egregious thing I saw was stonk-related wishcasting that Apple was obviously turning its Xcode CI service into a full-blown AWS competitor that'd wipe the floor with any cloud service, given the 2x performance)
That's ok, but why skip the previous iteration then? Isn't the M2 only two generations behind? It's not that much older. It's also a marketing blurb, not a reproducible benchmark. Why leave out comparisons with the previous iteration even when you're just hand-waving over your own data?
There were some disingenuous comparisons throughout the presentation going back to A11 for the first Neural Engine and some comparisons to M1, but the M2 comparison actually makes sense.
I mean, they compared the new iPad Pro to an iPod Nano, that's just using your own history to make a point.
that aside, the M4 is about the Neural Engine upgrades over anything (which probably should have been compared to the M3)
That’s not to say that any of these problems are easy, just that there’s probably more lower hanging fruit in ARM land.
And don't underestimate the investment Apple made - it's likely at a similar level to the big x86 incumbents. I mean AMD's entire Zen development team cost was likely a blip on the balance sheet for Apple.
That's more bound by legal than technical reasons...
Launching at Computex in 2 weeks, https://www.windowscentral.com/hardware/laptops/next-gen-ai-...
there was one quiet "we haven't got anything like that in the contract we're signing with ARM" from someone else, and then radio silence. And you'd really think that would be major news, because it's massively impactful on pretty much everyone, since one of the major use-cases of ARM is as a base SOC to bolt your custom proprietary accelerators onto...
seemed like obvious bullshit at the time from a company trying to "publicly renegotiate" a licensing agreement they probably broke...
That’s why Apple can release a meaningfully new chip every year where it takes several for x86 manufacturers
Sure, maybe they can do better but at what cost and for what? The only thing Apple does truly better is performance per watt which is not something that is relevant for a large part of the market.
x86 stuff is still competitive performance wise, especially in the GPU department where Apple attempts are rather weak compared to what is on offer across the pond. The Apple Silicon switch cost a large amount of developer effort for optimisation, and in the process a lot of software compatibility was lost, it took a long time to get even the most popular softwares to get properly optimized and some software house even gave up on supporting macOS because it just wasn't worth the man hour investment considering the tiny market.
This is why I am very skeptical about the Qualcomm ARM stuff, it needs to be priced extremely well to have a chance, if consumers do not pick it up in droves, no software port is going to happen in a timely manner and it will stay irrelevant. Considering the only thing much better than the current x86 offering is the performance per watt, I do not have a lot of hope, but I may be pleasantly surprised.
Apple aficionados keep raving about battery life but it's not really something a lot of people care about (appart for smartphones, where Apple isn't doing any better than the rest of industry).
That’s all. They’re trying to convince iPad users to upgrade.
We’ll see what they do when they get to computers later this year.
I agree that iPad has more interesting software than android for use cases like video or music editing, but I don't do those on a tablet anyway.
I just can't imagine anyone updating their ipad M2 for this except a tiny niche that really wants that more power.
I’m vaguely considering this but entirely for the screen. The chip has been irrelevant to me for years, it’s long past the point where I don’t notice it.
These are 2048x2732 with 120Hz displays, that support 6k external displays. Gaming and art apps push them pretty hard. From the iPad user in my house, goin from the 2020 non M* iPad to a 2023 M2 iPad made a huge difference for the drawing apps. Better latency is always better for drawing, and complex brushes (especially newer ones), selections, etc, would get fairly unusable.
For gaming, it was pretty trivial to dip well below 60Hz with a non M* iPad, with some of the higher demand games like Fortnight, Minecraft (high view distance), Roblox (it ain't what it used to be), etc.
But, the apps will always gravitate to the performance of the average user. A step function in performance won't show up in the apps until the adoption follows, years down the line. Not pushing the average to higher performance is how you stagnate the future software of the devices.
I just don’t push it at all. The few games I play are not complicated in graphics or CPU needs. I don’t draw, 3D model, use Logic or Final Cut or anything like that.
I agree the extra power is useful to some people. But even there we have the M1 (what I’ve got) and the M2 models. But I bet there are plenty of people like me who mostly bought the pro models for the better screen and not the additional grunt.
The iPads always had a lot of power, people simply started paying more attention when the chip family was ported to PC.
Sure this is faster but enough to make people care?
It may depend heavily on what they announce is in the next version of iOS/iPadOS.
The M1 air is a very fast machine and is perfect for anyone doing normal things on the computer.
The M3 Air performs better than the M1 in raw numbers but outside of some truly CPU or GPU limited tasks you're not likely to actually notice the difference. The day to day behavior between the two is pretty similar.
If your current M1 works you're not missing out on anything. For the power/size/battery envelope the M1 Air was pretty awesome, it hasn't really gotten any worse over time. If it does what you need then you're good until it doesn't do what you need.
Well, the obvious answer is that those with older machines are more likely to upgrade than those with newer machines. The market for insta-upgraders is tiny.
edit: And perhaps an even more obvious answer: there are no iPads that contained the M3, so the comparison would be more useless. The M4 was just launched today exclusively in iPads.
And it can signal that "We are serious about iPad as a computer", using their latest chip.
Logical alignment to progresses in engineering (and manufacturing) packaged smartly to generate marketing capital for sales and brand value creation.
Wonder how the newer Macs will use these "tandem OLED" capabilities of the M4.
I don't think this is true. When they launched the M3 they compared primarily to M1 to make it look better.
As for CPU power use, of course that doesn't translate into doubling battery life because there are other components. And yes, it seems the OLED display uses more power so, all in all, battery life seems to be about the same.
I'm interested to see an M3 vs M4 performance comparison in the real world. IIRC the M3 was a questionable upgrade. Some things were better but some weren't.
Overall the M-series SoCs have been an excellent product however.
[1]: https://www.laptopmag.com/features/laptop-battery-life-claim...
EDIT: added link
That's just laughable, sorry. No one is particularly honest in marketing copy, but Apple is for sure one of the worst, historically. Even more so when you go back to the PPC days. I still remember Jobs on stage talking about how the G4 was the fasted CPU in the world when I knew damn well that it was half the speed of the P3 on my desk.
1) Graphs often are unannotatted.
2) Comparisons are rarely against latest generation products. (their argument for that has been that they do not expect people to upgrade yearly, so its showing the difference of their intended upgrade path).
3) They have conflated performance, for performance per watt.
However, when it comes to battery life, performance (for a task) or specification of their components (screens, ability to use external displays up to 6k, port speed etc) there are almost no hidden gotchas and they have tended to be trustworthy.
The first wave of M1 announcements were met with similar suspicion as you have shown here; but it was swiftly dispelled once people actually got their hands on them.
*EDIT:* Blaming a guy who's been dead for 13 years for something they said 50 years ago, and primarily it seems for internal use is weird. I had to look up the context but it seems it was more about internal motivation in the 70’s than relating to anything today, especially when referring to concrete claims.
"The G4 chip is nearly three times faster than the fastest Pentium III"
- Steve Jobs (1999) [1]
[1] https://www.wired.com/1999/08/lavish-debut-for-apples-g4/
And again, the guy has been dead for the better part of this millennium.
What have they shown of any product currently on the market, especially when backed with any concrete claim, that has been proven untrue-
EDIT: After reading your article and this one: https://lowendmac.com/2006/twice-as-fast-did-apple-lie-or-ju...; it looks like it was true in floating point workloads.
I don't have a horse in this race, Jobs lied or bent the truth all the time so it wouldn't surprise me, I'm just curious.
Just add them up, it’s the same number of Hertz!
But Steve that’s two procs vs one!
I think this is when Adobe was optimizing for Windows/intel and was single threaded, but Steve put out some graphs showing better perf on the Mac.
[1] https://www.latimes.com/archives/la-xpm-2000-apr-17-fi-20482...
It's certainly fair to say that twenty years ago Apple was marketing some of its PPC systems as "the first supercomputer on a chip"[^1].
> but it was nowhere near the performance of a supercomputer of that age.
That was not the claim. Apple did not argue that the G4's performance was commensurate with the state of the art in supercomputing. (If you'll forgive me: like, fucking obviously? The entire reason they made the claim is precisely because the latest room-sized supercomputers with leapfrog performance gains were in the news very often.)
The claim was that the G4 was capable of sustained gigaflop performance, and therefore met the narrow technical definition of a supercomputer.
You'll see in the aforelinked marketing page that Apple compared the G4 chip to UC Irvine’s Aeneas Project, which in ~2000 was delivering 1.9 gigaflop performance.
This chart[^2] shows the trailing average of various subsets of super computers, for context.
This narrow definition is also why the machine could not be exported to many countries, which Apple leaned into.[^3]
> Maybe similar performance to a supercomputer from the 1970's
What am I missing here? Picking perhaps the most famous supercomputer of the mid-1970s, the Cray-1,[^4] we can see performance of 160 MFLOPS, which is 160 million floating point operations per second (with an 80 MHz processor!).
The G4 was capable of delivering ~1 GFLOP performance, which is a billion floating point operations per second.
Are you perhaps thinking of a different decade?
[^1]: https://web.archive.org/web/20000510163142/http://www.apple....
[^2]: https://en.wikipedia.org/wiki/History_of_supercomputing#/med...
[^3]: https://web.archive.org/web/20020418022430/https://www.cnn.c...
This is marketing we're talking about, people see "supercomputer on a chip" and they get hyped up by it. Apple was 100% using the "supercomputer" claim to make their luddite audience think they had a performance advantage, which they did not.
> The entire reason they made the claim is
The reason they marketed it that way was to get people to part with their money. Full stop.
In the first link you added, there's a photo of a Cray supercomputer, which makes the viewer equate Apple = Supercomputer = I am a computing god if I buy this product. Apple's marketing has always been a bit shady that way.
And soon after that period Apple jumped off the PPC architecture and onto the x86 bandwagon. Gimmicks like "supercomputer on a chip" don't last long when the competition is far ahead.
If I had some pearls I would be clutching them right now.
That is also not in dispute. I am disputing your specific claim that Apple somehow suggested that the G4 was of commensurate performance to a modern supercomputer, which does not seem to be true.
> Apple was 100% using the "supercomputer" claim to make their luddite audience think they had a performance advantage, which they did not.
This is why context is important (and why I'd appreciate clarity on whether you genuinely believe a supercomputer from the 1970s was anywhere near as powerful as a G4).
In the late twentieth and early twenty-first century, megapixels were a proxy for camera quality, and megahertz were a proxy for processor performance. More MHz = more capable processor.
This created a problem for Apple, because the G4's SPECfp_95 (floating point) benchmarks crushed Pentium III at lower clock speeds.
PPC G4 500 MHz - 22.6
PPC G4 450 MHz - 20.4
PPC G4 400 MHz - 18.36
Pentium III 600 MHz – 15.9
For both floating point and integer benchmarks, the G3 and G4 outgunned comparable Pentium II/III processors.
You can question how this translates to real world use cases – the Photoshop filters on stage were real, but others have pointed out in this thread that it wasn't an apples-to-apples comparison vs. Wintel – but it is inarguable that the G4 had some performance advantages over Pentium at launch, and that it met the (inane) definition of a supercomputer.
> The reason they marketed it that way was to get people to part with their money. Full stop.
Yes, marketing exists to convince people to buy one product over another. That's why companies do marketing. IMO that's a self-evidently inane thing to say in a nested discussion of microprocessor architecture on a technical forum – especially when your interlocutor is establishing the historical context you may be unaware of (judging by your comment about supercomputers from the 1970s, which I am surprised you have not addressed).
I didn't say "The reason Apple markets its computers," I said "The entire reason they made the claim [about supercomputer performance]…"
Both of us appear to know that companies do marketing, but only you appear to be confused about the specific claims Apple made – given that you proactively raised them, and got them wrong – and the historical backdrop against which they were made.
> In the first link you added, there's a photo of a Cray supercomputer
That's right. It looks like a stylized rendering of a Cray-1 to me – what do you think?
> which makes the viewer equate Apple = Supercomputer = I am a computing god if I buy this product
The Cray-1's compute, as measured in GFLOPS, was approximately 6.5x lower than the G4 processor.
I'm therefore not sure what your argument is: you started by claiming that Apple deliberately suggested that the G4 had comparable performance to a modern supercomputer. That isn't the case, and the page you're referring to contains imagery of a much less performant supercomputer, as well as a lot of information relating to the history of supercomputers (and a link to a Forbes article).
> Apple's marketing has always been a bit shady that way.
All companies make tradeoffs they think are right for their shareholders and customers. They accentuate the positives in marketing and gloss over the drawbacks.
Note, too, that Adobe's CEO has been duped on the page you link to. Despite your emphatic claim:
> Apple was 100% using the "supercomputer" claim to make their luddite audience think they had a performance advantage, which they did not.
The CEO of Adobe is quoted as saying:
> “Currently, the G4 is significantly faster than any platform we’ve seen running Photoshop 5.5,” said John E. Warnock, chairman and CEO of Adobe.
How is what you are doing materially different to what you accuse Apple of doing?
> And soon after that period Apple jumped off the PPC architecture and onto the x86 bandwagon.
They did so when Intel's roadmap introduced Core Duo, which was significantly more energy-efficient than Pentium 4. I don't have benchmarks to hand, but I suspect that a PowerBook G5 would have given the Core Duo a run for its money (despite the G5 being significantly older), but only for about fifteen seconds before thermal throttling and draining the battery entirely in minutes.
In my experience, I can confirm that this is just not true. The secret is heavy reliance on swap. It's still the case that 1GB = 1GB.
You are entirely (100%) wrong, but, sadly, NDA...
If there's any publicly available data to the contrary I'd love to read it. Anecdotally I haven't seen a significant difference between zswap on Linux and macOS memory compression in terms of compression ratios, and on the workloads I've tested zswap tends to be faster than no memory compression on x86 for many core machines.
My experience is that I can still tell when the OS is unhappy when I demand more RAM than it can give. MacOS is still relatively responsive around this range, which I just attributed to super fast swapping. (I'd assume memory compression too, but I usually run into this trouble when working with large amounts of poorly-compressible data.)
In either case, I know it's frustrating when someone is confidently wrong but you can't properly correct them, so you have my apologies
Is an occasional statement that they get pushback on really worse than what other brands do?
As an example from a competitor, take a look at the recent firestorm over Intel’s outlandish anti-AMD marketing:
https://wccftech.com/intel-calls-out-amd-using-old-cores-in-...
FWIW: the language upthread was that it was laughable to say Apple was the most honest. And I stand by that.
Though the author also made clear in their second sentence that they think Apple is one of the worst when it comes to marketing claims, so I don’t think your characterization is totally accurate either.
If you go for the base model, you are in for a bad time, 256GB with heavy swap and no dedicated GPU memory (making the 8GB even worse) is just plain stupid.
This what the Apple fanboys don't seem to get, their base model at somewhat affordable price are deeply incompetent and if you start to load it up the pricing just do not make a lot of sense...
Anyway, I manage a few M1 and M3 machines with 256/8 configs and they all run just as fast as 16 and 32 machines EXCEPT for workloads that need more than 8GB for a process (virtualization) or workloads that need lots of video memory (Lightroom can KILL an 8GB machine that isn't doing anything else...)
The 8GB is stupid discussion isn't "wrong" in the general case, but it is wrong for maybe 80% of users.
Isn't that exactly the upthread contention: Apple's magic compressed swap management is still swap management that replaces O(1) fast(-ish) DRAM access with thousands+ cycle page decompression operations. It may be faster than storage, but it's still extremely slow relative to a DRAM fetch. And once your working set gets beyond your available RAM you start thrashing just like VAXen did on 4BSD.
And if you go up in specs the bandwidth of Apple silicon has to be compared to the bandwidth of a combo with dedicated GPU. The bandwidth of dedicated GPUs is very high and usually higher than what Apple Silicon gives you if you consider the RAM bandwidth for the CPU.
It's a bit more complicated but that's marketing for you. When it comes to speed Apple RAM isn't faster than what can be found in high-end laptops (or desktops for that matter).
I got the base model M1 Air a couple of years back and whilst I don't do much gaming I do do C#, Python, Go, Rails, local Postgres, and more. I also have a (new last year) Lenovo 13th gen i7 with 16GB RAM running Windows 11 and the performance with the same load is night and day - the M1 walks all over it whilst easily lasting 10hrs+.
Note that I'm not a fanboy; I run both by choice. Also both iPhone and Android.
The Windows laptop often gets sluggish and hot. The M1 never slows down and stays cold. There's just no comparison (though the Air keyboard remains poor).
I don't much care about the technical details, and I know 8GB isn't a lot. I care about the experience and the underspecced Mac wins.
That said you're right about lots of RAM in that I wouldn't bother using the 8GB M1 Air for Docker or running LLMs (it can run SD for images though, but very slowly). Partly that's why I have the Lenovo. You need to pick the right machine for the job at hand.
And I agree that in pure performance, the Apple Silicon Macs will kill it; however, I am really skeptical that an 8GB model would give you a better experience overall. Faster for long compute operations sure, but then you have to deal with all the small slowdown from constant swapping. Unless you stick to a very small amounts of apps and very small amounts of tabs at the same time (which is rather limiting) I don't know how you do it. I don't want to call you a liar but maybe you are emotionally attached (just like I am sometimes) to the device to realize it, or maybe the various advantages of the Mac make you ignore the serious limitations that come with it.
Everyone has their own sets of tradeoffs but my argument is that you can deal with the 8GB Apple Silicon devices you are very likely to be well served by a much cheaper device anyway (like half as cheap).
> you have to deal with all the small slowdown from constant swapping
That just doesn't happen. As I responded to another post, though, I don't do Docker or LLMs on the M1 otherwise you'd probably be right.
> Unless you stick to a very small amounts of apps and very small amounts of tabs at the same time
It's really common to have approaching 50+ tabs open at once. And using Word is often accompanied by VS Code, Excel, Affinity Designer, DotNet, Python, and others due to the nature of what I'm doing. No slowdown.
> maybe you are emotionally attached
I am emotionally attached to the device. Though as a long-time Mac, Windows, and Linux user I'm neither blinkered nor tribal - the attachment is driven by the experience and not the other way around.
> maybe the various advantages of the Mac make you ignore the serious limitations that come with it
There are indeed limitations. 8GB is too small. The fact that for what I do it has no impact doesn't mean I don't see that.
> you can deal with the 8GB Apple Silicon devices you are very likely to be well served by a much cheaper device anyway (like half as cheap)
I already have better Windows laptops than that, and I know that going for a Windows laptop that's half as cheap as the entry level Air would be nothing like as nice because the more expensive ones already aren't (the Lenovo was dearer than the Air).
---
To conclude, you have to use the right tool for the job. If the nature of the task intrinsically needs lots of RAM then 8GB is not good enough. But when it is enough it runs rings around equivalent (and often 'better') Windows machines.
Confirmed here: https://computer.howstuffworks.com/question299.htm (and elsewhere.)
A year later I was doing bonkers (for the time) photoshop work on very large compressed tiff files and my G4 laptop running at 400Mhz was more than 2x as fast as PIIIs on my bench.
Was it faster all around? I don't know how to tell. Was Apple as honest as I am in this commentary about how it mattered what you were doing? No. Was it a CPU that was able to do some things very fast vs others? I know it was.
On top of that Intel increased frequency faster than Apple could handle. And after the release of the Pentium 4, the G4s became very noncompetitive so fast that one would question what could save Apple (later, down the road, Intel it turns out).
They tried to salvage it with the G5s but those came with so many issues that even their bi-proc water-cooled were just not keeping up. I briefly owned of those after repairing it for "free" using 3 of them, supposedly dead; the only thing worth a dam in that was the GPU. Extremely good hardware in many ways but also very weak for so many things that it had to be used only for very specific tasks, otherwise a cheap Intel PC was much better.
Which is precisely why right after they went with Intel. After years of subpar performance on laptops because they were stuck at G4 (not even high frequency).
Now I know from your other comments that you are a very strong believer and I'll admit that there were many reasons to use a Mac (software related) but please stop pretending they were performance competitive because that's just bonkers. If they were, the Intel switch would never have happend in the first place...
Okay, but your example was about battery life:
> LIke when they said an Macbook Air would last 10+ hours and third-party reviewers would get 8-9+ hours. All the while, Dell or HP would claim 19 hours and you'd be lucky to get 2 eg [1]
And even then, they exaggerated their claims. And your link doesn't say anything about HP or Dell claiming 19 hour battery life.
Apple has definitely exaggerated their performance claims over and over again. The Apple silicon parts are fast and low power indeed, but they've made ridiculous claims like comparing their chips to an nVidia RTX 3090 with completely misleading graphs
Even the Mac sites have admitted that the nVidia 3090 comparison was completely wrong and designed to be misleading: https://9to5mac.com/2022/03/31/m1-ultra-gpu-comparison-with-...
This is why you have to take everything they say with a huge grain of salt. Their chip may be "twice" as power efficient in some carefully chosen unique scenario that only exists in an artificial setting, but how does it fare in the real world? That's the question that matters, and you're not going to get an honest answer from Apple's marketing team.
> HP gave the 13-inch HP Spectre x360 an absurd 22.5 hours of estimated battery life, while our real-world test results showed that the laptop could last for 12 hours and 7 minutes.
> Speaking of the ThinkPad P72, here are the top three laptops with the most, er, far out battery life claims of all our analyzed products: the Lenovo ThinkPad P72, the Dell Latitude 7400 2-in-1 and the Acer TravelMate P6 P614. The three fell short of their advertised battery life by 821 minutes (13 hours and 41 mins), 818 minutes (13 hours and 38 minutes) and 746 minutes (12 hours and 26 minutes), respectively.
Dell did manage to be one of the top 3 most absurd claims though.
Dell and IBM were lying about battery life before OSX was even a thing and normal people started buying MacBooks. Dell and IBM will be lying about battery life when the sun goes red dwarf.
Reviewers and individuals like me have always been able to get 90% of Apple’s official battery times without jumping through hoops to do so. “If you were very careful” makes sense for an 11% difference. A ten hour difference is fucking bullshit.
Apple does usually explain their testing methodology and they don’t cheat on benchmarks like some other companies. It’s just that the results are still marketing and should be treated as such.
Outlandish claims notwithstanding, I don’t think anyone can deny the progress they achieved with their CPU and especially GPU IP. Improving performance on complex workloads by 30–50% in a single year is very impressive.
I guess you weren't around during the PowerPC days... Because that's a laughable statement.
We need more tanks in commercials.
A PC half the price was smoking their top of the line stuff.
What made it worth it at the time (I felt) was the software. Today I'm really don't think so, software has improved overall in the industry and there is not a lot of things "Mac specific" that makes it a clear-cut choice.
As for the performance I can't believe all the Apple silicon hype. Sure, it gets good battery life given you use strictly Apple software (or software optimized for it heavily) but in mixed workload situation it's not that impressive.
Using the M2 MacBook Pro of a friend I figured I could get maybe 4-5 hours out of its best case scenario which is better than the 2-3 hours you would get from a PC laptop but also not that great considering the price difference.
And when it comes to performance it is extremely unequal and very lackluster for many things. Like there is more lag launching Activity Monitor on a 2K++ MacBook Pro than launching task manager on a 500 PC. This is a small somewhat stupid example but it does tell the overall story.
They talk a big game but in reality, their stuff isn't that performant in the real world.
And they still market games when one of their 2K laptops plays Dota 2 (a very old, relatively ressource efficient game) worse than a cheapo PC.
Any electron apps on it?
I went the way of only Apple and Apple optimized software for quite a while but I just can't be bothered anymore, considering the price of the hardware and nowadays the price of subscription software.
And this is exactly my argument I you use the hardware in a very specific way, you get there but it is very limiting, annoying and inacceptable considering the pricing.
It's like saying that a small city car gets more gas mileage when what one needs is actually a capable truck. It's not strictly wrong but also not very helpful.
I think the Apple Silicon laptops are very nice if you can work within the limitations, but the moment you start pushing on those you realize they are not really worth the money. Just like the new iPad Pro they released; completely awesome hardware but how many people can actually work within the limitations of iPad OS to make the price not look like a complete ripoff. Very few I would argue.
Today, Apple Silicon is smoking all but the top end Intel chips, while using a fraction of the power.
Yes and no. They'll always be honest with the claim, but the scenario for the claimed improvement will always be chosen to make the claim as large as possible, sometimes with laughable results.
Typically something like "watch videos for 3x longer <small>when viewing 4k h265 video</small>" (which means they adapted the previous gen's silicon which could only handle h264).
Isn't that going to torch performance? My i9-9900 has a base frequency of 3.6 Ghz and a turbo of 5.0 Ghz. Disabling the turbo would create a 28% drop in performance.
I suppose if everything else on the system is configured to use as little power as possible, then it won't even be noticed. But seeing as CPUs underclock when idle (I've seen my i9 go as low as 1.2 Ghz), I'm not sure disabling turbo makes a significant impact except when your CPU is being pegged.
For literal YEARS, Apple battery life claims were a running joke on how inaccurate and overinflated they were.
What time period are you thinking about for Apple? I’ve been using their laptops since the last G4 which is twenty years. They’ve always been substantially more accurate about battery times.
For example I would be surprised if there is any laptop, which is sufficiently fast for my usage, and it's battery life is more than 2-3 hours top. Heck, I have several laptops and all of them dies in one-one and a half hours. But of course, I never optimized for battery life, so who knows. So in my case, all of them are lying equally. I don't even check battery life for 15 years now. It's a useless metric for me, because all of them are shit.
But of course for people who don't need to use VMs, run several "micro"services at once, have constant internet transfer and have 5+ Intellij project open at the same time which caching several millions LOC, while gazillion web pages are open, maybe there is a difference, for me it doesn't matter whether it's one or one and a half hours.
In nearly every single release, their claims are well above actual performance.
I'm not sure what you mean by "of all times" but half the battery usage of the processor definitely doesn't translate into double the battery life since the processor is not the only thing consuming power.
I can have my laptop with nothing on screen, and the battery still points to TrendMicro and others as the cause of heavy battery drain while my laptop seemingly idles.
I recently upgraded my personal laptop to the M3 MacBook pro and the difference is astonishing. I almost never use it plugged in because I genuinely get close to that 20 hour reported battery life. Last weekend I played a AAA Video Game through Xbox Cloud Gaming (awesome for mac gamers btw) and with essentially max graphics (rendered elsewhere and streamed to me of course), I got sucked into a game for like 5 hours and lost only 8% of my battery during that time, while playing a top tier video game! It really blew my mind. I also use GoLand IDE on there and have managed to get a full day of development done using only about 25-30% battery.
So yeah, whatever Apple is doing, they are doing it right. Performance without all the spyware that your work gives you makes a huge difference too.
That's mindblowing. Especially since my personal laptop is a Thinkpad X1 Extreme. I can't leave that unplugged at all.
Even considering the marketing, best case scenario you would be between 27 and 41% battery consumption for 5h of runtime. The actual number will be lower than that because you probably don't use the MBP at the low brightness they use for marketing benchmarks and game streaming constantly requires power for the wifi chip (video can buffer, hence the lower consumption).
There is no way to say this nicely, but can you stop lying ?
Compared to the competition, I'd trust Apple much more than the Windows laptop OEMs.
This is an absurd interpretation. Nobody hears that and says "they made the screen use half the energy".
The N3 process is in the A17 Pro, the M3, M3 Pro, and M3 Max. The A17 Pro name seems to imply you won't find it trickle down on the regular iPhones next year. So we'll see that processor only this year in phones, since Apple discontinues their Pro range of phones every year; only the regular phones trickle downrange lowering their prices. The M3 devices are all Macs that needed an upgrade due to their popularity: the Macbook Pro and Macbook Air. They made three chips for them, but they did not make an M3 Ultra for the lower volume desktops. With the announcement of an M4 chip in iPads today, we can expect to see the Macbook Air and Macbook Pro upgraded to M4 soon, with the introduction of an M4 Ultra to match later. We can now expect those M3 devices to be discontinued instead of going downrange in price.
That would leave one device with an N3 process chip: the iMac. At its sale level, I wouldn't be surprised if all the M3 chips that will go into it will be made this year, with the model staying around for a year or two running on fumes.
For instance, Apple supposedly required a deal where they only paid TSMC for usable chips per N3 wafer, and not for the entire wafer.
https://arstechnica.com/gadgets/2023/08/report-apple-is-savi...
The next iPhone generation is said to be a return to form with all models using the same SOC on the revised version of the 3nm node.
> Code from the operating system also indicates that the entire iPhone 16 range will use a new system-on-chip – t8140 – Tahiti, which is what Apple calls the A18 chip internally. The A18 chip is referenced in relation to the base model iPhone 16 and 16 Plus (known collectively as D4y within Apple) as well as the iPhone 16 Pro and 16 Pro Max (referred to as D9x internally)
https://www.macrumors.com/2023/12/20/ios-18-code-four-new-ip...
[1] https://semiwiki.com/semiconductor-manufacturers/tsmc/322688...
[2] https://semiengineering.com/sram-scaling-issues-and-what-com...
[3] https://semiengineering.com/sram-in-ai-the-future-of-memory/
I can see why AMD started putting the SRAM on top.
From what I can gather the key aspects are that decreased feature sizes lead to more variability between transistors, but also to less margin between on-state and off-state. Thus a kind of double-whammy. In logic circuits you're constantly overwriting with new values regardless of what was already there, so they're not as sensitive to this, while the entire point of a memory circuit is to reliably keep values around.
Alternate transistor designs such as FinFET, Gate-all-around and such can provide mitigation of some of this, say by reducing transistor-to-transistor variability by a factor, but can't get around root issue.
[1]: https://semiengineering.com/sram-scaling-issues-and-what-com...
Average performance per watt doubling time is 2.6 years: https://newsroom.arm.com/blog/performance-per-watt#:~:text=T....
[1] https://www.apple.com/newsroom/2022/06/apple-unveils-m2-with...
Same for Watts per bit.
There's just a lot more pixels and bits.
That said, the function keys make me think "and it runs macOS" is coming, and THAT would be extremely compelling.
Unlike MS that went with the Big Bang in your face approach that was oh-so successful.
We now have 'content consumption platforms' and 'content creation platforms'.
While attempts have been made to try and enable some creation on locked-down touchscreen devices, you're never going to want to try and operate a fully-featured version of Photoshop, Maya, Visual Studio, etc on them. And if you've got a serious workstation with multiple large monitors and precision input devices, you don't want to have dumbed-down touch-centric apps forced upon you Win8-style.
The bleak future that seems likely is that the 'content creation platforms' become ever more niche and far more costly. Barriers to entry for content creators are raised significantly as mainstream computing is mostly limited to locked-down content consumption platforms. And Linux is only an option for as long as non-locked-down hardware is available for sensible prices.
Maybe the end game for Apple isn’t the full convergence, but just having a touch screen on the Mac.
Not much point having a touchscreen on a Macbook (or any laptop really), unless the hardware has a 'tablet mode' with a detachable or fold-away keyboard.
There are plenty of laptops that do have touchscreens, and it has always felt more like a gimmick than a useful hardware interface.
Honestly, the biggest barrier to creativity is thinking you need a specific concept of a "serious workstation" to do it. Plenty of people are using $2k+ desktops just to play video games.
Then there's the whole dealing with lots of files and version control side of things, essential for working as part of a team. Think about creating (and previewing, and finally uploading) a very simple web page, just HTML and a couple of images, entirely on an iPad. While it's probably quite possible these days, I suspect the workflow would be abysmal compared to a 'proper computer' where the file system isn't hidden from you and where you're not constantly switching between full-screen apps.
And that's before you start dealing with anything with significant numbers of files in deep directory structures, or doing more technical image creation (e.g. dealing with alpha channels). And of course, before testing your webpage on all the major browsers. Hmm...
It's rather disingenuous to pretend that an iPad can be sufficient. At its price tag it is still a rather extremely expensive accessory and people pretending otherwise are just full of it. There are enough reviews/testimonies saying as much (even from the diehard fans) for it to be an obvious fact.
Respectfully, I disagree partially. It has never been easier or more affordable to get into creating content. You can create cinema grade video with used cameras that sell for a few hundred dollars. You can create pixar level animation on open source software, and a pretty cheap computer. A computer that can edit a 4k video costs less than the latest iPhone. There are people that create plenty of content with just a phone. Simply put it is orders of magnitude cheaper and easier to create content than it was less than two decades ago, which is why we are seeing so much content getting made. I used to work for a newspaper and it used to be a lot harder and more expensive to produce audio visual media.
My strong feeling is that the problem of content being locked into platforms has precious little to do with consumption oriented hardware, and more to do with the platforms. Embrace -> extinguish -> exlcusivity -> enshittify seems to be the model behind basically anything that hosts user content these days.
This is a completely artificial creation by Apple and Google to extract more money from you. Nothing technical prevents one from using a full OS on a phone today.
Sent from my Librem 5 running desktop GNU/Linux.
Apple then later took the tablet demo technology, wrapped it up in a very stripped-down OS X with a different window server and UI library, and called it iPhone OS. Apple was very clear from the beginning that Fingers Can't Use Mouse Software, Damn It, and that the whole ocean needed to be boiled to support the new user interface paradigm[1]. They even have very specific UI rules specifically to ensure a finger never meets a desktop UI widget, including things like iPad Sidecar just not forwarding touch events at all and only supporting connected keyboards, mice, and the Apple Pencil.
Microsoft's philosophy has always been the complete opposite. Windows XP through 7 had tablet support that amounted to just some affordances for stylus users layered on top of a mouse-only UI. Windows 8 was the first time they took tablets seriously, but instead of just shipping a separate tablet OS or making Windows Phone bigger, they turned it into a parasite that ate the Windows desktop from the inside-out.
This causes awkwardness. For example, window management. Desktops have traditionally been implemented as a shared data structure - a tree of controls - that every app on the desktop can manipulate. Tablets don't support this: your app gets one[2] display surface to present their whole UI inside of[3], and that surface is typically either full-screen or half-screen. Microsoft solved this incongruity by shoving the entire Desktop inside of another app that could be properly split-screened against the new, better-behaved tablet apps.
If Apple were to decide "ok let's support Mac apps on iPad", it'd have to be done in exactly the same way Windows 8 did it, with a special Desktop app that contained all the Mac apps in a penalty box. This is so that they didn't have to add support for all sorts of incongruous, touch-hostile UI like floating toolbars, floating pop-ups, global menus, five different ways of dragging-and-dropping tabs, and that weird drawer thing you're not supposed to use anymore, to iPadOS. There really isn't a way to gradually do this, either. You can gradually add feature parity with macOS (which they should), but you can't gradually find ways to make desktop UI designed by third-parties work on a tablet. You either put it in a penalty box, or you put all the well-behaved tablet apps in their own penalty boxes, like Windows 10.
Microsoft solved Windows 8's problems by going back to the Windows XP/Vista/7 approach of just shipping a desktop for fingers. Tablet Mode tries to hide this, but it's fundamentally just window management automation, and it has to handle all the craziness of desktop. If a desktop app decides it wants a floating toolbar or a window that can't be resized[4], Tablet Mode has to honor that request. In fact, Tablet Mode needs a lot of heuristics to tell what floating windows pair with which apps. So it's a lot more awkward for tablet users in exchange for desktop users having a usable desktop again.
[0] Given what I've heard about Jobs I don't think Jobs was psychologically capable of having friends, but I'll use the word out of convenience.
[1] Though the Safari team was way better at building compatibility with existing websites, so much so that this is the one platform that doesn't have a deep mobile/desktop split.
[2] This was later extended to multiple windows per app, of course.
[3] This is also why popovers and context menus never extend outside their containing window on tablets. Hell, also on websites. Even when you have multiwindow, there's no API surface for "I want to have a control floating on top of my window that is positioned over here and has this width and height".
[4] Which, BTW, is why the iPad has no default calculator app. Before Stage Manager there was no way to have a window the size of a pocket calculator.
RIP Graffiti.
It was kind of successful, touchscreen laptops see pretty big sales nowadays. I don't know what crack they were smoking with Windows 8.0 though.
It's a shame, because it's definitely powerful enough, and the idea of traveling with just an iPad seems super interesting, but I imagine they will not extend those features to any devices besides macs
Crostini is the new containerized version that is both officially supported and integrated into ChromeOS
That's great, but you need an M series chip in your mac for that to work so backwords compatibility only goes back a few years at this point, which is fine for corporate upgrade cycles but might be a bit short for consumers at this time. But it will be fine in the future.
M-class MacBooks can already run many iPhone and iPad apps.
Do you really want your OS using 100% of CPU?
Michelin-starred restaurants not only have top-tier chefs. They have buyers who negotiate with food suppliers to get the best ingredients they can at the lowest prices they can. Having a preferential relationship with a good supplier is as important to the food quality and the health of the business as having a good chef to prepare the dishes.
Apple has top-tier engineering talent but they are also able to negotiate preferential relationships with their suppliers, and it's both those things that make Apple a phenomenal tech company.
If the magic comes mostly from TSMC, there's a good chance for these claims to be true and to have a series of better chips coming on the other platforms as well.
I’m filing this into the bin with all the other “This next Qualcomm chip will close the performance gap” claims made over the past decade. Maybe this time it’ll be true. I wouldn’t bet on it.
Basically we'd need some basis to believe they'll be progressively improving at more or less the same pace as Intel's or Apple's chips to get on board with ARM laptops for Windows/linux.
Otherwise I don't see software makers care enough to port their build to ARM as well.
That is pretty crazy.
Or am I missing something?
https://www.trendforce.com/news/2024/05/06/news-apple-m4-inc....
But people like to assign credit solely to certain spaces if it suits their narrative (lately, Apple isn't actually all that special at designing their chips, it's all solely the process advantage)
In contrast, when Apple's CPU and GPU competitors get access to TSMC's new processes after Apple's exclusivity period expires, they achieve similar levels of performance (except for Qualcomm because they don't target the high end of CPU performance, but AMD does).
In general, OLED screens seem to have an efficiency around 20≈30%. Some research departments seem to be trying to bump that up [https://www.nature.com/articles/s41467-018-05671-x] which I'd be more hopeful on…
…but, honestly, at some point you just hit the limits of physics. It seems internal scattering is already a major problem; maybe someone can invent pixel-sized microlasers and that'd help? More than 50-60% seems like a pipe dream at this point…
…unless we can change to a technology that fundamentally doesn't emit light, i.e. e-paper and the likes. Or just LCD displays without a backlight, using ambient light instead.
[0] https://onyxboox.com/boox_mirapro
edit: "25, not "27
I was thinking, like, a couple hundred dollar Kindle the size of a big iPad I can plug into a laptop for text-editing out and about. Hell, for my purposes I'd love an integrated keyboard.
Basically a second, super-lightweight laptop form-factor I can just plug into my chonky Macbook Pro and set on top of it in high-light environments when all I need to do is edit text.
Honestly not a compelling business case now that I write it out, but I just wanna code under a tree lol
It is nice for some very specific use cases. (They're in the publishing/typesetting business. It's… idk, really depends on your usage patterns.)
Other than that, yeah, the technology just isn't there yet.
I can't replace my desktop monitor with eink because I occasionally play video games. I can't use a 2nd monitor because I live in a small apartment.
I can't replace my laptop screen with greyscale because I need syntax highlighting for programming.
Hmm, emacs on an epaper screen might be great if it had all the display update optimization and "slow modem mode" that Emacs had back in the TECO days. (The SUPDUP network protocol even implemented that at the client end and interacted with Emacs directly!)
Evidence can be seen when opening up iOS apps, which seem to glitch out and reveals the brighter backlight [1]. Notice how #FFFFFF white isn't the same brightness as the white in the iOS app.
It also just doesn't seem ideal that some apps (iOS) appear much brighter than the rest of the system. HDR support in macOS is a complete mess, although I'm not sure if Windows is any better.
I don't expect an M4 macbook to last any longer than an M2 macbook of otherwise similar specs; they will spend that extra power budget on things other than the battery life specification.
Old: 28.65 Wh (11") / 40.88 Wh (13"), up to 10 hours of surfing the web on Wi-Fi or watching video.
New: 31.29 Wh (11") / 38.99 Wh (13"), up to 10 hours of surfing the web on Wi-Fi or watching video.
Knowing nothing else about the technology, I assumed that would make OLED displays more efficient.
White background document editing, etc., will be worse, and this is rather common.
When you say "up to 10 hours" most people will think "oh nice that's an entire day" and be fine with it. It's what they're used to.
Turning that into 12 hours might be possible but are the tradeoffs worth it? Will enough people buy the device because of the +2 hour battery life? Can you market that effectively? Or will putting in a nicer fancy display cause more people to buy it?
We'll never get significant battery life improvements because of this, sadly.
Doing basic web navigation with some music in the background, my old M1 Pro has short bursts at ~5W (for the entire SoC) when navigating around, a pair of watts for mild webapps (e.g. checking various channels in discord), and typing into this here textbox it's sitting happy at under half a watt, with the P-cores essentially sitting idle and the E cores at under 50% utilisation.
With a 100Wh battery that would be a "potential" of 150 hours or so. Except nobody would ever sell it for that, because between the display and radios the laptop's actually pulling 10~11W.
However, we have more CPU cores, a newer core design, and a newer process node which would all contribute to improving multicore CPU performance.
Also, Apple is conservative on clock speeds, but those do tend to get bumped up when there is a new process node as well.
I believe that OLED is much more power hungry than the previous display type (LED backlit LCD of some type?). I could be wrong, but in TV land that's the case...
Could explain, at least partly, why run time isn't greatly increased.
I.e. would it sit between, or closer to M2 or M4?
I think Apple's design choices had a huge impact on the M1's performance but from there on out I think it's mostly due to TSMC.
It can deliver the same performance as itself at just a fourth of the power than it's using? That's incredible!